architecture-review-full

name	architecture-review-full
description	[Architecture] Use when auditing the ENTIRE project architecture and production readiness in one pass — bundles architecture-review + architecture-scalability-review + production-readiness-review at project or diff scope, then synthesizes one consolidated Architecture Health Report.

Codex compatibility note:

• Invoke repository skills with $skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.
• Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.
• User-question prompts mean to ask the user directly in Codex.
• Ignore Claude-specific mode-switch instructions when they appear.
• Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.
• Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.
• Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.
• For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.
• If a required step/tool cannot run in this environment, stop and ask the user before adapting.

Codex Project-Reference Loading (No Hooks)

Codex uses static project-reference loading instead of runtime-injected project docs. When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.

Always read:

• docs/project-config.json (project-specific paths, commands, modules, and workflow/test settings)
• docs/project-reference/docs-index-reference.md (routes to the full docs/project-reference/* catalog)
• docs/project-reference/lessons.md (always-on guardrails and anti-patterns)

Missing/stale context route: If docs/project-config.json, the docs index, lessons.md, CLAUDE.md, AGENTS.md, or any task-required reference doc is missing or stale, auto-run $project-init or the narrow setup route ($project-config, $docs-init, $scan-all, $scan --target=<key>, $claude-md-init) before ordinary project-specific work. If Codex mirrors or AGENTS.md are missing/stale, ask the user to run $sync-codex; do not auto-run it.

Situation-based docs:

• Project structure/architecture/tech-stack/deployment/setup (any layer — backend, frontend, or infra): project-structure-reference.md
• Backend/CQRS/API/domain/entity changes: backend-patterns-reference.md, domain-entities-reference.md
• Frontend/UI/styling/design-system: frontend-patterns-reference.md, scss-styling-guide.md, design-system/README.md
• Spec authoring, docs/specs/ pathing, or TC format: feature-spec-reference.md, spec-system-reference.md, spec-principles.md
• Behavior/public-contract changes or spec-test-code sync: workflow-spec-test-code-cycle-reference.md plus the spec docs above
• Derived spec indexes/ERDs/reimplementation guides: spec-system-reference.md and source Feature Specs under docs/specs/
• Integration test implementation/review: integration-test-reference.md
• E2E test implementation/review: e2e-test-reference.md
• Code review/audit work: code-review-rules.md plus domain docs above based on changed files

Do not read all docs blindly. Start from docs-index-reference.md, then open only relevant files for the task.

[BLOCKING] Execute skill steps in declared order. NEVER skip, reorder, or merge steps without explicit user approval. [BLOCKING] Before each step or sub-skill call, update task tracking: set in_progress when step starts, set completed when step ends. [BLOCKING] Every completed/skipped step MUST include brief evidence or explicit skip reason. [BLOCKING] If Task tools are unavailable, create and maintain an equivalent step-by-step plan tracker with the same status transitions.

Quick Summary

Goal: Audit the WHOLE project's architecture, scalability posture, and production readiness in ONE pass by orchestrating the three deliberately-non-overlapping sibling reviewers, then de-duplicating their intentional cross-references into ONE consolidated Architecture Health Report — this skill is a THIN orchestrator, it does NOT re-implement any of the three reviews.

Summary:

• Purpose: resolve scope once, fan three reviewers out as parallel read-only sub-agents behind an all-return barrier, PROGRESSIVELY synthesize + dedup each child's findings into ONE report file (status IN PROGRESS → FINISHED), run a $why-review fix gate that walks each review face, then finalize the combined verdict. Read-only until findings are validated — fixes route to a downstream $plan or feature flow.
• The three children — deliberately non-overlapping siblings that cross-reference each other, so their findings MUST be deduped:
  • architecture-scalability-review (subagent architect) — project-grading scorecard /20 + pass/fail gates. ALWAYS grades the project, even under diff scope (project-grader by design, "not the every-change diff reviewer").
  • architecture-review (subagent architect) — diff/scope-scoped 13-category PASS/WARN/BLOCKED compliance. Its Category 11 delegates full scalability/coupling grading to architecture-scalability-review.
  • production-readiness-review (subagent code-reviewer) — service/API SRE /24 + 8-item Extended SRE Readiness gate. architecture-scalability-review routes runtime readiness here.
• This skill runs INLINE in the main session because it spawns sub-agents; the three children are each 25k–34k tokens and CANNOT run inline together — they MUST be sub-agents.
• Dedup is the core value. Because the three siblings intentionally cross-reference each other, the same underlying issue surfaces from multiple angles; record it ONCE citing every source, preserve each child's route-to-sibling pointers. — why: undeduped, three intentionally-cross-referencing reviewers inflate severity counts and bury distinct issues.
• Coverage sweep + self-audit are orchestrator-only duties (Step 4). After Faces merged: 3/3, sweep the merged report against the design-review script (architecture-knowledge.md §20.2) and record every unanswered question as an INFO Coverage gap line; frame remaining risk against the five judgments (§20.4); then run the 11 thinking red flags (§20.3) across the merged findings before Step 5. — why: three correctly-in-lane reviewers cannot see a question that belongs to no lane, and synthesis is where their confirmation biases compound.

Workflow:

1. Step 1: Resolve Scope — $ARGUMENTS or ask the user directly; map the chosen scope to each child's args.
2. Step 2: Load Project Reference Docs Once — warm shared context before fan-out.
3. Step 3: Parallel Fan-Out (all-return barrier) — spawn all three read-only sub-agents in ONE message; advance only after ALL three return.
4. Step 4: Progressive Synthesis (IN PROGRESS) — open the ONE consolidated report at status 🚧 IN PROGRESS when fan-out starts; merge + dedup each child's findings into it AS that child returns — never held in memory to the end; then run the §20.2 coverage sweep and the §20.3 self-audit over the merged set.
5. Step 5: Fix-Report-Per-Review $why-review Gate — ONE merged $why-review pass that walks each of the three review faces + the dedup and fixes the report in place (severities, false positives, dedup-dropped issues).
6. Step 6: Finalize (FINISHED) — lock the combined verdict (worst-case rollup) and flip the report status to ✅ FINISHED.
7. Next Steps — ask the user directly: $plan (fix validated findings) / $code-simplifier / skip.

Key Rules (top 3 critical first):

• MUST ATTENTION this is a THIN orchestrator — NEVER re-implement any of the three reviews inline; fan them out as sub-agents and synthesize.
• MUST ATTENTION dedup the intentional overlaps — one underlying issue = one finding citing every reporting child; NEVER let cross-referencing siblings triple-count it.
• MUST ATTENTION read-only until validated — run the Step 5 $why-review gate before handoff; fixes route to a downstream $plan/feature flow, NEVER applied here.
• Spawn all three sub-agents in ONE message and honor the all-return barrier — advance only after every child returns (SYNC:parallel-phase-advancement discipline).
• Write the consolidated report to plans/reports/architecture-full-review-{YYMMDD}-{HHmm}-{slug}.md.

Your Mission

$ARGUMENTS

Review Mindset (NON-NEGOTIABLE)

Skeptical synthesizer. Judge the three children's reports; do not re-derive them.

• Trust each child's file:line evidence, but NEVER inflate severity by counting the same underlying issue three times — dedup first, then rank.
• A finding survives to the report only after the Step 5 $why-review gate; an unvalidated sub-agent claim is a hypothesis, not a finding.
• Preserve every route-to-sibling pointer a child emits — the combined report is the union of owned findings, not a re-review.

Step 1: Resolve Scope (ASK EACH RUN)

Decide audit scope, then map to each child's arguments.

• If $ARGUMENTS names files/dirs, or contains full / whole / diff / changes, use that directly.
• Else ask the user directly:
  • "Whole project (Recommended)" — audit the entire repository.
  • "Current changes (diff)" — audit the uncommitted diff only.
  • "Specific path" — audit a named service/module/directory.

Scope → child args mapping:

Chosen scope	architecture-scalability-review	architecture-review	production-readiness-review
Whole project	mode=audit over the whole repo	scope override full codebase	args = all backend service/API roots (per project-structure-reference.md)
Current changes (diff)	mode=audit focused on the services/modules the diff touches	default uncommitted diff	default uncommitted service/API diff
Specific path	mode=audit scoped to that path's services/modules	scope override = that path	that path's service/API files

MUST ATTENTION — architecture-scalability-review always grades the PROJECT, even under diff scope. A project-grader by design ("do not use as the every-change diff reviewer"). Under diff scope it still emits the /20 scorecard, focused on the services/modules the diff touches — it never degrades into a pure per-line diff reviewer. Document this nuance in the consolidated report so its scorecard is read as a project posture, not a diff verdict.

Step 2: Load Project Reference Docs Once

Warm shared context BEFORE fan-out so synthesis reasons from the same ground truth the children use. Read once here (each child re-reads what it needs via its own tool calls):

• docs/project-config.json
• docs/project-reference/project-structure-reference.md
• docs/project-reference/backend-patterns-reference.md
• docs/project-reference/frontend-patterns-reference.md
• docs/project-reference/code-review-rules.md
• Accepted ADRs under docs/adr/**, when present

Step 3: Parallel Fan-Out (ALL-RETURN BARRIER)

Spawn ALL THREE sub-agents in ONE message. Read-only and independent — no shared mutable state, no ordering dependency. Advance ONLY after EVERY member returns (SYNC:parallel-phase-advancement).

Each sub-agent writes its FULL report to plans/reports/ and returns ONLY the SYNC:subagent-return-contract summary (≤10 finding bullets + report path) — NEVER its full report inline.

#	Child skill	agent_type	Whole-project args	Diff-scope args	Emits
1	architecture-scalability-review	architect	mode=audit over whole repo	mode=audit focused on the diff's services/modules (still grades the project)	Scorecard /20 + pass/fail gates
2	architecture-review	architect	scope override full codebase	default uncommitted diff	13-category PASS/WARN/BLOCKED
3	production-readiness-review	code-reviewer	all backend service/API roots (per project-structure-reference.md)	default uncommitted service/API diff	SRE /24 + 8-item gate

Each sub-agent prompt states: READ-ONLY findings/score mode (no fixes); re-read all target files from scratch via its own tool calls; write full report incrementally to plans/reports/; return only the return-contract summary.

Each of the three faces feeds TWO validation gates downstream — state this in each sub-agent's prompt so it knows its findings will be adversarially validated, not trusted as-is: (1) the Step 5 fix-report-per-review $why-review gate that walks its face and fixes its findings in the consolidated report; (2) inside workflow-architecture-audit, the workflow-level FINAL $why-review gate that re-reviews the whole finalized report. A face's findings are hypotheses until they survive both — so every finding it emits MUST carry file:line proof + confidence that can withstand validation.

Step 4: Progressive Synthesis → One Report (status IN PROGRESS)

Exactly ONE report file for the whole audit — created ONCE, grown across Steps 4→6, never re-created per review. Open it when fan-out starts and evolve its status through its lifecycle: 🚧 IN PROGRESS (Step 4) → 🔍 VALIDATING (Step 5) → ✅ FINISHED (Step 6).

Write to plans/reports/architecture-full-review-{YYMMDD}-{HHmm}-{slug}.md.

On fan-out start — create the file with status 🚧 IN PROGRESS and a status line naming which of the three review faces have returned so far (e.g. Faces merged: 0/3). The single source of truth the whole audit synthesizes into — do NOT hold findings in memory until the end.

Header — all three sub-scores + ONE combined verdict (each sub-score is ⏳ pending until its face returns):

• Scalability Scorecard: X/20 + verdict (STRONG / NEEDS WORK / HIGH RISK)
• Architecture Compliance: PASS / WARN / BLOCKED
• SRE Readiness: X/24 + verdict (PASS / NEEDS WORK / NOT READY)
• Combined Verdict: ⏳ pending until FINISHED — computed in Step 6 as the worst-case rollup across the three (any BLOCKED / NOT READY / HIGH RISK dominates). Do NOT assert a combined verdict while status is IN PROGRESS.

Merge each face AS it returns. All three run behind the Step 3 all-return barrier, so all three summaries are in hand before synthesis — but merge them into the file one face at a time (updating Faces merged: N/3 each time) so a mid-synthesis context loss leaves the partial report on disk, not in memory. When ≥2 children report the same underlying issue, record it ONCE, citing every source. Dedup on these KNOWN overlap axes (the siblings cross-reference each other here by design):

Overlap axis	architecture-review face	Sibling face(s)
Module isolation / loose coupling / horizontal scaling / DRY regression	Category 11 (scalability & coupling regression)	architecture-scalability-review {module isolation, loose coupling, horizontal scaling, DRY}
Quality tooling / CI / observability	Category 0 (quality-tooling baseline)	architecture-scalability-review {Build & CI, Observability}
Recorded-decision / clean-architecture conformance	Category 9 (ADR conformance)	architecture-scalability-review {clean architecture}
DB performance / capacity ceilings	production-readiness-review DB-perf + capacity gate	architecture-scalability-review {horizontal scaling}
Technique applicability (advisory) — scale-tier technique matrix	Category 11 INFO advisory matrix	architecture-scalability-review + production-readiness-review advisory matrices
Scenario stress (advisory) — big-traffic/big-data/failure/self-heal	Category 11 INFO scenario-stress matrix	architecture-scalability-review + production-readiness-review scenario-stress matrices
Data / consistency / tenancy — dual write, idempotency, breaking migration, tenant isolation	Category 12 (data, consistency & tenancy boundaries)	production-readiness-review {migration safety, rollback}; security-review owns authz depth; performance-review owns query-plan depth

For each merged finding: assign ONE severity per SYNC:severity-rubric (do not sum severities across duplicate reports), cite each reporting child's file:line, and PRESERVE each child's route-to-sibling pointers. — why: undeduped, three intentionally-cross-referencing reviewers inflate severity counts and bury distinct issues.

Merged advisory Technique Applicability Matrix (does NOT change the combined verdict): all three children emit a scale-tier Technique Applicability Matrix from SYNC:scale-technique-gate; dedup the three views of the same technique onto ONE advisory matrix in the consolidated report. Pin ONE authoritative scale tier for the merged matrix — architecture-scalability-review's derived tier is canonical (owns scalability grading); if another child's derived tier DIVERGES, record the divergence as a one-line note and key the merged matrix's tier-warranted? column to the pinned tier, rather than merging contradictory warranted-sets. This only SELECTS which already-derived tier the matrix is keyed to — it does NOT re-derive any child's findings (respecting "you do not re-derive them" above). It is advisory/INFO only — a MISSING-WARRANTED technique is guidance, never a severity, and NEVER feeds the worst-case combined-verdict rollup. This orchestrator adds no own gate marker; the matrix is inherited from the children.

Merged advisory Scenario Stress Matrix (does NOT change the combined verdict): the same three children each emit a Scenario Stress Matrix from SYNC:scenario-stress-eval (top-down: big-traffic / big-data / dependency-failure / node-loss / data-corruption / self-heal survival vs. business need). Dedup the three views of the same scenario onto ONE advisory matrix in the consolidated report, exactly as for the technique matrix. Pin ONE authoritative scale tier AND business-criticality read — architecture-scalability-review's derived T-tier + B-tier is canonical (owns scalability grading); if another child's derived tier/criticality DIVERGES, record it as a one-line note and key the merged matrix to the pinned values, rather than merging contradictory in-scope sets. This only SELECTS which already-derived tier/criticality the matrix is keyed to — it does NOT re-derive any child's scenario findings. It is advisory/INFO only — a FAILS-HARD or OVER-HARDENED scenario is guidance, never a severity, and NEVER feeds the worst-case combined-verdict rollup. The criticality-signal floor and anti-over-engineering guard live in the children's matrices; this orchestrator adds no own gate marker and inherits the matrix from the children.

Completeness lens over the merged set (orchestrator-only — the children cannot see across faces). Once Faces merged: 3/3, sweep the merged report against the design-review script in .claude/docs/architecture-knowledge.md §20.2 and record any question NO face answered as an explicit Coverage gap: {question} — not covered by any face line. Frame each remaining risk against the five judgments in §20.4 — when to add complexity · when to split · when consistency can be relaxed · when to buy vs build · when GOOD ENOUGH is correct — so the consolidated report tells the reader which JUDGMENT is at stake, not only which rule was broken. A coverage gap is an INFO note, never a severity, and NEVER feeds the combined-verdict rollup. — why: three scoped reviewers each correctly stay in lane, so a question that belongs to no lane is invisible to every one of them and only this orchestrator can see it.

Self-audit the merged report (MANDATORY before Step 5): run the 11 thinking red flags in §20.3 across the merged findings — especially a recommendation whose SACRIFICE is unnamed, "best practice" with no named forces, and a scale claim with no evidence. Any hit is demoted or removed here, not passed to $why-review as ground truth. — why: the orchestrator's synthesis is where three children's confirmation biases compound into one authoritative-sounding report.

Step 4 ends only when Faces merged: 3/3 — all three sub-scores are populated, the §20.2 coverage sweep is recorded, and every finding is on disk.

Step 5: Fix-Report-Per-Review $why-review Gate (status VALIDATING) — MANDATORY when findings exist

Flip the report status to 🔍 VALIDATING, then run ONE merged $why-review pass that WALKS EACH of the three review faces (one merged pass, NOT three per-face passes — a single invocation is strictly more thorough because it also validates the cross-face dedup separate per-face passes cannot see). The "fix report after each review" gate: every face's findings are validated, the report fixed IN PLACE.

1. Read the consolidated report from plans/reports/architecture-full-review-{date}-{slug}.md.
2. Invoke $why-review with: validate findings in {report-path} — WALK EACH review face (architecture-scalability-review, architecture-review, production-readiness-review) in turn: for each face verify every finding it contributed has file:line proof and a correctly-classified severity, steel-man each rejected interpretation; THEN validate the cross-face dedup did not drop or merge-away a distinct issue.
3. $why-review demotes/removes any finding → FIX the report in place: revise severities, remove false positives, restore any distinct issue the dedup wrongly collapsed, and add a ## Why-Review Fix Notes section listing per-face what changed + why.
4. $why-review confirms all findings → append ## Why-Review Validation stating "All N merged findings re-validated across 3 faces; no severity changes."

Skip ONLY on an unconditional zero-finding PASS across all three children (log the skip reason, then proceed to Step 6 to finalize the clean PASS).

Step 6: Finalize (status FINISHED)

The report is now validated — lock it and hand off a stable artifact.

1. Compute the Combined Verdict as the worst-case rollup across the three now-validated sub-scores (any BLOCKED / NOT READY / HIGH RISK dominates); write it into the header, replacing the ⏳ pending placeholder.
2. Flip the report status from 🔍 VALIDATING to ✅ FINISHED and append a ## Finalization block: the three sub-scores, the combined verdict, the total validated finding count by severity, and the Faces merged: 3/3 confirmation.
3. This finalized report is the single deliverable the downstream workflow-level $why-review step and docs-update consume. Do NOT emit a second report file or re-synthesize — one file, finalized once.

Two-tier validation (why this skill runs $why-review AND the workflow adds a why-review step): Step 5 here is the FINDING-level, per-face fix that also protects standalone use of this skill. The workflow-level why-review step that follows is the REPORT-level final gate over the finalized artifact (verdict-rollup correctness, dedup completeness, cross-review severity consistency) and the machine-visible guarantee in the rendered sequence. Distinct altitudes; do not collapse one into the other.

Next Steps

MANDATORY — NO EXCEPTIONS: After completing, use ask the user directly to present:

• "$plan (fix validated findings)" (Recommended) — plan the fixes for the validated findings (fixes happen in the downstream plan/feature flow, NOT here).
• "$code-simplifier" — simplify and refine implicated code.
• "Skip, continue manually" — user decides.

Read-only until validated. This skill produces findings and a verdict only. Applies NO fixes — every validated finding routes to a downstream $plan or feature-implementation flow that owns the change.

[IMPORTANT] Use task tracking to break ALL work into small tasks BEFORE starting. For simple tasks, ask the user whether to skip.

External Memory: Complex/lengthy work → write intermediate findings + final results to plans/reports/ — prevents context loss, serves as deliverable.

Evidence Gate: MANDATORY — every claim, finding, recommendation requires file:line proof or traced evidence with confidence percentage (>80% to act, <80% verify first).

Graph-Assisted Investigation — MANDATORY when .code-graph/graph.db exists.

HARD-GATE: MUST ATTENTION run at least ONE graph command on key files before concluding any investigation.

Pattern: Grep finds files → trace --direction both reveals full system flow → Grep verifies details

Task	Minimum Graph Action
Investigation/Scout	trace --direction both on 2-3 entry files
Fix/Debug	callers_of on buggy function + tests_for
Feature/Enhancement	connections on files to be modified
Code Review	tests_for on changed functions
Blast Radius	trace --direction downstream

CLI: python .claude/scripts/code_graph {command} --json. Use --node-mode file first (10-30x less noise), then --node-mode function for detail.

Sub-Agent Return Contract — When this skill spawns a sub-agent, the sub-agent MUST return ONLY this structure. Main agent reads only this summary — NEVER requests full sub-agent output inline.

## Sub-Agent Result: [skill-name]

Status: ✅ PASS | ⚠️ PARTIAL | ❌ FAIL
Confidence: [0-100]%

### Findings (Critical/High only — max 10 bullets)

- [severity] [file:line] [finding]

### Actions Taken

- [file changed] [what changed]

### Blockers (if any)

- [blocker description]

Full report: plans/reports/[skill-name]-[date]-[slug].md

Main agent reads Full report file ONLY when: (a) resolving a specific blocker, or (b) building a fix plan. Sub-agent writes full report incrementally (per SYNC:incremental-persistence) — not held in memory.

Context budget — the return payload is a SUMMARY, not a transcript: ≤10 finding bullets, no raw file contents / full diffs / verbatim logs inline, no re-pasted source. Everything beyond the summary lives in the Full report on disk. A sub-agent that would exceed the summary shape MUST write the detail to its report and return only the pointer — the orchestrator's context is the scarce resource the whole map-reduce protects.

Nested Task Expansion Contract — For workflow-step invocation, the [Workflow] ... row is only a parent container; the child skill still creates visible phase tasks.

1. Call the current task list first. If a matching active parent workflow row exists, set nested=true and record parentTaskId; otherwise run standalone.
2. Create one task per declared phase before phase work. When nested, prefix subjects [N.M] $skill-name — phase.
3. When nested, link the parent with TaskUpdate(parentTaskId, addBlockedBy: [childIds]).
4. Orchestrators must pre-expand a child skill's phase list and link the workflow row before invoking that child skill or sub-agent.
5. Mark exactly one child in_progress before work and completed immediately after evidence is written.
6. Complete the parent only after all child tasks are completed or explicitly cancelled with reason.

Blocked until: the current task list done, child phases created, parent linked when nested, first child marked in_progress.

Project Reference Docs Gate — Run after task-tracking bootstrap and before target/source file reads, grep, edits, or analysis. Project docs override generic framework assumptions.

1. Identify scope: file types, domain area, and operation.
2. Read docs/project-config.json first — the project's machine-readable map. It is the single source of truth for THIS repo (modules/paths, framework + search keywords, test/E2E/integration run-commands, design system, architecture rules, workflow patterns); ground exact paths, run-commands, and conventions on it before investigating, planning, or coding — never assume framework defaults (CLAUDE.md + reference docs are derived from it). If it — or the docs index, lessons.md, CLAUDE.md, AGENTS.md, or any required reference doc — is missing or stale, auto-run $project-init or the narrow route ($project-config, $docs-init, $scan-all, $scan --target=<key>, $claude-md-init) first; if Codex mirrors or AGENTS.md are stale, ask the user to run $sync-codex (never auto-run it).
3. Required docs by trigger: always docs/project-reference/lessons.md; doc lookup docs-index-reference.md; review code-review-rules.md; backend/CQRS/API backend-patterns-reference.md; domain/entity domain-entities-reference.md; frontend/UI frontend-patterns-reference.md; styles/design scss-styling-guide.md + design-system/design-system-canonical.md; integration tests integration-test-reference.md; E2E e2e-test-reference.md; feature docs/specs feature-spec-reference.md + spec-system-reference.md + spec-principles.md; behavior/public-contract/spec-test-code sync workflow-spec-test-code-cycle-reference.md; derived spec index/ERD/reimplementation guides spec-system-reference.md + source Feature Specs under docs/specs/; architecture/new area project-structure-reference.md.
4. Read every required doc, then before target work state: Reference docs read: ... | Not applicable: ....

Ready when: scope evaluated, docs/project-config.json consulted, required docs checked/read or setup route completed, lessons.md confirmed, citation emitted.

Task Tracking & External Report Persistence — Bootstrap this before execution; then run project-reference doc prefetch before target/source work.

1. Create a small task breakdown before target file reads, grep, edits, or analysis. On context loss, inspect the current task list first.
2. Mark one task in_progress before work and completed immediately after evidence; never batch transitions.
3. For plan/review work, create plans/reports/{skill}-{YYMMDD}-{HHmm}-{slug}.md before first finding.
4. Append findings after each file/section/decision and synthesize from the report file at the end.
5. Final output cites Full report: plans/reports/{filename}.

Blocked until: task breakdown exists, report path declared for plan/review work, first finding persisted before the next finding.

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

Evidence-Based Reasoning — Speculation is FORBIDDEN. Every claim needs proof.

1. Cite file:line, grep results, or framework docs for EVERY claim
2. Declare confidence: >80% act freely, 60-80% verify first, <60% DO NOT recommend
3. Cross-service validation required for architectural changes
4. "I don't have enough evidence" is valid and expected output

BLOCKED until: - [ ] Evidence file path (file:line) - [ ] Grep search performed - [ ] 3+ similar patterns found - [ ] Confidence level stated

Forbidden without proof: "obviously", "I think", "should be", "probably", "this is because" If incomplete → output: "Insufficient evidence. Verified: [...]. Not verified: [...]."

Validated-Finding Fix + Full Re-Review Loop — Re-review is triggered by a validated finding fix cycle, not by a round number. Review purpose: review → validate findings → fix validated findings → full re-review until a complete review pass finds no issues. A clean review ENDS the loop — no further rounds required.

aka Self-Review Convergence Loop. The name is historical — there is NO 2-round cap; "double-round-trip" only means a validated-finding fix cycle forces at least one fresh re-review. It runs until a clean pass, bounded by the 5-round ceiling below.

Round cap — 5 rounds MAX (a ceiling, NEVER a target). A clean pass ENDS the loop immediately at ANY round — round 1 included; the cap never obliges you to keep spinning. Hitting round 5 with validated findings still open → STOP and escalate by asking the user directly with the still-open findings listed; NEVER emit a silent "good enough" PASS on cap exhaustion, and NEVER let the cap substitute for the clean-review requirement. The 3-repeated-no-progress blocker rule stays an EARLIER exit — escalate at whichever trips first.

Universal scope (any new output/judgment): any newly produced output or judgment gets ≥1 self-review; any new judgment gets ≥1 $why-review --validate-findings pass; anything flagged to re-check is re-checked ≥1 time — before that output is treated as final. This loop is the default convergence contract for ANY work-producing skill, not review skills only.

Routing invariant (author-facing): a skill that validates findings MUST route them through $why-review --validate-findings (the terminal validator) — NEVER fork an inline finding-validation. Routing through why-review is what makes the finding-survival bar and this loop apply; the verify-review-validate-coverage sensor enforces this exact route mechanically.

Round 1: Main-session review. Read target files, build understanding, note issues. Output findings + verdict (PASS / FAIL).

Decision after Round 1:

• No issues found (PASS, zero findings) → review ENDS. Do NOT spawn a fresh sub-agent for confirmation.
• Issues found (FAIL, or any non-zero findings) → run the active review skill's findings-validation gate first; for review skills the default gate is $why-review --validate-findings <report-path>. Fix only validated findings, then restart the full review protocol from the beginning with a fresh task breakdown.

Fresh full re-review after every fix cycle: Re-run the whole review protocol over the current full target. When sub-agents are part of that protocol, spawn NEW spawn_agent calls — never reuse prior agents. Reviewers re-read ALL files from scratch with ZERO memory of prior rounds. See SYNC:fresh-context-review for the spawn mechanism and SYNC:review-protocol-injection for the canonical Agent prompt template. Each fresh full review must catch:

• Cross-cutting concerns missed in the prior round
• Interaction bugs between changed files
• Convention drift (new code vs existing patterns)
• Missing pieces that should exist but don't
• Subtle edge cases the prior round rationalized away
• Regressions introduced by the fixes themselves

Loop termination: After each full re-review, repeat the same decision: clean → END; issues → validate findings → fix → restart from the first review phase. Continue until a complete review pass finds zero issues, capped at 5 rounds. Escalate by asking the user directly at whichever comes first: the same validated finding repeats for 3 full invocations with no progress · a fix requires product/owner input · round 5 completes with validated findings still open. NEVER loop past 5 rounds, and NEVER convert cap exhaustion into a PASS.

Rules:

• A clean Round 1 ENDS the review — no mandatory Round 2
• NEVER fix unvalidated findings; validate first using the caller's validation gate
• Every surviving finding must additionally clear the finding-survival bar defined in why-review's Findings Validation Routine (a deliberately higher bar than the generic act-gate — "keep this finding?" is a stricter question than "act on this evidence?"); a finding below the bar is demoted or dropped, not kept
• NEVER skip the full re-review after a fix cycle (every fix invalidates the prior verdict)
• NEVER reuse a sub-agent across rounds — every iteration that uses sub-agents spawns NEW Agent calls
• Main agent READS sub-agent reports but MUST NOT filter, reinterpret, or override findings
• The 5-round cap NEVER replaces the clean-review requirement — it bounds runaway looping, it does not authorize shipping an un-clean review; a clean pass ends the loop early at any round, and cap exhaustion escalates rather than passes
• Enforce the round cap of 5 alongside the 3 repeated-no-progress blocker rule; both are escalation triggers, neither is a completion criterion
• Track recursive invocation count and repeated blockers in conversation context (session-scoped)
• Final verdict must incorporate ALL rounds executed

Report must include ## Round N Findings (Fresh Sub-Agent) for every round N≥2 that was executed.

Fresh Context Re-Review — Eliminate orchestrator confirmation bias after fixes by restarting the full review with isolated sub-agents where applicable.

Why: The main agent knows what it (or $feature-implement) just fixed and rationalizes findings accordingly. A fresh sub-agent has ZERO memory, re-reads from scratch, and catches what the main agent dismissed. Sub-agent bias is mitigated by (1) fresh context, (2) verbatim protocol injection, (3) main agent not filtering the report.

When: ONLY after a validated-finding fix cycle. A review round that finds zero issues ENDS the loop — do NOT spawn a confirmation sub-agent. A review round that finds issues triggers: validate findings → fix → full review restart from the first phase.

How:

1. Start a NEW full review invocation/task breakdown; when that protocol calls for agents, spawn NEW spawn_agent tool calls — use code-reviewer agent_type for code reviews, general-purpose for plan/doc/artifact reviews
2. Inject ALL required review protocols VERBATIM into the prompt — see SYNC:review-protocol-injection for the full list and template. Never reference protocols by file path; AI compliance drops behind file-read indirection (see SYNC:shared-protocol-duplication-policy)
3. Sub-agent re-reads ALL target files from scratch via its own tool calls — never pass file contents inline in the prompt
4. Sub-agent writes structured report to plans/reports/{review-type}-round{N}-{date}.md
5. Main agent reads the report, integrates findings into its own report, DOES NOT override or filter

Rules:

• SKIP fresh sub-agent when the prior full review found zero issues (no fixes = nothing new to verify)
• NEVER skip the full review restart after a fix cycle — every fix invalidates the prior verdict
• NEVER reuse a sub-agent across rounds — every fresh round spawns a NEW spawn_agent call
• Continue until a complete full review pass has zero findings; if the same blocker repeats 3 times with no progress, escalate by asking the user directly
• Track iteration count and repeated blockers in conversation context (session-scoped, no persistent files)

Review Protocol Injection — Every fresh sub-agent review prompt MUST embed 11 protocol blocks VERBATIM. The template below has ALL 11 bodies already expanded inline. Copy the template wholesale into the Agent call's prompt field at runtime, replacing only the {placeholders} in Task / Round / Reference Docs / Target Files / Output sections with context-specific values. Do NOT touch the embedded protocol sections.

Why inline expansion: Placeholder markers would force file-read indirection at runtime. AI compliance drops significantly behind indirection (see SYNC:shared-protocol-duplication-policy). Therefore the template carries all 11 protocol bodies pre-embedded.

Subagent Type Selection

• code-reviewer — for code reviews (reviewing source files, git diffs, implementation)
• general-purpose — for plan / doc / artifact reviews (reviewing markdown plans, docs, specs)

Canonical Agent Call Template (Copy Verbatim)

spawn_agent({
  description: "Fresh Round {N} review",
  agent_type: "code-reviewer",
  prompt: `
## Task
{review-specific task — e.g., "Review all uncommitted changes for code quality" | "Review plan files under {plan-dir}" | "Review integration tests in {path}"}

## Round
Round {N}. You have ZERO memory of prior rounds. Re-read all target files from scratch via your own tool calls. Do NOT trust anything from the main agent beyond this prompt.

## Protocols (follow VERBATIM — these are non-negotiable)

### Spec ↔ Tests ↔ Code Triangulation
DO THIS FIRST — before any per-protocol check below. The review target is the WHOLE PACKAGE, not the diff alone: load the behavior's spec (§3 ACs / §4 BRs / §8 TCs), its tests, and the changed code TOGETHER, and reason about their mutual consistency BEFORE judging any one in isolation.
1. Locate all three faces: the Feature Spec section(s) governing the changed behavior, the tests that guard it, and the production code that implements it. A missing face is itself a finding (SPEC-GAP / TEST-GAP / DEAD-SPEC).
2. Triangulate pairwise — every disagreement is a finding; classify which face is wrong:
   - code vs spec: behavior the code does that no §3/§4/§8 rule describes → CODE-EXTRA or SPEC-STALE; a [HARD] §4 rule or §5 invariant with no enforcing code path → CODE-WRONG.
   - tests vs spec: a §8 TC with no test, or a test asserting behavior no TC/rule names → TEST-GAP or SPEC-SILENT.
   - tests vs code: a changed code path with no covering test → TEST-GAP; a test that still passes against a deliberately broken invariant → WEAK-TEST (apply the mutation thinking in Bug Detection).
3. Hidden-rule capture: any invariant the code enforces but the spec never states (SPEC-SILENT) MUST be surfaced as a finding to add into §3/§4/§8 AND guarded with a test — the enrichment loop, never a silent pass.
4. Only after the three faces agree — or every disagreement is logged as a finding — proceed to the per-protocol checks below; when enrichment adds spec/test content, re-review the package against the enriched spec.
NEVER mark review PASS while any spec/test/code face disagrees without a logged finding. The diff is the entry point; the package is the unit of judgment.

### Evidence-Based Reasoning
Speculation is FORBIDDEN. Every claim needs proof.
1. Cite file:line, grep results, or framework docs for EVERY claim
2. Declare confidence: >80% act freely, 60-80% verify first, <60% DO NOT recommend
3. Cross-service validation required for architectural changes
4. "I don't have enough evidence" is valid and expected output
BLOCKED until: Evidence file path (file:line) provided; Grep search performed; 3+ similar patterns found; Confidence level stated.
Forbidden without proof: "obviously", "I think", "should be", "probably", "this is because".
If incomplete → output: "Insufficient evidence. Verified: [...]. Not verified: [...]."

### Bug Detection
MUST check categories 1-4 for EVERY review. Never skip.
1. Null Safety: Can params/returns be null? Are they guarded? Optional chaining gaps? .find() returns checked?
2. Boundary Conditions: Off-by-one (< vs <=)? Empty collections handled? Zero/negative values? Max limits?
3. Error Handling: Try-catch scope correct? Silent swallowed exceptions? Error types specific? Cleanup in finally?
4. Resource Management: Connections/streams closed? Subscriptions unsubscribed on destroy? Timers cleared? Memory bounded?
5. Concurrency (if async): Missing await? Race conditions on shared state? Stale closures? Retry storms?
6. Stack-Specific: Check the configured language/runtime pitfalls and framework-specific failure modes discovered from local code.
Classify: CRITICAL (crash/corrupt) → FAIL | HIGH (incorrect behavior) → FAIL | MEDIUM (edge case) → WARN | LOW (defensive) → INFO.

### Design Patterns Quality
Priority checks for every code change:
1. DRY via OOP: Same-suffix classes (*Entity, *Dto, *Service) MUST share base class. 3+ similar patterns → extract to shared abstraction.
2. Right Responsibility: Logic in LOWEST layer (Entity > Domain Service > Application Service > Controller). Never business logic in controllers.
3. SOLID: Single responsibility (one reason to change). Open-closed (extend, don't modify). Liskov (subtypes substitutable). Interface segregation (small interfaces). Dependency inversion (depend on abstractions).
4. After extraction/move/rename: Grep ENTIRE scope for dangling references. Zero tolerance.
5. YAGNI gate: NEVER recommend patterns unless 3+ occurrences exist. Don't extract for hypothetical future use.
Anti-patterns to flag: God Object, Copy-Paste inheritance, Circular Dependency, Leaky Abstraction.

### Logic & Intention Review
Verify WHAT code does matches WHY it was changed.
1. Change Intention Check: Every changed file MUST serve the stated purpose. Flag unrelated changes as scope creep.
2. Happy Path Trace: Walk through one complete success scenario through changed code.
3. Error Path Trace: Walk through one failure/edge case scenario through changed code.
4. Acceptance Mapping: If plan context available, map every acceptance criterion to a code change.
5. Tests Verify Intent: For test/spec changes, verify tests name the protected business rule or invariant and would fail if that intent breaks.
6. Migration Test Exclusion: Do not write tests for migration code. Schema/data migrations are one-time execution paths, not core application logic.
NEVER mark review PASS without completing both traces (happy + error path).

### Test Spec Verification
Map changed code to test specifications.
1. Identify the project's test/spec format from existing docs, test-case files, BDD feature files, or spec folders.
2. Every changed code path MUST map to a corresponding test case/spec (or flag as "needs test case").
3. New functions/endpoints/handlers → flag for test spec creation.
4. Migration files are excluded from test/spec creation; schema/data migrations are one-time execution paths, not core application logic.
5. If spec evidence fields exist, verify they point to actual code (file:line, not stale references).
6. Verify each meaningful test case names the business intent/invariant; flag behavior-only cases that only mirror implementation details.
7. Auth/data changes → verify corresponding authorization and data-state test cases exist.
8. If no specs exist for a changed path → log the gap and recommend the project's test-spec workflow.
NEVER skip test mapping. Untested code paths are the #1 source of production bugs.

### Behavioral Delta Matrix
MANDATORY for any bugfix review. Produce input-state × pre-fix × post-fix × delta table BEFORE writing verdict.
- Minimum 3 rows; include at least one row OUTSIDE the original bug report.
- Any "REGRESSION" delta → review returns FAIL until a preservation test is added.
- Narrative descriptions do NOT substitute for the matrix.
Example rows (external-record sync fix):
| Input                 | Pre-fix | Post-fix                  | Delta      |
| --------------------- | ------- | ------------------------- | ---------- |
| Record exists (valid) | Reused  | Always recreated → orphan | REGRESSION |
| Record missing (404)  | Error   | Recreated                 | Fixed      |

### Fix-Layer Accountability
NEVER fix at the crash site. Trace the full flow, fix at the owning layer. The crash site is a SYMPTOM, not the cause.
MANDATORY before ANY fix:
1. Trace full data flow — Map the complete path from data origin to crash site across ALL layers (storage → backend → API → frontend → UI). Identify where bad state ENTERS, not where it CRASHES.
2. Identify the invariant owner — Which layer's contract guarantees this value is valid? Fix at the LOWEST layer that owns the invariant, not the highest layer that consumes it.
3. One fix, maximum protection — If fix requires touching 3+ files with defensive checks, you are at the wrong layer — go lower.
4. Verify no bypass paths — Confirm all data flows through the fix point. Check for direct construction skipping factories, clone/spread without re-validation, raw data not wrapped in domain models, mutations outside the model layer.
BLOCKED until: Full data flow traced (origin → crash); Invariant owner identified with file:line evidence; All access sites audited (grep count); Fix layer justified (lowest layer that protects most consumers).
Anti-patterns (REJECT): "Fix it where it crashes" (crash site ≠ cause site, trace upstream); "Add defensive checks at every consumer" (scattered defense = wrong layer); "Both fix is safer" (pick ONE authoritative layer).

### Rationalization Prevention
AI skips steps via these evasions. Recognize and reject:
- "Too simple for a plan" → Simple + wrong assumptions = wasted time. Plan anyway.
- "I'll test after" → RED before GREEN. Write/verify test first.
- "Already searched" → Show grep evidence with file:line. No proof = no search.
- "Just do it" → Still need task tracking. Skip depth, never skip tracking.
- "Just a small fix" → Small fix in wrong location cascades. Verify file:line first.
- "Code is self-explanatory" → Future readers need evidence trail. Document anyway.
- "Combine steps to save time" → Combined steps dilute focus. Each step has distinct purpose.

### Graph-Assisted Investigation
MANDATORY when .code-graph/graph.db exists.
HARD-GATE: MUST run at least ONE graph command on key files before concluding any investigation.
Pattern: Grep finds files → trace --direction both reveals full system flow → Grep verifies details.
- Investigation/Scout: trace --direction both on 2-3 entry files
- Fix/Debug: callers_of on buggy function + tests_for
- Feature/Enhancement: connections on files to be modified
- Code Review: tests_for on changed functions
- Blast Radius: trace --direction downstream
CLI: python .claude/scripts/code_graph {command} --json. Use --node-mode file first (10-30x less noise), then --node-mode function for detail.

### Understand Code First
HARD-GATE: Do NOT write, plan, or fix until you READ existing code.
1. Search 3+ similar patterns (grep/glob) — cite file:line evidence.
2. Read existing files in target area — understand structure, base classes, conventions.
3. Run python .claude/scripts/code_graph trace <file> --direction both --json when .code-graph/graph.db exists.
4. Map dependencies via connections or callers_of — know what depends on your target.
5. Write investigation to .ai/workspace/analysis/ for non-trivial tasks (3+ files).
6. Re-read analysis file before implementing — never work from memory alone.
7. NEVER invent new patterns when existing ones work — match exactly or document deviation.
BLOCKED until: Read target files; Grep 3+ patterns; Graph trace (if graph.db exists); Assumptions verified with evidence.

## Reference Docs (READ before reviewing)
- `.claude/docs/development-rules.md` — canonical development rules, code-quality guidelines, and pre-commit checklist
- docs/project-reference/code-review-rules.md
- {skill-specific reference docs — e.g., integration-test-reference.md for integration-test-review; backend-patterns-reference.md for backend reviews; frontend-patterns-reference.md for frontend reviews}

## Target Files
{explicit file list OR "run git diff to see uncommitted changes" OR "read all files under {plan-dir}"}

## Output
Write a structured report to plans/reports/{review-type}-round{N}-{date}.md with sections:
- Status: PASS | FAIL
- Issue Count: {number}
- Critical Issues (with file:line evidence)
- High Priority Issues (with file:line evidence)
- Medium / Low Issues
- Cross-cutting findings

Return the report path and status to the main agent.
Every finding MUST have file:line evidence. Speculation is forbidden.
`
})

Rules

• DO copy the template wholesale — including all 11 embedded protocol sections
• DO replace only the {placeholders} in Task / Round / Reference Docs / Target Files / Output sections with context-specific content
• DO choose code-reviewer agent_type for code reviews and general-purpose for plan / doc / artifact reviews
• DO NOT paraphrase, summarize, or skip any protocol section
• DO NOT pass file contents inline — the sub-agent reads via its own tool calls so it has a fresh context
• DO NOT reference protocols by file path or tag name — the bodies are already embedded above
• DO NOT introduce placeholder markers for the protocols — they must stay literally expanded

AI Mistake Prevention — Failure modes to avoid on every task:

Re-read files after context changes. Context compaction, resume, or long-running work can make memory stale; verify current files before acting. Verify generated content against source evidence. AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing. Check downstream references before deleting or renaming. Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first. Trace the full impact chain after edits. Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done. Verify ALL affected outputs, not just the first. One green check is not all green checks; validate every output surface the change can affect. Assume existing values are intentional — ask WHY before changing. Before changing a constant, limit, flag, wording, or pattern, read nearby context and history. Surface ambiguity before acting — don't pick silently. Multiple valid interpretations require an explicit question or stated assumption with risk. Keep shared guidance role-relevant. Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.

Systematic Review Batching (map-reduce) — When a changeset is large, do NOT review files one-by-one. Partition into size-capped batches, fire one specialized sub-agent per batch in parallel, then reduce. This bounds EVERY context — each batch agent AND the orchestrator — so coverage stays complete as file count grows.

Trigger ladder (one ordered escalation — not competing thresholds):

1. < 10 changed files → sequential per-file review (default; no batching).
2. ≥ 10 changed files → switch to systematic parallel mode. Announce: "Detected {N} changed files. Switching to systematic parallel review protocol." Then: categorize → size-capped batches → flat consolidation.
3. categories > 6 OR files > 40 → additionally insert the hierarchical synthesis tier (below). Everything from rung 2 still applies.

Step 1 — Categorize. Group changed files into logical categories derived from the project's actual structure (not forced). Category is the concern axis; orient with these examples, derive what fits the repository:

Category Type	Example Groupings
Agent/Tooling	AI scripts, hooks, skill definitions, workflow configs, linting rules
Root config/docs	Root README, project config, CI/CD pipeline configs
Reference docs	Architecture docs, patterns references, setup guides
Feature/domain docs	Business feature documentation, spec files, ADRs
Backend logic	Service/handler/controller source (infer from project structure)
Frontend logic	UI component/state/API source (infer from project structure)
Data/Schema	Migrations, schema files, seed data
Tests	Unit, integration, E2E test files
Infrastructure	Docker, k8s, CI/CD, cloud manifests

Step 2 — Size-capped batches. One sub-agent per batch of ≤8 files OR ≤2000 diff-lines, whichever hits first. Category stays the concern axis, but any category exceeding a cap splits into multiple size-capped batches (30 backend files → 4 batches). Size caps — not category caps — make "many files" safe: a category cap alone lets one giant category blow a single agent's context.

Step 2a — Sub-agent type per batch (match the batch's dominant concern):

• Code logic (any stack) → code-reviewer
• Security-sensitive changes → security-auditor
• Performance-critical paths → performance-optimizer
• Docs, plans, specs, configs, infra → general-purpose

Each batch sub-agent receives: its full file list; SYNC:category-review-thinking as its primary thinking model — derive each category's concerns from first principles, NOT a fixed checklist (if the consuming skill does not carry that block, apply category-first thinking directly); project reference docs relevant to its concern (discover via *patterns*, *conventions*, *style-guide*); cross-reference verification instructions (counts, tables, links). All batch agents run in parallel and write findings to plans/reports/ (per SYNC:task-tracking-external-report); reducers read from disk, never from memory.

Step 3 — Reduce.

• Flat reduction (rung 2, ≤6 categories AND ≤40 files): the orchestrator collects each batch report, cross-references counts/tables/contracts ACROSS batches, detects gaps visible only across categories (feature in code but missing from docs; new API endpoint with no client call), and consolidates into one categorized holistic report.
• Hierarchical reduction (rung 3, > 6 categories OR > 40 files): insert a mid-tier — each concern gets ONE synthesizer agent that reads only its own batch reports and emits a single concern-synthesis. The orchestrator reads the concern-syntheses (~5), never the raw batch reports — keeping the reducer's context O(#concerns), not O(#files).
  • Cross-concern interaction pass (mandatory at rung 3 — closes the synthesis-tier blind spot): concern-siloed synthesis can drop an interaction spanning two concerns AND two batches (tainted source in data-layer/batch 7 → sink in api/batch 3). So: (a) each concern-synthesizer MUST emit an explicit "cross-concern interaction candidates" list — entities/symbols/contracts it touched that plausibly bind to another concern (shared DTOs, event names, table/collection names, exported symbols); (b) the orchestrator MUST run the Step-3 cross-reference/gap step over those candidate lists across all concern-syntheses, not only within a batch, before concluding. Without this pass the tier trades completeness for context-bounding on exactly the large diffs it targets.

Step 4 — Holistic assessment. With all findings combined, judge: overall coherence as a unified intent; cross-category sync (docs match code? contracts match callers?); risk areas where categories interact; missing doc/spec updates for changed artifacts.

No silent truncation. If any cap forces sampling or a batch is dropped for budget, ANNOUNCE the dropped/sampled scope explicitly — bounded coverage must never read as complete coverage.

Severity Rubric — Classify every finding by consequence, not by how easy it is to fix. One scale across all reviews so a "High" means the same thing everywhere.

Severity	Action	Definition
CRITICAL	Block merge	Silent runtime failure, data corruption, validation bypass, security hole
HIGH	Must fix	Incorrect behavior, invariant gap, architectural violation
MEDIUM	Should fix	Design debt, maintainability, likely future bug
LOW	Nice to fix	Convention, documentation, minor clarity

Score-based skills map their numeric scale onto these tiers — do not invent a parallel vocabulary:

• 0-2 criterion scoring (e.g. production-readiness-review): 0 = CRITICAL/HIGH (criterion unmet, blocks production readiness), 1 = MEDIUM (partial, should fix), 2 = pass (no finding).
• Two-axis scoring (e.g. performance-review, impact × likelihood): map the resulting cell to the nearest tier — high-impact + high-likelihood → CRITICAL/HIGH; low-impact OR low-likelihood → MEDIUM/LOW.

A finding's tier drives the gate: CRITICAL/HIGH must be resolved or explicitly accepted by the owner before PASS; MEDIUM/LOW may ship with a tracked follow-up.

Category Review Thinking — A thinking framework for reviewing any category of changed files. NOT a fixed checklist — derive concerns from domain knowledge; the examples are starting points only. Your knowledge of the category exceeds any list here — trust it.

Step 1 — Understand the category's role. What is this category responsible for in the overall system? What invariants must it uphold? What are its consumer contracts (who depends on it, what do they expect)?

Step 2 — Read project conventions for this category. Search for reference docs, style guides, ADRs, or READMEs specific to this area. Grep 3+ existing similar files — extract naming conventions, structural patterns, shared base classes. If no docs exist, derive conventions empirically from existing code.

Step 3 — Derive concerns from first principles. Apply all that are relevant; expand beyond this list based on the actual category:

• Correctness: Does the logic match the intent? Trace happy path AND error path.
• Boundary contracts: Are interfaces/APIs/events/protocols honored? No implicit coupling introduced?
• Project conventions: Does new code follow the patterns found in Step 2? Evidence-confirmed, not assumed.
• Security: Auth enforced at every entry point? Input validated at boundaries? No secrets in the diff?
• Performance: Unbounded operations? N+1 patterns? Blocking calls in async context? Unindexed queries?
• Maintainability: DRY? Single responsibility? Complexity within reason? Names reveal intent?
• Test coverage: Are the changed paths covered by tests? Are existing tests still valid after the change?
• Documentation: Do related docs, specs, or READMEs reflect the changes?

Step 4 — Create sub-tasks and execute. For each identified concern: create a task tracking sub-task, work through it with file:line evidence, mark done. No findings without proof.

Illustrative concern examples by category type (not exhaustive — trust your knowledge beyond this):

• Server-side logic: handler/service structure conventions, validation layer placement, side-effect isolation, cross-service boundary enforcement, data-access layer separation, error propagation strategy
• Client-side logic: component lifecycle management, resource cleanup (subscriptions, listeners, timers), state management patterns, API integration layer separation, reactive stream composition
• Data/Schema: migration reversibility (rollback script), lock impact on table volume, backfill idempotency, index coverage for query patterns, deployment ordering
• Configuration: present in ALL environments? No secrets in diff? App fails fast if config missing (not silently null)? Documented in setup guide?
• Infrastructure: dev/prod parity? No hardcoded dev values (localhost, debug flags)? Pinned image/dependency versions? CI/CD secret requirements documented?
• Styles/Assets: follows project naming conventions? Uses design variables/tokens (no hardcoded magic values)? Correct scope (no global side effects from component styles)?
• Documentation: accurate? Links valid? Examples still match current code/behavior? Covers new scenarios?
• Tests: assertions verify specific outcomes (not just "no exception")? Idempotent (repeatable N times)? Covers edge cases, not just happy path?
• Security artifacts: all code paths reach the gate? Negative tests exist (unauthorized denied)? Both enforcement AND display control updated?
• Build/Tooling: rule changes apply consistently? No exceptions that silently swallow violations? Impact on CI runtime documented?

Goal Contract Satisfaction Loop — Persist the user goal in an external file, execute against it, and loop review/fix until every saved required criterion passes or a blocker escalates. Bounded closed loop — NEVER open-ended autonomous exploration.

1. Resolve the active goal (in order): active plan goal.md → plans/goals/{YYMMDD-HHmm}-{slug}/goal.md → create a new Goal Contract from the current user request (template: .claude/templates/goal-contract-template.md).
2. Required sections: Original Request, Purpose, Success Criteria (checkboxes; mark required vs optional), Constraints, Evidence Required, Iteration Log, Goal Satisfaction matrix.
3. Before work: read the active goal and map planned work to saved success criteria — execution serves the saved criteria, never chat memory alone.
4. After execution/verification: append an Iteration Log entry — result, evidence references (file:line, command output, report path), remaining gaps.
5. Review gate: emit a Goal Satisfaction matrix — | Success Criterion | Evidence | Status | with PASS/FAIL/BLOCKED. Overall PASS requires every required criterion PASS.
6. Loop rule (retry): required criterion FAIL → validate the gap is real → fix → re-review only the affected criteria. Stop cleanly when all required criteria PASS.
7. Escalation rule (stop): two consecutive iterations with no criterion progressing, or a blocker needing user input → mark the criterion BLOCKED with a user-facing reason and escalate. NEVER loop indefinitely.
8. Skip rule: tiny conversational tasks may skip the goal file ONLY with a recorded one-line reason. User-accepted gate skips are recorded in the goal file with reason and scope.
9. Security: NEVER store secrets, tokens, credentials, or private customer data in goal files — store evidence references and redact sensitive values.

Blocked until: active goal resolved (or skip reason recorded) · saved success criteria read before edits · iteration evidence appended after execution · Goal Satisfaction matrix emitted before any PASS verdict.

Trade-Off Interrogation Gate — ALWAYS ask these THREE questions before ANY verdict, score, finding, or recommendation — about the thing under review AND about every recommendation YOU make. — why: naming a benefit without its price is an endorsement, not a review; the costliest trade-offs are the ones nobody wrote down.

1. Is there any trade-off? Name what it SACRIFICES. "None" / "pure win" is an unfinished analysis, NOT an answer — to claim none, state which dimensions you checked and why each is unaffected: future change cost · complexity · performance/latency · memory/cost · coupling · reversibility · migration burden · operational load · blast radius · security posture · testability · team skill/ramp · delivery time · UX.
2. Is it worth it? Weigh gain against sacrifice EXPLICITLY — what is gained (with a metric) · what it costs · WHO pays · WHEN it comes due — then emit WORTH IT / NOT WORTH IT / UNCLEAR. "Better" with no metric and no cost FAILS this question. NOT WORTH IT → withdraw or replace the recommendation, never keep it as-is.
3. Is the trade-off material enough to CONFIRM WITH THE USER? A material trade-off is the user's call, never yours. MATERIAL when ANY holds: irreversible / one-way door (data migration, public contract, storage format, vendor lock-in) · cost shifted onto someone else (another team, ops/on-call, future maintainer, end user) · one quality attribute traded for another (correctness↔speed, security↔convenience, latency↔cost, simplicity↔flexibility) · a boundary crossed (client↔server tier, service contract, event contract, shared library) · a high-consequence path (auth, money, data integrity, breaking change, High/Medium residual risk) · the worth-it verdict is UNCLEAR.

MATERIAL → STOP and confirm by asking the user directly BEFORE the verdict stands — state the trade-off, both options, what each sacrifices, and your recommendation. NOT material → record it inline with a one-line justification and proceed.

Non-asking execution contexts — ESCALATE BY HANDOFF, never by silence. ask the user directly reaches only the main interactive agent: a sub-agent cannot ask the user, and a terminal/verdict-only mode asks nothing by design. When you are running in such a context, the obligation is redirected, never waived — do ALL of: (a) complete questions 1 and 2 normally; (b) decide materiality and record it in the Trade-Off Assessment row with confirmed? = NO — cannot ask from this context; (c) name the unconfirmed MATERIAL trade-off explicitly in your returned summary/verdict so the CALLER (or parent orchestrator) escalates it by asking the user directly on your behalf — a material trade-off mentioned only inside a report file on disk is NOT a handoff; (d) do not emit an unqualified PASS — mark the verdict as carrying an unconfirmed material trade-off, so the caller's gate stays closed until the user answers. The caller inherits the escalation duty the moment it reads your return.

This carve-out is about reachability, not convenience: it applies ONLY where the tool genuinely cannot reach the user (spawned sub-agent, terminal validate/verdict-only mode, non-interactive/headless run). It is NEVER a licence to skip the question, to self-approve a one-way door, or to downgrade materiality because asking is inconvenient — if you CAN ask, you MUST ask.

Emit a Trade-Off Assessment row per reviewed decision and per recommendation: | decision | sacrifices | gain (metric) | who pays, when | WORTH IT/NOT/UNCLEAR | material? | confirmed? |.

BLOCKED until: trade-off named (or dimensions-checked justification given) · worth-it verdict emitted · materiality decided · every MATERIAL trade-off either confirmed with the user OR — in a non-asking context — handed off in the returned verdict for the caller to confirm. A MATERIAL trade-off that is neither confirmed nor handed off can NEVER be PASS, and NEVER gets buried as a Low-severity note.

NEVER answer "no trade-off" without checking · decide a material trade-off silently on the user's behalf · let convergence/delivery pressure authorize walking through a one-way door · bundle several material trade-offs into one vague "proceed?".

• MANDATORY IMPORTANT MUST ATTENTION execute the review loop (aka Self-Review Convergence Loop): review → validate findings → fix validated findings → full re-review. A complete review pass with zero findings ENDS the review. Any newly produced output/judgment gets ≥1 self-review; any new judgment gets ≥1 $why-review --validate-findings pass before it is treated as final.
• MANDATORY enforce the round cap of 5 — a ceiling, NEVER a target: a clean pass ends the loop immediately at any round (round 1 included), and round 5 completing with validated findings still open → STOP & escalate by asking the user directly, never a silent PASS. The 3-repeated-no-progress blocker rule is an earlier exit — escalate at whichever trips first. NEVER loop open-ended.

IMPORTANT MUST ATTENTION run at least ONE graph command on key files before concluding (when graph.db exists).

IMPORTANT MUST ATTENTION cite file:line evidence for every claim. Confidence >80% to act, <60% do NOT recommend.

MUST ATTENTION apply critical + sequential thinking — every claim needs appropriate traced evidence (file:line for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.

MUST ATTENTION apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting.

• MANDATORY Bootstrap task tracking before target work; transition one task at a time.
• MANDATORY Persist plan/review findings to plans/reports/ incrementally and synthesize from disk.

• MANDATORY Before investigating, planning, or coding, read docs/project-config.json (the project map: modules/paths, run-commands, conventions, architecture/workflow rules) + the required project-reference docs, and cite Reference docs read: ....
• MANDATORY Always include lessons.md; project config + conventions override generic framework defaults.
• MANDATORY If project config, root instruction files, or any required reference doc is missing or stale, auto-run $project-init or the narrow lower-level route before ordinary project-specific work.

• MANDATORY Parent workflow rows do not replace child phase tracking; expand phases and link the parent when nested.
• MANDATORY Orchestrators pre-expand child skill phases before invocation; use [N.M] $skill-name — phase prefixes and one-in_progress discipline.

• MANDATORY Large changeset → batch by size cap (≤8 files OR ≤2000 diff-lines), one parallel sub-agent per batch; never review many files one-by-one.
• MANDATORY > 6 categories OR > 40 files → add the hierarchical synthesis tier; each concern-synthesizer emits cross-concern interaction candidates and the orchestrator runs the cross-concern pass before concluding.

• MANDATORY Classify findings Critical/High/Medium/Low by consequence; Critical/High block PASS until fixed or owner-accepted.
• MANDATORY Score-based skills (sre 0-2, perf two-axis) map onto the same four tiers — no parallel severity vocabulary.

• MANDATORY Derive review categories from file language + directory semantics + change nature; create a sub-task per category.
• MANDATORY Derive each category's concerns from first principles with file:line evidence — never a fixed checklist.

Prompt-Enhance Closing Anchors

IMPORTANT MUST ATTENTION follow declared step order for this skill; NEVER skip, reorder, or merge steps without explicit user approval IMPORTANT MUST ATTENTION for every step/sub-skill call: set in_progress before execution, set completed after execution IMPORTANT MUST ATTENTION every skipped step MUST include explicit reason; every completed step MUST include concise evidence IMPORTANT MUST ATTENTION if Task tools unavailable, maintain an equivalent step-by-step plan tracker with synchronized statuses

• MANDATORY Resolve the active Goal Contract BEFORE work (active plan goal.md → plans/goals/{YYMMDD-HHmm}-{slug}/goal.md → create from current request) and read saved success criteria before editing.
• MANDATORY Append iteration evidence after execution; emit a Goal Satisfaction matrix (PASS/FAIL/BLOCKED) before reporting PASS; loop on validated FAIL; escalate repeated no-progress or blockers. NEVER store secrets in goal files.