refine-review

name	refine-review
description	[Code Quality] Use when you need to review PBI artifact for completeness, missing concerns, and quality before proceeding to story creation.

Codex compatibility note:

• Invoke repository skills with $skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.
• Prefer the plan-hard skill for planning guidance in this Codex mirror.
• 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 does not receive Claude hook-based doc injection. 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)

Situation-based docs:

• Backend/CQRS/API/domain/entity changes: backend-patterns-reference.md, domain-entities-reference.md, project-structure-reference.md
• Frontend/UI/styling/design-system: frontend-patterns-reference.md, scss-styling-guide.md, design-system/README.md
• Spec/test-case planning or TC mapping: feature-docs-reference.md
• 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: Auto-review a refined PBI artifact for completeness, quality, and correctness before story creation proceeds.

Key distinction: AI self-review (automatic), NOT user interview.

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

Frontend/UI Context (if applicable)

When this task involves frontend or UI changes,

• Component patterns: docs/project-reference/frontend-patterns-reference.md (read directly when relevant; do not rely on hook-injected conversation text)
• Styling/BEM guide: docs/project-reference/scss-styling-guide.md
• Design system tokens: docs/project-reference/design-system/README.md

Adversarial Review Mindset (NON-NEGOTIABLE)

Default stance: SKEPTIC reviewing your own work. You just produced this PBI. Your natural bias is to find it acceptable. Break that bias deliberately.

Self-review trap: The AI wrote this PBI moments ago. Every reasoning chain you used to WRITE it is still active in this context. You will find it coherent because YOU made it coherent — not because it is correct. This section forces adversarial challenge.

Adversarial Techniques (apply ALL before concluding)

1. Scope Creep Detector Read each acceptance criterion. Ask: "Is this required for the core user value, or is it a 'nice to have' that grew in during writing?" Flag any AC that is NOT directly traceable to the problem statement. A PBI with 8 ACs for a simple feature is almost certainly over-scoped.

2. Assumption Stress Test List the 3 biggest assumptions embedded in the acceptance criteria. For each: "What if this assumption is wrong?" Common hidden assumptions: "users will provide valid input," "the data is in the expected format," "the system is in a known state." If any AC fails when an assumption breaks, it needs a corresponding error-path AC.

3. Missing Stakeholder Check Ask: "Who else uses this feature who was NOT the primary user in the problem statement?" (e.g., admins, support staff, other services). Does any missing stakeholder have a use case the PBI does NOT cover? Flag gaps.

4. Pre-Mortem Assume this PBI is implemented exactly as written and deployed. In 3 months, a user files a critical support ticket. Write the most plausible complaint — the gap the PBI failed to address. If you can't find one, you wrote too safe a PBI.

5. Testability Challenge For each acceptance criterion: "Can a QA engineer write an automated test for this AC without asking any clarifying questions?" If not — the AC is ambiguous or unmeasurable. Flag it.

6. Contrarian Pass Before writing any verdict, generate at least 2 sentences arguing the OPPOSITE conclusion. Then decide which argument is stronger.

Forbidden Patterns (self-review specific)

• "ACs look comprehensive" — You wrote them. Of course they look comprehensive to you. Challenge each one.
• "Scope is well-defined" — Did you REDUCE scope during writing? What did you cut? Was cutting justified?
• "Problem statement is clear" — Could it be framed differently to lead to a different (better) solution?
• "Ready for story creation" — Have you checked with INVEST? Would a developer estimate this in < 1 sprint?
• Confirming your own work without adversarial challenge — Forbidden. Find at least one thing to question.

Anti-Bias Gate (MANDATORY before finalizing verdict)

Complete this checklist before writing the final verdict:

• Checked each AC for scope creep (traceable to problem statement)
• Identified 3 hidden assumptions and stress-tested them
• Checked for missing stakeholders
• Ran pre-mortem (most plausible support complaint in 3 months)
• Verified all ACs are unambiguously testable
• Generated at least 2 sentences arguing the opposite verdict

If any box is unchecked — you have NOT completed the adversarial review. Go back.

Workflow

1. Locate PBI — Find latest PBI artifact in team-artifacts/pbis/ or active plan context
2. Evaluate checklist — Score each check as PASS/FAIL
3. Classify — PASS (all Required + >=50% Recommended), WARN (all Required), FAIL (any Required fails)
4. Output verdict — Status, issues, recommendations

Checklist

Required (all must pass)

#	Check	Presence	Quality Depth
1	Problem statement — Clear problem defined (not just solution description)	Is a problem statement section present?	Is the problem scoped correctly? Does it confuse symptoms with root cause? Is it framed to lead to only one solution, or is the solution space left open?
2	Acceptance criteria — Minimum 3 GIVEN/WHEN/THEN scenarios	Are at least 3 GIVEN/WHEN/THEN ACs present?	Are they realistic scenarios, not trivial? Do they cover error paths? Are edge cases specified, or only the happy path?
3	Story points + complexity — Both fields present with valid values	Are story points and complexity both filled in?	Do both values match the scope of work? Is complexity above 5 justified with a rationale, or just assigned arbitrarily?
4	Dependencies table — Has dependency table with must-before/can-parallel/blocked-by types	Is a dependencies table present with typed rows?	Are ALL dependencies captured (technical, data, service)? Are "can-parallel" items truly safe to parallelize, or do they share a resource?
5	Stakeholder validation — User interview was conducted (validation section present)	Is a stakeholder/validation section present?	Was the interview substantive? Does the validation section show actual user responses and insights, or just "interviewed on [date]"?
6	No vague language — No "should work", "might need", "TBD" in acceptance criteria	Are all ACs free of vague terms?	Are "should work"/"TBD"/"might need" absent from ALL acceptance criteria, including edge cases and error paths?
7	Scope boundary — Clear "out of scope" or "not included" section	Is an out-of-scope section present?	Are out-of-scope items specific enough to prevent scope creep during implementation? Is anything ambiguously in/out?
8	Authorization defined — PBI has "Authorization & Access Control" section with roles × CRUD table	Is an authorization section with a CRUD table present?	Does the CRUD table cover ALL PBI-relevant roles? Are there roles (admin, support, service account) that are missing or not addressed?
9	UI Layout section — If UI: has ## UI Layout section per wireframe protocol. If backend-only: explicit "N/A"	Is a UI Layout section or explicit N/A present?	If UI: does the wireframe have component tree + states + design tokens? If backend-only: is the N/A explicit and justified, not just omitted?
10	Reestimate drift check — Phase 7.5 re-evaluation ran; frontmatter has reestimate_delta_pct + reestimate_reason populated post-Validation Interview	Are reestimate_delta_pct and reestimate_reason present in frontmatter?	Was the re-evaluation actually performed against the LOCKED scope (post-Phase 7), or copy-pasted? If |delta| > 20%, were SP/complexity/man_days fields actually updated to match? If |delta| > 50%, is there a documented user rescope decision in ## Validation Summary? Stale Phase 6 numbers with a delta_pct: 0 and no reason = FAIL.

Recommended (>=50% should pass)

#	Check	Presence	Quality Depth
1	RICE/MoSCoW score — Prioritization applied	Is a RICE or MoSCoW prioritization score present?	Is the scoring justified with data or reasoning, or assigned arbitrarily without rationale?
2	Domain vocabulary — Uses project-specific terms from domain-entities-reference.md	Are domain-specific terms used in the PBI?	Is domain language consistent with domain-entities-reference.md, or are new terms introduced without definition?
3	Risk assessment — Risks identified with mitigations	Is a risk section present with at least one item?	Are risks specific to this PBI, or generic "technical risk"? Are mitigations actionable (who does what, when triggered)?
4	Non-functional requirements — Performance, security, accessibility considered	Is an NFR section or NFR notes present?	Are perf/security/accessibility numbers specified (e.g., "< 200ms response time", "WCAG AA"), not just "considered" or "addressed"?
5	Production readiness concerns — PBI includes "Production Readiness Concerns" table with Yes/No/Existing	Is the Production Readiness Concerns table present with all 5 rows?	Are all 5 table rows meaningfully filled — not just "Yes" for all? Are gaps called out with rationale?
6	Seed data assessed — PBI addresses seed data needs or explicitly states "N/A"	Is seed data addressed or explicitly marked N/A?	If "N/A" is used, is it justified? Is it the right N/A (no new reference data needed), or is seed data actually required and skipped?
7	Data migration assessed — PBI addresses schema changes and data migration needs or explicitly states "N/A"	Is data migration addressed or explicitly marked N/A?	If "N/A" is used, is it justified? Are there hidden schema implications (added columns, changed constraints) that require migration even if "no new tables"?

Output

## PBI Review Result

**Status:** PASS | WARN | FAIL
**Artifact:** {pbi-path}

### Required ({X}/{Y})

- ✅/❌ Check description

### Recommended ({X}/{Y})

- ✅/⚠️ Check description

### Issues Found

- ❌ FAIL: {issue}
- ⚠️ WARN: {issue}

### Verdict

{PROCEED | REVISE_FIRST}

Round 2+ : Fresh Sub-Agent Re-Review (MANDATORY)

Protocol: SYNC:double-round-trip-review + SYNC:fresh-context-review + SYNC:review-protocol-injection (all inlined above in this file).

After completing Round 1 checklist evaluation, spawn a fresh general-purpose sub-agent for Round 2 using the canonical Agent template from SYNC:review-protocol-injection above. PBI artifact reviews are NOT code reviews — use agent_type: "general-purpose". When constructing the Agent call prompt:

1. Copy the Agent call shape from the SYNC:review-protocol-injection template verbatim
2. Set agent_type: "general-purpose"
3. Embed the full verbatim body of these SYNC blocks: SYNC:evidence-based-reasoning, SYNC:rationalization-prevention, SYNC:understand-code-first (omit code-specific protocols like SYNC:bug-detection, SYNC:design-patterns-quality, SYNC:fix-layer-accountability which are not applicable to PBI artifacts)
4. Set the Task as "Review the PBI artifact for completeness and quality. Focus on: implicit assumptions not validated, missing acceptance criteria coverage, edge cases not addressed, cross-references not verified, vague language, authorization gaps."
5. Set Target Files as the explicit PBI artifact file path
6. Set report path as plans/reports/refine-review-round{N}-{date}.md

After sub-agent returns:

1. Read the sub-agent's report
2. Integrate findings as ## Round {N} Findings (Fresh Sub-Agent) in the main report — DO NOT filter or override
3. If FAIL: fix issues in the PBI, then spawn a NEW Round N+1 fresh sub-agent (new Agent call — never reuse Round 2's agent)
4. Max 3 fresh rounds — escalate to user via a direct user question if still failing after 3 rounds
5. Final verdict must incorporate findings from ALL rounds

Key Rules

• FAIL blocks workflow — If FAIL, do NOT proceed to $story. List specific fixes needed.
• WARN allows proceeding — Note gaps but continue.
• No guessing — Every check must reference specific content in the PBI artifact.
• Constructive — Focus on implementation-blocking issues, not pedantic details.
• Production Readiness — When reviewing production readiness concerns in a PBI, verify coverage of: Code Quality Tooling, Error Handling Foundation, Loading State Management, Docker Development Environment, Integration Points (see SYNC:scaffold-production-readiness for definitions).

---

Next Steps

MANDATORY IMPORTANT MUST ATTENTION — NO EXCEPTIONS after completing this skill, you MUST ATTENTION use a direct user question to present these options. Do NOT skip because the task seems "simple" or "obvious" — the user decides:

• "$story (Recommended)" — Create user stories from validated PBI
• "$refine" — Re-refine if FAIL verdict
• "Skip, continue manually" — user decides

[IMPORTANT] Use task tracking to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.

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

OOP & DRY Enforcement: MANDATORY IMPORTANT MUST ATTENTION — flag duplicated patterns that should be extracted to a base class, generic, or helper. Classes in the same group or suffix (ex *Entity, *Dto, *Service, etc...) MUST ATTENTION inherit a common base (even if empty now — enables future shared logic and child overrides). Verify project has code linting/analyzer configured for the stack.

External Memory: For complex or lengthy work (research, analysis, scan, review), write intermediate findings and final results to a report file in plans/reports/ — prevents context loss and serves as deliverable.

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

Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal. Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing. Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain. Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path. When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site. Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code. Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks. Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis. Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly. Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.

Estimation Framework — Bottom-up first; SP DERIVED; output min-max range when likely ≥3d. Stack-agnostic. Baseline: 3-5yr dev, 6 productive hrs/day. AI estimate assumes Claude Code + project context.

Method:

1. Blast Radius pass (below) — drives code AND test cost
2. Decompose phases → hours/phase → bottom_up_hours = Σ phase_hours
3. likely_days = ceil(bottom_up_hours / 6) × productivity_factor
4. Sum Risk Margin (base + add-ons) → max_days = likely_days × (1 + margin)
5. min_days = likely_days × 0.9
6. Output as range when likely_days ≥3; single point allowed <3 (still record margin)
7. man_days_ai = same range × AI speedup
8. story_points DERIVED from likely_days via SP-Days — NEVER driver. Disagreement >50% → trust bottom-up

Productivity factor: 0.8 strong scaffolding+codegen+AI hooks · 1.0 mature default · 1.2 weak patterns · 1.5 greenfield

Cost Driver Heuristic (apply BEFORE work-type row):

• UI dominates in CRUD/business apps — 1.5-3x backend (states, validation, responsive, a11y, polish)
• Backend dominates ONLY: multi-aggregate invariants, cross-service contracts, schema migrations, heavy query/perf, new event flows

Reuse-vs-Create axis (PRIMARY lever, per layer):

UI tier	Cost
Reuse component on existing screen	0.1-0.3d
Add control/column to existing screen	0.3-0.8d
Compose components into NEW screen	1-2d
NEW screen, custom layout/states/validation	2-4d
NEW shared/common component (themed, tested)	3-6d+

Backend tier	Cost
Reuse query/handler from new place	0.1-0.3d
Small update existing handler/entity	0.3-0.8d
NEW query on existing repo/model	0.5-1d
NEW command/handler on existing aggregate (additive)	1-2d
NEW aggregate/entity (repo, validation, events)	2-4d
NEW cross-service contract OR schema migration	2-4d each
Multi-aggregate invariant / heavy domain rule	3-5d

Rule: Sum tiers across UI+backend+tests, apply productivity factor. Reuse short-circuits tiers — call out.

Test-Scope drivers (compute test_count EXPLICITLY — "+tests" hand-wave is #1 failure):

Driver	Count
Happy-path journeys	1 per story / AC main flow
State-machine transitions	reachable transitions × allowed actors
Multi-entity state combos	state(A) × state(B) — REACHABLE only, not Cartesian
Authorization matrix	(owner, non-owner, elevated, unauth) × each mutation
Validation rules	1 per required field / boundary / format / cross-field
UI states (per new screen/dialog)	happy, loading, empty, error, partial — present only
Negative paths / invariants	1 per violatable business rule

Test tier (Trad, incl. setup+assert+flake)	Cost
1-5 cases, fixtures reused	0.3-0.5d
6-12 cases, 1 new fixture	0.5-1d
13-25 cases, multi-entity setup	1-2d
26-50 cases OR new state-machine coverage	2-3d
>50 cases OR full E2E journey	3-5d

Test multipliers: new fixture/seed harness +0.5d · cross-service/bus assertion +0.3d each · UI E2E ×1.5 · each new role +1-2 cases

Blast Radius (mandatory pre-pass — affects code AND test):

1. Files/components directly modified — count
2. Of those, "complex" (>500 LOC, multi-handler, central, frequently-modified) — count
3. Downstream consumers (callers, event subscribers, cross-service) — list
4. Shared/common code touched (multi-app blast) — yes/no
5. Regression scope — areas needing re-test

Rule: Complex touch → add risk_factors. Each downstream consumer → +1-3 regression cases. Blast >5 areas OR >2 complex → re-evaluate SPLIT before estimating.

Risk Margin (drives max bound):

likely_days	Base margin
<1d trivial	+10%
1-2d small additive	+20%
3-4d real feature	+35%
5-7d large	+50%
8-10d very large	+75%
>10d	+100% AND flag SHOULD SPLIT

Risk-factor add-ons (additive — enumerate in risk_factors):

Factor	+margin
touches-complex-existing-feature (>500 LOC, multi-handler, central)	+20%
cross-service-contract change	+25%
schema-migration-on-populated-data	+25%
new-tech-or-unfamiliar-pattern	+30%
regression-fan-out (≥3 downstream areas re-test)	+20%
performance-or-latency-critical	+20%
concurrency-race-event-ordering	+25%
shared-common-code (multi-consumer/multi-app)	+25%
unclear-requirements-or-design	+30%

Collapse rule: total margin >100% → STOP, split (padding past 2x is dishonesty). Margin <15% on likely_days ≥5 → under-estimated, widen.

Work-Type Caps (hard ceilings on likely_days):

Work type	Max SP	Max likely
Single field / config flag / style fix	1	0.5d
Add property to existing model + bind to existing UI	2	1d
Additive endpoint + minor UI control (button/menu/column), reuses fixtures	3	2-3d
Additive endpoint + NEW UI surface OR additive multi-layer + new domain rule + 2+ test files	5	3-5d
NEW model/aggregate OR migration OR cross-module contract OR heavy test (>1.5d) OR NEW UI + non-trivial backend	8	5-7d
NEW UI surface + (NEW aggregate OR migration OR cross-service contract)	13	SHOULD split
Cross-service contract + migration combined	13	SHOULD split
Beyond	21	MUST split

SP→Days (validation only): 1=0.5d/0.25d · 2=1d/0.35d · 3=2d/0.65d · 5=4d/1.0d · 8=6d/1.5d · 13=10d/2.0d (Trad/AI likely) AI speedup: SP 1≈2x · 2-3≈3x · 5-8≈4x · 13+≈5x. AI cost = (code_gen × 1.3) + (test_gen × 1.3) (30% review overhead).

MANDATORY frontmatter:

story_points: <n>
complexity: low | medium | high | critical
man_days_traditional: '<min>-<max>d' # range when likely ≥3d; '<N>d' when <3d
man_days_ai: '<min>-<max>d'
risk_margin_pct: <n> # base + add-ons
risk_factors: [touches-complex-existing-feature, regression-fan-out] # closed-list from add-ons; [] if none
blast_radius:
    touched_areas: <n>
    complex_touched: <n>
    downstream_consumers: [list or count]
    shared_common_code: yes | no
estimate_scope_included: [code, integration-tests, frontend, i18n, docs]
estimate_scope_excluded: [unit-tests, e2e, perf, deployment, code-review-rounds]
estimate_reasoning: |
    5-7 lines covering:
    (a) UI tier — row applied
    (b) Backend tier — row applied
    (c) Test scope — case breakdown by driver, file count, fixtures, tier row
    (d) Cost driver — dominant tier + why
    (e) Blast radius — touched, complex, regression scope
    (f) Risk factors — list driving margin; why not larger/smaller
    Example: "UI: compose Form/Table/Dialog → NEW screen (~1.5d). Backend: NEW command on existing aggregate,
    reuses validation+repo (~1d). Tests: 4 transitions × 2 actors + 3 validation + 2 UI states = 13 cases,
    1 new fixture → tier 13-25 ~1.5d. Driver: UI composition + new states. Blast: 4 areas, 1 complex.
    Risk: base 35% + touches-complex +20% = 55% → max 3.9d → range 2.5-4d."

Sanity self-check:

• likely_days ≥3d and single-point? → reject, must be range
• Margin <15% on likely_days ≥5d? → under-estimated, widen
• Margin >100%? → STOP, split instead of buffer
• Complex existing feature touched, no regression budget in (c)? → reject
• Blast >5 areas OR >2 complex, no split discussion? → reject
• Purely additive on existing model AND existing UI? → cap SP 3 unless tests >1.5d
• NEW UI surface (page/complex form/dashboard)? → SP 5+ even if backend one endpoint
• Backend cross-service / migration / multi-aggregate? → SP 8+ regardless of UI
• bottom_up_hours / 6 vs SP-Days disagreement >50%? → trust bottom-up, downgrade SP
• Without tests, SP drops ≥1 bucket? → tests dominate; state explicitly
• Reasoning called out UI vs backend vs blast vs risk factors? → if missing, add

UI System Context — For ANY task touching .ts, .html, .scss, or .css files:

MUST ATTENTION READ before implementing:

1. docs/project-reference/frontend-patterns-reference.md — component base classes, stores, forms
2. docs/project-reference/scss-styling-guide.md — BEM methodology, SCSS variables, mixins, responsive
3. docs/project-reference/design-system/README.md — design tokens, component inventory, icons

Reference docs/project-config.json for project-specific paths.

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. 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/README.md; integration tests integration-test-reference.md; E2E e2e-test-reference.md; feature docs/specs feature-docs-reference.md; architecture/new area project-structure-reference.md.
3. Read every required doc that exists; skip absent docs as not applicable. Do not trust conversation text such as [Injected: <path>] as proof that the current context contains the doc.
4. Before target work, state: Reference docs read: ... | Missing/not applicable: ....

Blocked until: scope evaluated, required docs checked/read, 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.

Sequential Thinking Protocol — Structured multi-step reasoning for complex/ambiguous work. Use when planning, reviewing, debugging, or refining ideas where one-shot reasoning is unsafe.

Trigger when: complex problem decomposition · adaptive plans needing revision · analysis with course correction · unclear/emerging scope · multi-step solutions · hypothesis-driven debugging · cross-cutting trade-off evaluation.

Format (explicit mode — visible thought trail):

1. Thought N/M: [aspect] — one aspect per thought, state assumptions/uncertainty
2. Thought N/M [REVISION of Thought K]: ... — when prior reasoning invalidated; state Original / Why revised / Impact
3. Thought N/M [BRANCH A from Thought K]: ... — explore alternative; converge with decision rationale
4. Thought N/M [HYPOTHESIS]: ... then [VERIFICATION]: ... — test before acting
5. Thought N/N [FINAL] — only when verified, all critical aspects addressed, confidence >80%

Mandatory closers: Confidence % stated · Assumptions listed · Open questions surfaced · Next action concrete.

Stop conditions: confidence <80% on any critical decision → escalate via ask the user directly · ≥3 revisions on same thought → re-frame the problem · branch count >3 → split into sub-task.

Implicit mode: apply methodology internally without visible markers when adding markers would clutter the response (routine work where reasoning aids accuracy).

Deep-dive: see $sequential-thinking skill (.claude/skills/sequential-thinking/SKILL.md) for worked examples (api-design, debug, architecture), advanced techniques (spiral refinement, hypothesis testing, convergence), and meta-strategies (uncertainty handling, revision cascades).

Fix-Triggered Re-Review Loop — Re-review is triggered by a FIX CYCLE, not by a round number. Review purpose: review → if issues → fix → re-review until a round finds no issues. A clean review ENDS the loop — no further rounds required.

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) → fix the issues, then spawn a fresh sub-agent for Round 2 re-review.

Fresh sub-agent re-review (after every fix cycle): Spawn a NEW spawn_agent tool call — never reuse a prior agent. Sub-agent re-reads 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 round 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 fresh round, repeat the same decision: clean → END; issues → fix → next fresh round. Continue until a round finds zero issues, or 3 fresh-subagent rounds max, then escalate to user via a direct user question.

Rules:

• A clean Round 1 ENDS the review — no mandatory Round 2
• NEVER skip the fresh sub-agent re-review after a fix cycle (every fix invalidates the prior verdict)
• NEVER reuse a sub-agent across rounds — every iteration spawns a NEW Agent call
• Main agent READS sub-agent reports but MUST NOT filter, reinterpret, or override findings
• Max 3 fresh-subagent rounds per review — if still FAIL, escalate via a direct user question (do NOT silently loop)
• Track round count 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 Sub-Agent Review — Eliminate orchestrator confirmation bias via isolated sub-agents.

Why: The main agent knows what it (or $cook) 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 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: fix → fresh sub-agent re-review.

How:

1. Spawn a NEW spawn_agent tool call — use code-reviewer subagent_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 round found zero issues (no fixes = nothing new to verify)
• NEVER skip fresh sub-agent 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
• Max 3 fresh-subagent rounds per review — escalate via a direct user question if still failing; do NOT silently loop or fall back to any prior protocol
• Track iteration count in conversation context (session-scoped, no persistent files)

Review Protocol Injection — Every fresh sub-agent review prompt MUST embed 10 protocol blocks VERBATIM. The template below has ALL 10 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 10 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)

### 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: JS: === vs ==, typeof null. C#: async void, missing using, LINQ deferred execution.
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.
NEVER mark review PASS without completing both traces (happy + error path).

### Test Spec Verification
Map changed code to test specifications.
1. From changed files → find TC-{FEAT}-{NNN} in docs/business-features/{Service}/detailed-features/{Feature}.md Section 15.
2. Every changed code path MUST map to a corresponding TC (or flag as "needs TC").
3. New functions/endpoints/handlers → flag for test spec creation.
4. Verify TC evidence fields point to actual code (file:line, not stale references).
5. Auth changes → TC-{FEAT}-02x exist? Data changes → TC-{FEAT}-01x exist?
6. If no specs exist → log gap and recommend $tdd-spec.
NEVER skip test mapping. Untested code paths are the #1 source of production bugs.

### 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)
- 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 10 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 subagent_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

Graph Impact Analysis — When .code-graph/graph.db exists, run blast-radius --json to detect ALL files affected by changes (7 edge types: CALLS, MESSAGE_BUS, API_ENDPOINT, TRIGGERS_EVENT, PRODUCES_EVENT, TRIGGERS_COMMAND_EVENT, INHERITS). Compute gap: impacted_files - changed_files = potentially stale files. Risk: <5 Low, 5-20 Medium, >20 High. Use trace --direction downstream for deep chains on high-impact files.

• MANDATORY IMPORTANT MUST ATTENTION execute the review loop: review → if issues → fix → fresh sub-agent re-review. A round that finds zero issues ENDS the review.

**IMPORTANT MUST ATTENTION** run `blast-radius` when graph.db exists. Flag impacted files NOT in changeset as potentially stale.

**IMPORTANT MUST ATTENTION** read frontend-patterns-reference, scss-styling-guide, design-system/README before any UI change.

• MANDATORY MUST ATTENTION estimation: bottom-up phase hours drive man_days_traditional (Σh/6 × productivity_factor); SP DERIVED. UI cost usually dominates — bump SP one bucket if NEW UI surface (page/complex form/dashboard). Frontmatter MUST include story_points, complexity, man_days_traditional, man_days_ai, estimate_scope_included, estimate_scope_excluded, estimate_reasoning (UI vs backend cost driver). Cap SP 3 for additive-on-existing-model+existing-UI unless test scope >1.5d. SP 13 SHOULD split, SP 21 MUST split.

MUST ATTENTION apply critical thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact.

MUST ATTENTION apply sequential-thinking — multi-step Thought N/M, REVISION/BRANCH/HYPOTHESIS markers, confidence % closer; see $sequential-thinking skill.

MUST ATTENTION apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction.

• 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 After task-tracking bootstrap and before target/source work, read required project-reference docs and cite Reference docs read: ....
• MANDATORY Always include lessons.md; project conventions override generic defaults.

• 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.

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

Closing Reminders

MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using task tracking BEFORE starting. MANDATORY IMPORTANT MUST ATTENTION validate decisions with user via a direct user question — never auto-decide. MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify work quality. MANDATORY IMPORTANT MUST ATTENTION READ the following files before starting:

[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using task tracking.

[IMPORTANT] Analyze how big the task is and break it into many small todo tasks systematically before starting — this is very important.

Hookless Prompt Protocol Mirror (Auto-Synced)

Source: .claude/hooks/lib/prompt-injections.cjs + .claude/.ck.json

[WORKFLOW-EXECUTION-PROTOCOL] [BLOCKING] Workflow Execution Protocol — MANDATORY IMPORTANT MUST CRITICAL. Do not skip for any reason.

1. DETECT: Match prompt against workflow catalog
2. ANALYZE: Find best-match workflow AND evaluate if a custom step combination would fit better
3. ASK (REQUIRED FORMAT): Use a direct user question with this structure:
   • Question: "Which workflow do you want to activate?"
   • Option 1: "Activate [BestMatch Workflow] (Recommended)"
   • Option 2: "Activate custom workflow: [step1 → step2 → ...]" (include one-line rationale)
4. ACTIVATE (if confirmed): Call $workflow-start <workflowId> for standard; sequence custom steps manually
5. CREATE TASKS: task tracking for ALL workflow steps
6. EXECUTE: Follow each step in sequence [CRITICAL-THINKING-MINDSET] Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination principle: 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. AI Attention principle (Primacy-Recency): Put the 3 most critical rules at both top and bottom of long prompts/protocols so instruction adherence survives long context windows.

Learned Lessons

Lessons Learned

[CRITICAL] Hard-won project debugging/architecture rules. MUST ATTENTION apply BEFORE forming hypothesis or writing code.

Quick Summary

Goal: Prevent recurrence of known failure patterns — debugging, architecture, naming, AI orchestration, environment.

Top Rules (apply always):

• MUST ATTENTION verify ALL preconditions (config, env, DB names, DI regs) BEFORE code-layer hypothesis
• MUST ATTENTION fix responsible layer — NEVER patch symptom sites with caller-specific defensive code
• MUST ATTENTION use ExecuteInjectScopedAsync for parallel async + repo/UoW — NEVER ExecuteUowTask
• MUST ATTENTION name by PURPOSE not CONTENT — adding member forces rename = abstraction broken
• MUST ATTENTION persist sub-agent findings incrementally after each file — NEVER batch at end
• MUST ATTENTION Windows bash: verify Python alias (where python/where py) — NEVER assume python/python3 resolves

---

Debugging & Root Cause Reasoning

• [2026-04-11] Holistic-first: verify environment before code. Failure → list ALL preconditions (config, env vars, DB names, endpoints, DI regs, credentials, permissions, data prerequisites) → verify each via evidence (grep/cat/query) BEFORE code-layer hypothesis. Worst rabbit holes: diving nearest layer while bug sits elsewhere — e.g., hours debugging "sync timeout", real cause: test appsettings pointing wrong DB. Cheapest check first.
• [2026-04-01] Ask "whose responsibility?" before fixing. Trace: bug in caller (wrong data) or callee (wrong handling)? Fix responsible layer — NEVER patch symptom site masking real issue.
• [2026-04-01] Trace data lifecycle, not error site. Follow data: creation → transformation → consumption. Bug usually where data created wrong, not consumed.
• [2026-04-01] Code is caller-agnostic. Functions/handlers/consumers don't know who invokes them. Comments/guards/messages describe business intent — NEVER reference specific callers (tests, seeders, scripts).

Architecture Invariants

• [2026-03-31] ParallelAsync + repo/UoW MUST use ExecuteInjectScopedAsync, NEVER ExecuteUowTask. ExecuteUowTask creates new UoW but reuses outer DI scope (same DbContext) — parallel iterations sharing non-thread-safe DbContext silently corrupt data. ExecuteInjectScopedAsync creates new UoW + new DI scope (fresh repo per iteration).
• [2026-03-31] Bus message naming MUST include service name prefix — core services NEVER consume feature events. Prefix declares schema ownership (AccountUserEntityEventBusMessage = Accounts owns). Core services (Accounts, Communication) are leaders. Feature services (Growth, Talents) sending to core MUST use {CoreServiceName}...RequestBusMessage — never define own event for core to consume.

Naming & Abstraction

• [2026-04-12] Name PURPOSE not CONTENT — "OrXxx" anti-pattern. HrManagerOrHrOrPayrollHrOperationsPolicy names set members, not what it guards. Add role → rename = broken abstraction. Rule: names express DOES/GUARDS, not CONTAINS. Test: adding/removing member forces rename? YES = content-driven = bad → rename to purpose (e.g., HrOperationsAccessPolicy). Nuance: "Or" fine in behavioral idioms (FirstOrDefault, SuccessOrThrow) — expresses HAPPENS, not membership.

Environment & Tooling

• [2026-04-20] Windows bash: NEVER assume python/python3 resolves — verify alias first. Python may not be in bash PATH under those names. Check: where python / where py. Prefer py (Windows Python Launcher) for one-liners, node if JS alternative exists.

Test-specific lessons → docs/project-reference/integration-test-reference.md Lessons Learned section. Production-code anti-patterns → docs/project-reference/backend-patterns-reference.md Anti-Patterns section. Generic debugging/refactoring reminders → System Lessons in .claude/hooks/lib/prompt-injections.cjs.

---

Closing Reminders

• IMPORTANT MUST ATTENTION holistic-first: verify ALL preconditions (config, env, DB names, endpoints, DI regs) BEFORE code-layer hypothesis — cheapest check first
• IMPORTANT MUST ATTENTION fix responsible layer — NEVER patch symptom site; trace caller (wrong data) vs callee (wrong handling), fix root owner
• IMPORTANT MUST ATTENTION parallel async + repo/UoW → ALWAYS ExecuteInjectScopedAsync, NEVER ExecuteUowTask (shared DbContext = silent data corruption)
• IMPORTANT MUST ATTENTION bus message prefix = schema ownership; feature services NEVER define events for core services — use {CoreServiceName}...RequestBusMessage
• IMPORTANT MUST ATTENTION name by PURPOSE — adding/removing member forces rename = broken abstraction
• IMPORTANT MUST ATTENTION sub-agents MUST write findings after each file/section — NEVER batch all findings into one final write
• IMPORTANT MUST ATTENTION Windows bash: NEVER assume python/python3 resolves — run where python/where py first, use py launcher or node

[LESSON-LEARNED-REMINDER] [BLOCKING] Task Planning & Continuous Improvement — MANDATORY. Do not skip.

Break work into small tasks (task tracking) before starting. Add final task: "Analyze AI mistakes & lessons learned".

Extract lessons — ROOT CAUSE ONLY, not symptom fixes:

1. Name the FAILURE MODE (reasoning/assumption failure), not symptom — "assumed API existed without reading source" not "used wrong enum value".
2. Generality test: does this failure mode apply to ≥3 contexts/codebases? If not, abstract one level up.
3. Write as a universal rule — strip project-specific names/paths/classes. Useful on any codebase.
4. Consolidate: multiple mistakes sharing one failure mode → ONE lesson.
5. Recurrence gate: "Would this recur in future session WITHOUT this reminder?" — No → skip $learn.
6. Auto-fix gate: "Could $code-review/$code-simplifier/$security/$lint catch this?" — Yes → improve review skill instead.
7. BOTH gates pass → ask user to run $learn. [TASK-PLANNING] [MANDATORY] BEFORE executing any workflow or skill step, create/update task tracking for all planned steps, then keep it synchronized as each step starts/completes.