dor-gate

name	dor-gate
description	[Code Quality] Use when you need to validate a PBI against Definition of Ready before grooming.

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:

• 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 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: Validate a PBI artifact against the Definition of Ready (DoR/M1-M6) checklist so that only grooming-ready PBIs pass the gate — every failure is caught with its concrete section/line citation, blocking ambiguous, untestable, or unimplementable stories from reaching the team.

Summary:

• This is an automated quality gate, NOT a collaborative review — it runs two checklists: the 7 Required DoR criteria (story template, testable AC, wireframes, UI design, AI pre-review, story points, dependencies) AND the M1-M6 compliance gate; ANY single failure across either set returns FAIL.
• The DoR is self-contained here (BA Refinement Context section) — no external protocol file is needed; every verdict must cite the concrete PBI section + line/AC, and a PASS over any M1-M5 violation is itself defective.
• Verify story-point estimation frontmatter (Fibonacci 1-21 + complexity, man-days range, blast-radius) per the SYNC estimation framework; story points >13 trigger a SHOULD-SPLIT WARN (not a FAIL).
• Emit the DoR Gate Result template (checklist table + Blocking Items + Verdict), then route via a direct user question — never auto-decide the next step.

Key distinction: Automated quality gate (not collaborative review — use $pbi-challenge for that).

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

Workflow

1. Locate PBI — Find PBI artifact in team-artifacts/pbis/ or active plan context. If not found, ask user for path.
2. Load DoR protocol — Apply DoR 7-criteria checklist (story template, testable AC, wireframes, UI design, AI pre-review, story points, dependencies)
3. Evaluate each criterion — Parse PBI sections against 7 DoR items:
   • Check user story template format ("As a... I want... So that...")
   • Scan AC for vague language ("should", "might", "TBD", "etc.", "various")
   • Verify GIVEN/WHEN/THEN format (min 3 scenarios)
   • Check for wireframe/mockup references (or explicit "N/A" for backend-only)
   • Check for UI design status
   • Verify story_points and complexity fields present with valid values
   • Verify dependencies table with correct columns
4. Classify result:
   • PASS — All 7 criteria pass → ready for grooming
   • FAIL — Any criterion fails → blocked, list fixes needed
5. Output verdict — Use the DoR Gate Output Template from protocol

Checklist (from protocol)

Required (ALL must pass)

• MUST ATTENTION verify User story template — "As a {role}, I want {goal}, so that {benefit}" present
• MUST ATTENTION verify AC testable — All AC use GIVEN/WHEN/THEN, no vague language, min 3 scenarios
• MUST ATTENTION verify Wireframes/mockups — Present or explicit "N/A" for backend-only
• MUST ATTENTION verify UI design ready — Completed or "N/A" for backend-only
• MUST ATTENTION verify AI pre-review — $review-artifact --type=pbi or $pbi-challenge result is PASS or WARN
• MUST ATTENTION verify Story points — Valid Fibonacci (1-21) + complexity (Low/Medium/High)
• MUST ATTENTION verify Dependencies table — Complete with Type column (must-before/can-parallel/blocked-by/independent)

M1-M6 Compliance Gate (BLOCKING — each check FAILs the gate)

Contract: See .claude/skills/shared/sdd-artifact-contract.md → "AI-SDD Mandates (M1-M6)". DoR enforces M6: a PBI that violates any of M1-M5 is NOT ready for grooming — return FAIL and name the violated mandate ID with its concrete PBI section + line/AC citation. A DoR PASS over an M1-M5 violation is itself defective.

Carriers are EXEMPT from M1/M2 — source identifiers are CORRECT inside [Source: ...], **Evidence**, **IntegrationTest** fields, YAML frontmatter, and ```mermaid ``` blocks. Only flag leakage in PBI narrative prose (problem statement, AC text, scope, rule descriptions). Banned prose token list: spec-principles.md §3.2.

• MUST ATTENTION verify M1 — Tech-agnostic prose — FAIL if problem statement, AC, or rule prose names a framework/product, language-native type, or product/design-pattern class name (banned list in spec-principles.md §3.2). Cite section + token.
• MUST ATTENTION verify M2 — No source code in prose — FAIL if a requirement is expressed as a class/method/file-path/namespace instead of a business operation. Source identifiers belong only in evidence carriers. Cite section + line.
• MUST ATTENTION verify M3 — Abstract-IDs-first — FAIL if a requirement/rule lacks a logical ID (FR-/BR-/OP-), has a logical ID but no [Source: namespace/service/id] abstract-anchor evidence, uses physical code coordinates or repository-root paths instead of an abstract anchor, or makes the anchor its primary citation. Evidence is REQUIRED and KEPT, but SECONDARY to the logical ID (physical coordinates live only in the provenance sidecar).
• MUST ATTENTION verify M4 — Unambiguous AC — FAIL if any AC uses vague language ("handle appropriately", "process normally", "as needed"), two engineers could implement it differently while both claiming conformance, or no observable completion state / named error condition exists. (Reinforces the "AC testable" required criterion above.)
• MUST ATTENTION verify M5 — Implementable from artifact alone — FAIL if a competent team with ZERO codebase knowledge could not implement the PBI on a different stack from the PBI alone (relies on reading source to understand it). Cite section + missing detail.

If ANY box fails → DoR result is FAIL; list each violated mandate ID with its concrete section/line citation in the Blocking Items.

BA Refinement Context (canonical DoR)

Applies to Writes under team-artifacts/pbis/. Mirrored for Codex via SYNC:refinement-dor-checklist / SYNC:ba-team-decision-model in AGENTS.md (do not hand-edit the mirror). This is the self-contained DoR source — no external protocol-file dependency required to run the gate.

Decision Model: 2/3 majority vote (UX BA + Designer BA + Dev BA PIC). Dev BA PIC has technical veto. Disagree-and-commit after decision. Grooming override requires >75% remaining-team vote.

DoR Gate (ALL must pass before grooming):

• User story template (As a... I want... So that...)
• AC testable (GIVEN/WHEN/THEN, no vague language; min 3 scenarios + 1 auth scenario)
• Wireframes attached (UX BA) + UI design ready (Designer BA); backend-only → explicit "N/A"
• AI pre-review passed ($review-artifact --type=pbi or $pbi-challenge returned PASS or WARN)
• Story points estimated (Fibonacci 1-21 + complexity); >13 SP → recommend split
• Dependencies table complete (Dependency · Type must-before/can-parallel/blocked-by/independent · Status)

Failure fixes: Vague AC → specify exact CRUD + roles. Missing auth → add roles × CRUD table. No wireframes → UX BA creates. TBD in AC → replace with decision.

Output

## DoR Gate Result

**PBI:** {PBI filename}
**Status:** PASS | FAIL
**Date:** {date}

### Checklist Results

| #   | Criterion                   | Status    | Evidence / Issue |
| --- | --------------------------- | --------- | ---------------- |
| 1   | User story template         | ✅/❌     | {evidence}       |
| 2   | AC testable and unambiguous | ✅/❌     | {evidence}       |
| 3   | Wireframes/mockups          | ✅/❌/N/A | {evidence}       |
| 4   | UI design ready             | ✅/❌/N/A | {evidence}       |
| 5   | AI pre-review passed        | ✅/❌     | {evidence}       |
| 6   | Story points estimated      | ✅/❌     | {evidence}       |
| 7   | Dependencies complete       | ✅/❌     | {evidence}       |

### Blocking Items (if FAIL)

1. {Fix instruction}

### Verdict

**{READY_FOR_GROOMING | FIX_REQUIRED}**

Key Rules

• FAIL blocks grooming — If ANY required criterion fails, PBI cannot enter grooming. List specific fixes.
• No guessing — Every check must reference specific content (line numbers) in the PBI artifact.
• Protocol is source of truth — Always reference refinement-dor-checklist-protocol.md for criteria definitions.
• Story points >13 — Flag recommendation to split (not a FAIL, but a strong WARN).

---

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:

• "$prioritize (Recommended)" — If PASS: PBI is grooming-ready; prioritize into the backlog
• "$refine" — If FAIL: revise PBI
• "$pbi-challenge" — If collaborative review needed before re-checking DoR
• "Skip, continue manually" — user decides

[IMPORTANT] Use task tracking to break ALL work into small tasks BEFORE starting.

Evidence Gate: MANDATORY IMPORTANT MUST ATTENTION — every claim requires file:line proof or traced evidence with confidence percentage (>80% to act).

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.

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

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.

• 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 + 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.

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

IMPORTANT MUST ATTENTION Goal: Only grooming-ready PBIs pass the gate — every DoR/M1-M6 failure caught with its concrete section/line citation, so no ambiguous, untestable, or unimplementable story reaches the team.

IMPORTANT MUST ATTENTION — Protocols in force (concise digest of the SYNC/shared blocks this skill carries; each is a signpost to its canonical body above, NEVER a replacement):

• AI Mistakes: holistic-first debugging, fix at responsible layer, surgical diff, verify all outputs.
• Estimation: bottom-up phase hours drive man-days; SP derived; >13 SHOULD-SPLIT.
• Critical Thinking: traced proof per claim, confidence >80% to act, never guess.

MANDATORY IMPORTANT MUST ATTENTION FAIL blocks grooming — ANY of the 7 required criteria OR any M1-M5 mandate fails → return FAIL, name the violated ID with its concrete PBI section + line/AC citation. NEVER PASS over an M1-M5 violation — a PASS over one is itself defective. — why: an unready story poisons grooming and ships ambiguity downstream. IMPORTANT MUST ATTENTION automated quality gate, NOT collaborative review — run both checklists (7 required + M1-M6); route $pbi-challenge for collaborative review. — why: conflating gate with review lets soft-pass judgments through a hard gate. IMPORTANT MUST ATTENTION cite file:line/section evidence for EVERY verdict (confidence >80% to act, <60% DO NOT decide) — every check references the concrete PBI section + line/AC; NEVER guess a criterion's status. — why: an uncited PASS/FAIL is unauditable and pattern-matched, not verified. IMPORTANT MUST ATTENTION carriers EXEMPT from M1/M2 — source identifiers are CORRECT inside [Source: ...], **Evidence**, **IntegrationTest**, YAML frontmatter, ```mermaid ```; flag leakage ONLY in PBI narrative prose (banned tokens: spec-principles.md §3.2). — why: flagging a carrier as a violation is a false FAIL that blocks a ready PBI. IMPORTANT MUST ATTENTION verify story-point frontmatter per the SYNC estimation framework — Fibonacci 1-21 + complexity, bottom-up man_days range, blast-radius; story points >13 → SHOULD-SPLIT WARN, NOT a FAIL. — why: a WARN escalated to a FAIL wrongly blocks a groomable large story. MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks via task tracking BEFORE starting; add a final review todo verifying every verdict cites its PBI section/line. MANDATORY IMPORTANT MUST ATTENTION emit the DoR Gate Result template (checklist table + Blocking Items + Verdict), then route via a direct user question — never auto-decide the next step.

Anti-Rationalization:

Evasion	Rebuttal
"AC looks testable enough, pass it"	Show GIVEN/WHEN/THEN ×3 + 1 auth scenario, no vague tokens. No proof = FAIL.
"M1-M5 is minor, the rest passes — PASS overall"	ANY M1-M5 violation = FAIL. A PASS over an M1-M5 violation is itself defective.
"Source name in [Source: ...] — flag it M1/M2"	Carriers are EXEMPT. Flag leakage ONLY in narrative prose, never in evidence carriers.
"Story points >13, fail the gate"	>13 SP = SHOULD-SPLIT WARN, not a FAIL. Do not escalate a WARN to a FAIL.
"Skip a direct user question, result is obvious"	NEVER auto-decide. Emit the result template, then route via a direct user question — the user decides.

[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.

---

IMPORTANT MUST ATTENTION FAIL blocks grooming on ANY required-criterion or M1-M5 failure — name the violated ID + cite PBI section/line; NEVER PASS over an M1-M5 violation. IMPORTANT MUST ATTENTION cite file:line/section for EVERY verdict (>80% confidence to act); NEVER guess a check's status. IMPORTANT MUST ATTENTION emit the DoR Gate Result template, then route via a direct user question — never auto-decide.

Hookless Prompt Protocol Mirror (Auto-Synced)

Source: .claude/.ck.json + .claude/skills/shared/sync-inline-versions.md (:full blocks) + .claude/scripts/lib/hookless-prompt-protocol.cjs

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

Generic portability boundary: Reusable skills and protocol text stay project-neutral; project-specific conventions are discovered from docs/project-config.json and docs/project-reference/. Apply shared AI-SDD from shared/sdd-artifact-contract.md. Read docs/project-config.json and docs/project-reference/docs-index-reference.md, then open the project reference docs named there. For spec, test-case, behavior-change, public-contract, or docs/specs/ work, route through the local spec docs named by the docs index: feature-spec-reference.md, spec-system-reference.md, spec-principles.md, and workflow-spec-test-code-cycle-reference.md when specs/tests/code must stay synchronized. If either file or a required reference doc is missing or stale, auto-run $project-init (or the narrow lower-level route such as $project-config, $docs-init, $scan-all, or $scan --target=<key>) before ordinary project-specific work. Any supported AI tool may execute when this shared context and local docs are available.

1. DETECT: If the prompt starts with an explicit slash skill/workflow command, execute it directly. Otherwise match the prompt against the workflow catalog and skill list.
2. ANALYZE: Choose the best option: execute directly, invoke a skill, activate a standard workflow, or compose a custom step combination.
3. AUTO-SELECT: Pick the best option yourself. Do not ask the user to choose between direct execution, skill, standard workflow, or custom workflow.
4. ACTIVATE: For a selected workflow, call $start-workflow <workflowId>; for a selected skill, invoke that skill; for a custom workflow, sequence custom steps directly; for direct execution, proceed with the task.
5. CREATE TASKS: task tracking for ALL workflow/skill/custom steps before execution when the selected path has multiple steps.
6. EXECUTE: Advance per the Workflow Step Advancement & Parallel Phases rule in your context instructions — model-driven; a sub-agent completion advances a step identically to an inline call; a parallel-phase group is an all-return barrier (advance only after ALL members return, never serialize it)

Shared AI-SDD Protocol Markers

Source: .claude/skills/shared/sync-inline-versions.md

SYNC:ai-sdd-artifact-contract

AI-SDD Artifact Contract — Shared spec-driven development rules stay portable and source-owned.

1. Keep reusable AI-SDD principles in .claude; put repository-specific paths, commands, owners, products, and formats in project config/reference docs.
2. Preserve cycle: spec -> plan -> tasks -> implement -> verify -> update spec/docs.
3. Trace every requirement or invariant through decision, task, TC/test, source evidence, and docs/spec update.
4. Treat code-to-spec extraction as reference-only until accepted by the canonical spec owner.
5. Any supported AI tool may plan, implement, review, or verify with synced context; using multiple tools is optional.
6. Update .claude source first, then sync generated mirrors; do not manually edit .agents, .codex, or AGENTS.md. — why: mirrors are generated artifacts; hand-edits are overwritten on the next sync
7. If docs/project-config.json, root instruction files, or a required project-reference doc is missing or stale, auto-run $project-init or the narrow lower-level route before ordinary project-specific work.

Active reference: shared/sdd-artifact-contract.md in the active skills root.

---

SYNC:ai-sdd-artifact-contract:reminder

• MANDATORY Apply shared/sdd-artifact-contract.md; keep reusable AI-SDD in .claude and local rules in project docs.
• MANDATORY Code-to-spec extraction is reference-only until canonical acceptance; any supported AI tool may execute with synced context.
• MANDATORY Update .claude source before syncing generated mirrors; do not manually edit .agents, .codex, or AGENTS.md.
• MANDATORY Missing or stale project config, root instruction files, or required reference docs route project-specific work through $project-init or the narrow setup route automatically. [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.

[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/$security-review/$lint catch this?" — Yes → improve review skill instead.
7. BOTH gates pass → ask user to run $learn. [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. Goal-driven execution: Define success criteria first, loop until verified, and stop only when observable checks pass. Tests verify intent: Tests must protect business rules/invariants and fail when the protected intent breaks, not only mirror current behavior.

Common AI Mistake Prevention (System Lessons)

• Re-read files after context compaction. Edit requires prior Read in same context; compaction wipes read state. Re-read before editing.
• Grep for old terms after bulk replacements. AI over-trusts find/replace completeness. Grep full repo after bulk edits for missed refs in docs/configs/catalogs.
• Check downstream references before deleting. Deletions cascade doc/code staleness. Map referencing files before removal.
• After memory loss, check existing state before creating new. Compaction wipes prior-work memory. Query current state to resume — never blindly duplicate.
• Verify AI-generated content against actual code. AI hallucinates APIs, class names, method signatures. Grep to confirm existence before documenting/referencing.
• Trace full dependency chain after edits. Changing a definition misses downstream consumers. Trace the full chain.
• When renaming, grep ALL consumer file types. Some file types silently ignore missing refs (no compile error). Search code, templates, configs, generated files.
• Trace ALL code paths when verifying correctness. Code existing ≠ code executing. Trace early exits, error branches, conditional skips — not just happy path.
• Update docs that embed canonical data when source changes. Docs inlining derived data (workflows, schemas, configs) go stale silently. Update all embedding docs alongside source.
• Verify sub-agent results after context recovery. Background agents may finish while parent compacted — grep-verify output, don't trust assumed completion.
• Cross-check full target list against sub-agent assignments. Parallel sub-agents by category miss boundary items. Reconcile union of assignments against target list before proceeding.
• Sub-agents inherit knowledge only from their agent .md definition — use custom agent types, not built-in Explore. Tool adoption = permission + knowledge + enforcement (numbered workflow step).
• Persist sub-agent findings incrementally, not as a final batch. Long sub-agents hit cutoffs before final write — findings lost. Instruct append-per-section to report file.
• When debugging, ask "whose responsibility?" before fixing. Trace caller (wrong data) vs callee (wrong handling). Fix at responsible layer — never patch symptom site.
• Grep ALL removed names after extraction/refactoring. Primary file "done" ≠ secondary files clean. Grep entire scope for every removed symbol before declaring complete.
• Assume existing values are intentional — ask WHY before changing. Pattern-matching as "wrong" skips context. Before changing any constant/limit/flag: read comments, git blame, surrounding code.