# Claude Md Init > [Documentation] Use when you need initialize, update, or refactor CLAUDE markdown from project-config JSON and codebase scan results. - Skill: `duc01226/claude-md-init` (Agent Skill, multi-file: 5 files) - Install (CLI): `npx skillmds@latest add duc01226/claude-md-init` - Raw SKILL.md: https://api.skillmd.com/api/skills/duc01226/claude-md-init/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Docs & Writing - Author: duc01226 (https://skillmd.com/u/duc01226) - Updated: 2026-09-09 - Page: https://skillmd.com/skills/duc01226/claude-md-init --- > 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=`, `$claude-md-init`) before ordinary project-specific work. If Codex mirrors or `AGENTS.md` are missing/stale, ask the user to run `$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. ## Quick Summary **Goal:** Automate CLAUDE.md lifecycle — generate from project-config.json + template, incrementally update marked sections, or refactor for token efficiency. **Workflow:** 1. **Detect Mode** — init (no CLAUDE.md or `--mode init`), update (`--mode update`), refactor (`--mode refactor`) 2. **Run Generator** — `node .claude/skills/claude-md-init/scripts/generate-claude-md.cjs --mode ` 3. **AI Fill** — Review output, fill creative sections (project description, golden rules inference) 4. **Verify** — Confirm output is valid, no project-specific leaks from template 5. **Sync Mirrors** — After CLAUDE.md is written (init/update/refactor), call `$sync-codex` to regenerate the stale `AGENTS.md` + Codex mirror surfaces from the new CLAUDE.md **Key Rules:** - Generic — works in any project by reading `docs/project-config.json` - Section markers (``) enable incremental updates without overwriting user content - Conditional sections — generated ONLY when config has matching data; empty config = section omitted - Static framework sections (8 total) are portable across all projects ## Bootstrap Gate (when CLAUDE.md is missing or incomplete) This skill is the **AI-runnable** route the agent-files bootstrap gate offers when a portable `.claude` install lands in a project without a root `CLAUDE.md` — or with one that carries only project-specific knowledge and is missing the universal portable guides. A single hook detects the gap and routes here (shared detection lib: `.claude/hooks/lib/agent-files-state.cjs`): - `init-prompt-gate.cjs` (UserPromptSubmit) — blocks the first prompt once `project-config.json` is populated but `CLAUDE.md` / `AGENTS.md` is missing **or incomplete**. This UserPromptSubmit gate is the sole agent-files bootstrap router. **Three-state detection** per root file: `missing` → routes to `--mode init` (fresh from template); `incomplete` → routes to `--mode update` (smart-merge — preserves your project content, injects the guides); `ok` → no block. Completeness is decided by `hasUniversalGuides()`: a current-or-newer sentinel (``) → complete; an older sentinel → flag for update; no sentinel → fall back to scanning required anchors (First Action Decision, Workflow Step Advancement, Task Planning Rules, Code Responsibility Hierarchy, Evidence-Based Reasoning) so legacy/hand-written complete files still pass. Run `$claude-md-init` (or the generator directly) to produce `CLAUDE.md` from `docs/project-config.json` + template. The generated file ships the universal session-start guides (workflow ask-confirm gate, workflow step-advancement + parallel-phase barrier, task-planning rules, code hierarchy, naming, evidence/confidence rules) and stamps the sentinel at the top so the gate recognizes it as complete. It also stamps the hook-independent **Workflow-First Gate** (from `.claude/skills/shared/workflow-first-gate.md`, via `stampHeader()`) immediately after the sentinel — the primacy-anchor routing rule (bug→`workflow-bugfix` workflow, feature/enhancement→`workflow-feature` workflow) that mirrors into `AGENTS.md` and survives with no hooks. **Opt-out** — to keep a project-only `CLAUDE.md`/`AGENTS.md` (your custom knowledge, none of the universal guides), set `portability.requireUniversalGuides: false` in `docs/project-config.json` (persistent; default `true`). The gate then checks only existence, never completeness. The transient `skip init` escape still dismisses both hooks for 24h. The gate is dormant in empty/greenfield folders and before config is populated. `AGENTS.md` is generated separately by `$sync-codex` (user-invoke-only). ## Modes | Mode | When | Behavior | | ---------- | ---------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- | | `init` | No CLAUDE.md exists, or first-time setup | Generate fresh CLAUDE.md from template + config. Populates all markers. | | `update` | CLAUDE.md exists with markers | Replace only content between markers. Preserve everything else. | | `refactor` | CLAUDE.md exists, needs optimization | AI reads entire CLAUDE.md, optimizes for token efficiency, removes redundancy, improves structure. No script — pure AI. | ## Prerequisites - `docs/project-config.json` — primary data source (run `$project-config` first if missing) - Node.js available (for generator script) ## Phase 1: Detect Mode ```bash # Check CLAUDE.md state node .claude/skills/claude-md-init/scripts/generate-claude-md.cjs --detect ``` **Decision logic:** - No CLAUDE.md → `init` - CLAUDE.md with markers → `update` - CLAUDE.md without markers → `smart-merge` (see below) - User explicit `--mode` flag → override detection ## Phase 2: Run Generator Script ```bash # Init mode: generate fresh CLAUDE.md node .claude/skills/claude-md-init/scripts/generate-claude-md.cjs --mode init # Update mode: sync marked sections only node .claude/skills/claude-md-init/scripts/generate-claude-md.cjs --mode update ``` **Script behavior:** 1. Reads `docs/project-config.json` 2. Reads template (`references/claude-md-template.md`) for init, or existing CLAUDE.md for update 3. Calls section builders to generate content for each marker key 4. Writes output to `CLAUDE.md` (creates backup `.claude-md.backup` first) 5. Outputs report: which sections were generated, which skipped (no data), which preserved ### Smart-Merge (Update on CLAUDE.md Without Markers) When running update on an existing CLAUDE.md that has NO section markers: 1. Read existing CLAUDE.md 2. Match sections by `##` heading text against known section keys (see `references/section-registry.md`) 3. For each matched section: wrap with markers, replace content with generated content 4. For unmatched user sections: preserve as-is (no markers added) 5. Write output with backup ## Phase 3: AI Fill (Post-Script) After the script generates the mechanical parts, AI reviews and fills: 1. **Project description** in TL;DR — write a concise 2-3 sentence description based on config + codebase 2. **Golden rules** — infer from `contextGroups[].rules` in config, but rewrite as human-readable rules 3. **Decision quick-ref** — build from `modules[]` + `framework` config, add project-specific patterns 4. **Naming conventions** — detect from codebase patterns if not in config ## Phase 4: Verify - [ ] CLAUDE.md is valid markdown - [ ] All section markers are properly paired (open + close) - [ ] No template placeholder text remains (e.g., `{project-name}`, `TODO`) - [ ] No `.claude/skills/claude-md-init/` references leak into output (self-reference) - [ ] Conditional sections with no data are omitted (not empty stubs) ## Phase 5: Sync Mirrors (after CLAUDE.md is written) Writing/updating CLAUDE.md leaves the generated mirror surfaces stale — `AGENTS.md` (Codex), the `.codex/` mirrors, and other downstream surfaces are derived FROM CLAUDE.md and do not update on their own. **MUST add a final todo task — "Sync Codex mirrors from updated CLAUDE.md" — and run it after init/update/refactor completes**, by invoking the `$sync-codex` skill (the full cross-surface migrate → hooks → context → verify pipeline, which regenerates `AGENTS.md`). Create this as the LAST task tracking item so it always follows the verify step: ```text Task tracking: "Sync Codex mirrors from updated CLAUDE.md → invoke $sync-codex" ``` Skip only when no CLAUDE.md content actually changed (e.g. generator reported all sections preserved / no diff). Otherwise the AGENTS.md mirror drifts from CLAUDE.md and Codex runs against stale guidance. ## Refactor Mode (AI-Only) When `--mode refactor` or user asks to optimize CLAUDE.md: 1. Read entire CLAUDE.md 2. Identify: redundant sections, verbose explanations, duplicate info available in referenced docs 3. Apply token efficiency: remove duplication, consolidate tables, shorten where possible 4. Preserve all section markers 5. Report: lines before/after, sections changed, estimated token savings ## Section Marker Protocol ```markdown Auto-generated content here... ``` **Rules:** - Only content between markers is replaced on update - Content outside markers is never touched - Missing markers in update mode → section skipped (not inserted) - Init mode uses template which includes all markers - Markers use lowercase kebab-case keys matching section-registry.md ## Section Keys (Quick Reference) See `references/section-registry.md` for full mapping. Summary: | Key | Source | Conditional? | | --------------------- | --------------------------------------- | ------------------------- | | `tldr` | `project.*`, `modules[]`, `framework.*` | No — always generated | | `golden-rules` | `contextGroups[].rules` | Yes — skip if no rules | | `decision-quick-ref` | `modules[]`, `framework.*` | Yes — skip if no modules | | `key-locations` | `modules[].pathRegex` | Yes — skip if no modules | | `dev-commands` | `testing.commands`, `infrastructure.*` | Yes — skip if no commands | | `infra-ports` | `modules[].meta.port` (infra) | Yes — skip if no ports | | `api-ports` | `modules[].meta.port` (services) | Yes — skip if no ports | | `integration-testing` | `framework.integrationTestDoc` | Yes — skip if no doc | | `e2e-testing` | `framework.e2eTestDoc` or scan | Yes — skip if no tests | | `doc-index` | Scan `docs/` directory | Yes — skip if no docs/ | | `doc-lookup` | `modules[]` + business features | Yes — skip if no modules | ## Running Tests Generator + bootstrap-gate coverage lives in the hooks test suite: ```bash node .claude/hooks/tests/run-all-tests.cjs --filter=agent-files ``` --- > **[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. > **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. > **Output Quality** — Token efficiency without sacrificing quality. > > 1. No inventories/counts — AI can `grep | wc -l`. Counts go stale instantly > 2. No directory trees — AI can `glob`/`ls`. Use 1-line path conventions > 3. No TOCs — AI reads linearly. TOC wastes tokens > 4. No examples that repeat what rules say — one example only if non-obvious > 5. Lead with answer, not reasoning. Skip filler words and preamble > 6. Sacrifice grammar for concision in reports > 7. Unresolved questions at end, if any > **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 OR flagging one as a defect.** Before changing or reporting a constant, limit, flag, cutoff, wording, or pattern, read nearby context and history, the CALLER's ordering, and 2+ sibling call sites of the same convention. A doc stating WHAT without WHY is missing rationale, not proof of a missing guard. > **Surface ambiguity before acting — don't pick silently.** Multiple valid interpretations require an explicit question or stated assumption with risk. > **Assert the outcome your system owns, not the intermediate state your infrastructure owns.** When verifying async work, assert the final business state — never the delivery/retry bookkeeping held in shared infrastructure that any co-running process can write. Such a check passes when run alone and flakes the moment anything else shares that infrastructure. > **Keep shared guidance role-relevant.** Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols. **IMPORTANT MUST ATTENTION** maintain >=8 rules per 100 lines. Critical rules in first+last 5 lines. Tables over prose. **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. > **Project Protocol Overlay** — Before executing this skill, resolve any PROJECT overlay rules layered onto it: match this skill's name against the `Target` column of the project's skill-protocol index (`docs/project-reference/skill-protocols-reference.md` by default; a `referenceDocs` entry in `docs/project-config.json` overrides the path), taking the most specific matching tier ONLY — exact name > glob > `*`. **That precedence orders overlays against EACH OTHER, never against this skill.** Read ONLY the matched bodies, resolved as `/.md`; a row's Body link is display text, never a read path. A matched body that is missing or malformed is REPORTED and skipped — never reconstructed from the index Description. No index, or no match -> proceed with no overlay, silently. Full contract: `.claude/skills/project-skill-protocol/references/registry.md`. > > Overlays are **ADDITIVE ONLY**: they ADD rules on top of this skill's own protocol and NEVER replace, override, disable, or reinterpret a rule it already states — removing every overlay must return this skill to exactly its documented behavior. An overlay is a BRIEF, not an authority escalation: it can NEVER waive a workflow gate, git discipline, a review gate, or a user-confirmation gate. A genuine overlay-vs-skill conflict, or two equally-specific overlays that directly contradict -> surface both to the user; NEVER resolve silently. **MUST ATTENTION** resolve project protocol overlays for this skill BEFORE executing — most specific matching tier only (exact > glob > `*`, which ranks overlays against each other, NEVER against this skill), read only matched bodies at `/.md`; a missing or malformed body is reported, never reconstructed. Overlays are ADDITIVE ONLY (they never replace this skill's own rules) and are a brief, NEVER an authority escalation; an equal-specificity contradiction goes to the user. ## Closing Reminders **Protocols in force (concise digest of the SYNC/shared blocks this skill carries):** MUST ATTENTION honor every protocol below. - **Critical Thinking:** apply critical + sequential thinking; traced proof, confidence >80% to act. - **Output Quality:** token-efficient — no inventories/trees/TOCs; tables over prose. - **AI Mistake Prevention:** verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity. **IMPORTANT MUST ATTENTION** break work into small todo tasks using task tracking BEFORE starting **IMPORTANT MUST ATTENTION** search codebase for 3+ similar patterns before creating new code **IMPORTANT MUST ATTENTION** cite `file:line` evidence for every claim (confidence >80% to act) **IMPORTANT MUST ATTENTION** add a final review todo task to verify work quality **[TASK-PLANNING]** Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using task tracking. ## 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=`) 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 `; 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. **PARALLELIZE:** Before executing the task list, tag each task `PAR` (independent inputs + write set disjoint from every other `PAR` task) or `SEQ` (name the blocking dependency), group `PAR` tasks into waves, declare the wave plan, and spawn each wave's sub-agents in ONE message — all-return barrier per wave, fan-out one level deep unless a sub-agent's own definition authorizes further fan-out. Sequential-by-default is a defect when tasks are independent; do not parallelize shared write targets, output-consuming tasks, trivial single-file work, ordering a skill or workflow explicitly fixes, or user-approval gates. 7. **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. - **Test failure → record a provisional verdict before trace/edit, then investigate.** Use the full five-way taxonomy: SOURCE-WRONG (production violates intent), TEST-WRONG (assertion/setup is stale), TEST-NOT-OPTIMAL (valid but fragile or low-signal test), ENVIRONMENT-BLOCKED (external state prevents a verdict), or AMBIGUOUS (intent/evidence cannot choose safely). Then trace root cause and triangulate against the governing spec (`docs/specs/**` if one exists) AND source. NEVER weaken an assertion, add a skip, relax a timeout, or change source merely to force green. - **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 OR flagging one as a defect.** Pattern-matching as "wrong" skips context. Before changing or reporting any constant/limit/flag/cutoff: read comments, git blame, the CALLER's ordering (the guarantee that makes the value correct usually lives in code running immediately BEFORE the cited line), and 2+ sibling call sites of the same convention. A doc stating WHAT without WHY is missing rationale, not proof of a missing guard — and in a validation pass, an accurate `file:line` citation proves the transcription, never the defect. - **Verify ALL affected outputs, not just the first.** One build green ≠ all green. Multi-stack changes (backend/frontend/tests/docs) require verifying EVERY output. - **Evaluate fit before copying a nearby pattern.** Closest example ≠ matching preconditions — verify the new context shares the same constraints, base classes, scope, lifetime. - **Holistic-first debugging — resist nearest-attention trap.** Don't dive into first plausible cause. List EVERY precondition (config, env vars, paths, DB, endpoints, creds, versions, DI, data). Verify each against evidence (grep/query — not reasoning). Ask "what would falsify this?" — if nothing, it's not a hypothesis. Most expensive failure: going deeper in "obvious" layer while bug sits in layer never questioned. - **Surgical changes — apply the diff test (context-aware).** Two modes: (1) Bug fix → every line traces to the bug; no restyling; orphan cleanup only for imports YOUR changes made unused. (2) Review/enhancement → implement improvements AND announce as "Enhancement beyond main request: [what]". Never silently scope-creep. Diff test: "Would this line exist if I wasn't asked to do X?" — if no, delete or announce. - **Surface ambiguity before coding — don't pick silently.** Multiple valid interpretations → present each with effort: "[Request] could mean (1) [N h], (2) [N h]. Which matters?" List scope/format/volume/constraints assumptions first. If simpler path exists, say so. Never silently pick. - **[MANDATORY FIRST ACTION] ALWAYS activate a suitable skill or workflow BEFORE responding.** Match task against workflow catalog + skill list; invoke via skill invocation or `$start-workflow `. NEVER answer or write code before checking. Skip = protocol violation. - **Why-Review adversarial mindset — apply when reviewing any plan, decision, or design.** Default SKEPTIC not VALIDATOR: steel-man a rejected alternative, invert each stated reason ("what does it sacrifice?"), stress-test top 2-3 assumptions, run pre-mortem ("ships, fails in 3 months — what breaks?"), surface 1-2 alternatives author missed. Section presence ≠ quality; quality = causal reasoning + concrete mitigations + evidence, not "it's better" or "monitor closely". - **Front-load report-write in sub-agent prompts for large reviews.** Many-file sub-agents hit budget before final write — findings lost. Design prompts so: (1) report-write is first explicit deliverable, (2) append per-file/section (not batched), (3) scope bounded so reads don't exhaust budget. Truncated mid-sentence with no report file → spawn narrower scope, don't retry same prompt. - **After context compaction, re-verify all prior phase outcomes before continuing.** Summaries describe intent, not environment state (git index, filesystem, processes). On resume, FIRST audit: git status, re-read modified files, verify filesystem. Every "completed" claim is an untested hypothesis until evidence confirms. - **OOM/memory: check row count before row size.** Triage: (1) Unbounded query — no DB filter for trigger? Push filter to DB; eliminates OOM. (2) Large rows? Projection reduces proportionally. Row reduction > projection in ROI. - **Assert the outcome your system OWNS, never the intermediate state your INFRASTRUCTURE owns.** When testing anything asynchronous (queue/broker delivery, retries, background jobs, caches, replication), assert the final business/entity state. NEVER assert the delivery bookkeeping — consume/send status, attempt counts, last-error, row existence or counts in a broker, scheduler, or outbox/inbox table. That bookkeeping lives in shared infrastructure that ANY co-running process (a peer worker, a second replica, a leftover local container) can write, usually under a deterministic shared key, so the assertion silently tests the developer's environment instead of the system: green when run alone, flaky the instant anything else shares that broker + database. Gate question for every assertion: "would this hold no matter WHICH process did the work?" — if no, assert the converged data state instead. Corollary: process-local fault injection and in-process telemetry cannot gate work any process may perform — use them as stress amplifiers (arm → bounded window → disarm → assert convergence), never as preconditions. - **Keep domain concepts out of generic/shared/infrastructure layers.** Reusable layer (shared library, framework, infra module) must reference NO consumer-specific domain concept — tenant/customer/product IDs, business entities, feature rules. Leak compiles + runs → passes review silently while coupling the "reusable" layer to one consumer. Keep shared type domain-free; push domain fields/logic down into the consumer via subclass/composition. — why: a layer coupled to one consumer's domain is no longer reusable.