# Sync Codex > [Codex] Use when you need to run the full Codex mirror sync + verify pipeline (migrate → hooks → context → verify) standalone, no npm/package JSON needed. - Skill: `duc01226/sync-codex` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add duc01226/sync-codex` - Raw SKILL.md: https://api.skillmd.com/api/skills/duc01226/sync-codex/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: DevOps & Infra - Author: duc01226 (https://skillmd.com/u/duc01226) - Updated: 2026-09-09 - Page: https://skillmd.com/skills/duc01226/sync-codex --- > 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:** Run the full Codex mirror pipeline standalone — equivalent to `npm run sync:all && npm run verify:all` (sync + verify) without `package.json` or `npm`. This runner is the **single source of truth** for the pipeline; the `package.json` `sync:all`/`verify:all` scripts delegate to it, so a project that only copied `.claude` (no root `package.json`) runs the identical pipeline. > **Renamed:** formerly `/codex-sync` — that name no longer resolves as a slash command; use `$sync-codex`. Also bootstraps team-wide Codex completion notifications by copying the portable `.claude/scripts/codex/codex-notify.mjs` helper into `.codex/scripts/codex/` and upserting notification plus TUI status-line keys into `.codex/config.toml`. **Workflow:** 1. **Run** — `node .claude/skills/sync-codex/scripts/run-codex-sync.mjs` 2. **Verify** — Exit code `0` = pass; check stdout summary 3. **Inspect** — On failure, re-run failing stage manually with `--only=` and `--verbose` **Key Rules:** - MUST run all 16 stages in order — orchestrator fails fast on first non-zero exit - NEVER edit `.agents/skills/sync-codex/**` (auto-mirror) — edit `.claude/skills/sync-codex/**` source instead - `.claude` is the source for skills/workflows/hooks; generated acceptance targets are `.agents/skills/**`, `.codex/CODEX_CONTEXT.md`, and `AGENTS.md` - Stages 1-3 mutate `.agents/skills/`, `.codex/`, `AGENTS.md`; stages 4-16 are read-only verifiers (codex tooling tests, repo-script unit tests, 3 hook-suite gates, the 7 codex verifiers, and the cross-surface divergence oracle) - Stage 1 upserts `[tui].status_line` to show model+reasoning, current directory, project root, context used, five-hour limit, and weekly limit by default - Stage 3 mirrors full `CLAUDE.md` into `AGENTS.md`, then appends the generated Codex hook/context mirror and shared AI-SDD markers so Codex has both source instructions and hookless parity context - Stage 1 must not inline `docs/project-reference/lessons.md` content into `.agents/skills/**`; generated skill mirrors reference the project-reference loading gate instead - The `SYNC:ai-sdd-artifact-contract` marker must appear after sync in `.codex/CODEX_CONTEXT.md` and `AGENTS.md` - No npm dependency — pure `node` + spawned subprocesses - Idempotent — safe to re-run; second run produces only timestamp diffs ## Bootstrap Gate (when AGENTS.md is missing or incomplete) This skill is the route the agent-files bootstrap gate offers for a missing — **or incomplete** — root `AGENTS.md`, the generated Codex mirror of `CLAUDE.md`. Because Codex has no hooks, the universal session-start guides must be embedded in `AGENTS.md` directly; stage 3 produces that mirror (full `CLAUDE.md` copy, so the `` sentinel propagates) + hookless-parity context. "Incomplete" means the file exists but lacks the universal guides — same three-state detection as the CLAUDE.md route (`missing` → init, `incomplete` → update smart-merge preserving project content, `ok` → no block), decided by the shared sentinel-then-anchors check. Detection is shared with the CLAUDE.md route via `.claude/hooks/lib/agent-files-state.cjs`. Opt out of completeness enforcement with `portability.requireUniversalGuides: false` in `docs/project-config.json` (default `true`); `skip init` dismisses both hooks for 24h. Generate `CLAUDE.md` first (via `$claude-md-init`) — stage 3 reads it as the mirror source. ## Stages 16 stages, sequential — the full `npm run sync:all && npm run verify:all` pipeline (the npm scripts delegate here). Stages 1-3 mutate; 4-16 verify (read-only): | # | Stage | Script | Effect | | --- | ------------------------ | -------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | 1 | migrate | `.claude/scripts/codex/migrate-claude-to-codex.mjs` | Migrate Claude agents → `.codex/agents/`; mirror skills → `.agents/skills/`; setup Codex notifications | | 2 | hooks | `.claude/scripts/codex/sync-hooks.mjs` | Generate `.codex/hooks.json` + sync report | | 3 | context | `.claude/scripts/codex/sync-context-workflows.mjs` | Regenerate `.codex/CODEX_CONTEXT.md` + `AGENTS.md` with workflow context and shared AI-SDD markers | | 4 | tests | `node --test .claude/scripts/codex/tests/*.test.mjs` | Run codex tooling unit tests | | 5 | scripts-tests | `node --test .claude/scripts/tests/*.test.mjs` | Run repo-script unit tests (statusline widgets, etc.) | | 6 | hooks-count-drift | `.claude/hooks/tests/run-all-tests.cjs --filter=count-drift` | Verify the `` inventory markers have not drifted from the real skill/hook/agent/workflow counts | | 7 | hooks-parity | `.claude/hooks/tests/run-all-tests.cjs --filter=parity` | Verify hook parity across the Claude/Codex/Copilot surfaces | | 8 | hooks-doc-sync | `.claude/hooks/tests/run-all-tests.cjs --filter=doc-sync-gate` | Verify hook documentation stays in sync with the wired hook set | | 9 | wf-cycle | `.claude/scripts/codex/verify-workflow-cycle-compliance.mjs` | Verify workflow sequence cycle compliance | | 10 | sk-proto | `.claude/scripts/codex/verify-skill-protocol-compliance.mjs` | Verify skill strict-execution-contract | | 11 | residue | `.claude/scripts/codex/verify-no-project-residue.mjs` | Verify no project residue in generated and generic source artifacts | | 12 | sdd | `.claude/scripts/codex/verify-sdd-semantic-compliance.mjs` | Verify AI-SDD semantic contract coverage | | 13 | review-validate-coverage | `.claude/scripts/codex/verify-review-validate-coverage.mjs` | Verify every review-family skill carries the `$why-review --validate-findings` route; graders never embed the fix-loop (Self-Review Convergence Loop sensor) | | 14 | sync-adoption-parity | `.claude/scripts/codex/verify-sync-adoption-parity.mjs` | Verify SYNC tag ↔ carrier adoption parity: declared carriers carry both main + `:reminder` blocks, no undeclared skill carries a matrix tag, every injected body byte-matches canonical | | 15 | provenance-markers | `.claude/scripts/codex/verify-provenance-markers.mjs` | Verify provenance-marker discipline in `architecture-knowledge.md`: declared tags only · `— VERIFY` only on a declared tag · §3/§8/§9/§10 each carry a default-basis banner · no banner enumerates row-level exceptions · a `[model-knowledge]` marker carries `— VERIFY`. Fail-soft when the catalog is absent | | 16 | sync-divergence | `.claude/scripts/codex/verify-sync-divergence.mjs` | Byte-equality oracle: `.agents/skills` mirror === `.claude/skills` (codex mirror) | ## Usage ```bash # Full sync (standalone, no npm): node .claude/skills/sync-codex/scripts/run-codex-sync.mjs # Stream live child output: node .claude/skills/sync-codex/scripts/run-codex-sync.mjs --verbose # Full sync while forcing skill copy mode: node .claude/skills/sync-codex/scripts/run-codex-sync.mjs --copy-skills # Read-only verifiers (no mutation) — the full `npm run verify:all`: node .claude/skills/sync-codex/scripts/run-codex-sync.mjs --only=tests,scripts-tests,hooks-count-drift,hooks-parity,hooks-doc-sync,wf-cycle,sk-proto,residue,sdd,review-validate-coverage,sync-adoption-parity,provenance-markers,sync-divergence # Skip stages while debugging: node .claude/skills/sync-codex/scripts/run-codex-sync.mjs --skip=migrate,hooks ``` **Exit codes:** `0` all pass · `1` orchestrator failure · non-zero propagates from failing stage. > **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. > **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** each canonical body below still binds: - **AI Mistake Prevention:** verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity. - **Critical Thinking:** traced `file:line` proof per claim, confidence >80% to act, never guess. **MUST ATTENTION** invoke ONLY when user explicitly requests codex sync — never auto-invoke, with ONE authorized exception: `$project-skill-protocol` runs this pipeline automatically after its three writes, because it is the sole writer of the `CLAUDE.md` `CK:PROJECT-PROTOCOLS` block and a stale `AGENTS.md` would defeat that block's only purpose (cross-host reach). No other skill, agent, or workflow may auto-run it **MUST ATTENTION** edit source `.claude/skills/sync-codex/**`, NEVER the `.agents/skills/sync-codex/**` mirror **MUST ATTENTION** keep `.codex/scripts/codex/codex-notify.mjs` generated from `.claude/scripts/codex/codex-notify.mjs`; edit the `.claude` source first **MUST ATTENTION** keep Codex config upserts surgical; preserve unrelated `.codex/config.toml` keys and tables while updating the managed notification/status-line keys **MUST ATTENTION** keep `AGENTS.md` sync comprehensive; mirror full `CLAUDE.md` plus generated hook/context blocks, and preserve unmanaged `AGENTS.md` preface text **MUST ATTENTION** keep learned-lessons content out of `.agents/skills/**`; skills may point to `docs/project-reference/lessons.md` but must not embed its entries **MUST ATTENTION** orchestrator fails fast — re-run single failing stage with `--only= --verbose` to debug **MUST ATTENTION** working directory auto-resolves to repo root from script path — do not pass `--cwd` **MUST ATTENTION** stages 1-3 mutate; stages 4-16 verify only — use `--only=` for non-destructive validation **Anti-Rationalization:** | Evasion | Rebuttal | | --------------------------------------- | ------------------------------------------------------------------------ | | "Just edit the .agents mirror directly" | Next sync overwrites it. Always edit `.claude/skills/sync-codex/` source | | "Skip a stage to save time" | Verifiers (4-16) catch drift; skipping = silent regression risk | | "Sync looks idempotent, skip verify" | Timestamp diffs are normal; structural diffs = bug. Always run verifiers | > **[FAILS FAST]** First non-zero stage exit aborts chain. Re-run failing stage manually to debug. > **[REPO ROOT]** Orchestrator auto-resolves repo root from its own path. NEVER pass `--cwd`. > **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. **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. ## 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.