Codex compatibility note:
- Invoke repository skills with
$skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.
- Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.
- User-question prompts mean to ask the user directly in Codex.
- Ignore Claude-specific mode-switch instructions when they appear.
- Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.
- Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required
spawn_agent subagent(s) for that task.
- Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.
- For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.
- If a required step/tool cannot run in this environment, stop and ask the user before adapting.
Codex Project-Reference Loading (No Hooks)
Codex uses static project-reference loading instead of runtime-injected project docs.
When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.
Always read:
docs/project-config.json (project-specific paths, commands, modules, and workflow/test settings)
docs/project-reference/docs-index-reference.md (routes to the full docs/project-reference/* catalog)
docs/project-reference/lessons.md (always-on guardrails and anti-patterns)
Missing/stale context route: If docs/project-config.json, the docs index, lessons.md, CLAUDE.md, AGENTS.md, or any task-required reference doc is missing or stale, auto-run $project-init or the narrow setup route ($project-config, $docs-init, $scan-all, $scan --target=<key>, $claude-md-init) before ordinary project-specific work. If Codex mirrors or AGENTS.md are missing/stale, ask the user to run $sync-codex; do not auto-run it.
Situation-based docs:
- Project structure/architecture/tech-stack/deployment/setup (any layer — backend, frontend, or infra):
project-structure-reference.md
- Backend/CQRS/API/domain/entity changes:
backend-patterns-reference.md, domain-entities-reference.md
- Frontend/UI/styling/design-system:
frontend-patterns-reference.md, scss-styling-guide.md, design-system/README.md
- Spec authoring,
docs/specs/ pathing, or TC format: feature-spec-reference.md, spec-system-reference.md, spec-principles.md
- Behavior/public-contract changes or spec-test-code sync:
workflow-spec-test-code-cycle-reference.md plus the spec docs above
- Derived spec indexes/ERDs/reimplementation guides:
spec-system-reference.md and source Feature Specs under docs/specs/
- Integration test implementation/review:
integration-test-reference.md
- E2E test implementation/review:
e2e-test-reference.md
- Code review/audit work:
code-review-rules.md plus domain docs above based on changed files
Do not read all docs blindly. Start from docs-index-reference.md, then open only relevant files for the task.
Quick Summary
Goal: Analyze all file changes between git branches, perform impact analysis, and update specification documents.
Workflow:
- Discovery — Run git diff/log, classify changes (Frontend/Backend, Feature/Bugfix)
- Knowledge Graph — Document each changed file with dependencies, impact level, service context
- Analysis — Code review (strengths, weaknesses, security), refactoring recommendations
- Approval Gate — Present findings for explicit approval before updating specs
- Spec Update — Update requirements, tests, architecture docs based on approved analysis
Key Rules:
- All analysis must be evidence-based from actual git diffs
- Proceed past the approval gate only after explicit user approval, never before
Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).
Branch Comparison & Specification Update
You are to operate as an expert full-stack principal developer, software architect, and technical analyst to analyze all file changes between branches, perform comprehensive impact analysis, and update specification documents using the configured repository stack.
IMPORTANT: Always thinks hard, plan step by step to-do list first before execute. Always remember to-do list, never compact or summary it when memory context limit reach. Always preserve and carry your to-do list through every operation.
PHASE 1: EXTERNAL MEMORY-DRIVEN BRANCH ANALYSIS
Build a structured knowledge model in .ai/workspace/analysis/[comparison-name].analysis.md.
PHASE 1A: INITIALIZATION AND DISCOVERY
- Initialize the analysis file with standard headings
GIT BRANCH ANALYSIS DISCOVERY
GIT_DIFF_COMPREHENSIVE_ANALYSIS: Start with systematic git change detection:
- Primary Change Detection Commands:
git diff --name-status [source-branch]..[target-branch]
git diff --stat [source-branch]..[target-branch]
git log --oneline [source-branch]..[target-branch]
Document results under ## Git Diff Analysis and ## Commit History.
- Change Impact & Scope Classification: Document under
## Change Classification and ## Change Scope Analysis:
- Types: Frontend, Backend, Config, DB
- Purpose: Feature, Bug Fix, Refactor
RELATED_FILES_COMPREHENSIVE_DISCOVERY: For each changed file, discover all related components:
- Importers
- Dependencies
- Test files
- API consumers
- UI components
Save ALL changed files AND related files to ## Comprehensive File List with:
filePath
changeType
relationshipType
impactLevel
serviceContext
INTELLIGENT_SCOPE_MANAGEMENT: If file list exceeds 75, prioritize by impactLevel (Critical > High > Medium > Low).
PHASE 1B: KNOWLEDGE GRAPH CONSTRUCTION
IMPORTANT: MUST ATTENTION DO WITH TODO LIST
For each file, document in ## Knowledge Graph:
- All standard fields from feature skill
- Focus on change-specific context
PHASE 1C: OVERALL ANALYSIS
Write comprehensive summary showing:
- Complete end-to-end workflows discovered
- Key architectural patterns and relationships
- Business logic workflows affected
- Integration points and dependencies
PHASE 2: COMPREHENSIVE ANALYSIS AND PLANNING
Generate detailed analysis under these headings:
1. Code Review Analysis
- Strengths
- Weaknesses
- Security concerns
- Performance implications
- Maintainability
2. Refactoring Recommendations
- Immediate improvements
- Structural changes
- Technical debt items
3. Specification Update Plan
- New Requirements Discovery
- Test Specification Updates
- Documentation Strategy
PHASE 3: APPROVAL GATE
CRITICAL: Present comprehensive analysis, code review, refactoring recommendations, and specification update plan for explicit approval. DO NOT proceed without it.
PHASE 4: SPECIFICATION UPDATE EXECUTION
Once approved, read existing specification document and update with:
- Requirements
- Test Specifications
- Architecture Documentation
- Code Review findings
SUCCESS VALIDATION
Verify updated specification accurately reflects all changes. Document under ## Specification Validation.
Branch Comparison Guidelines
- Evidence-Based Analysis: Start with
git diff and base all updates on concrete code changes
- Comprehensive Impact Assessment: Analyze direct and indirect effects, including cross-service impacts
- Enterprise Architecture Awareness: Respect the project's architectural patterns, CQRS, and Clean Architecture
- Quality-Focused Approach: Perform thorough code review and identify refactoring opportunities
- Specification Completeness: Ensure full traceability between code, requirements, and tests
Related
[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.
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.
Evidence-Based Reasoning — Speculation is FORBIDDEN. Every claim needs proof.
- Cite
file:line, grep results, or framework docs for EVERY claim
- Declare confidence: >80% act freely, 60-80% verify first, <60% DO NOT recommend
- Cross-service validation required for architectural changes
- "I don't have enough evidence" is valid and expected output
BLOCKED until: - [ ] Evidence file path (file:line) - [ ] Grep search performed - [ ] 3+ similar patterns found - [ ] Confidence level stated
Forbidden without proof: "obviously", "I think", "should be", "probably", "this is because"
If incomplete → output: "Insufficient evidence. Verified: [...]. Not verified: [...]."
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 IMPORTANT MUST ATTENTION cite
file:line evidence for every claim. Confidence >80% to act, <60% = do NOT recommend.
MUST ATTENTION apply critical + sequential thinking — every claim needs appropriate traced evidence (file:line for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.
MUST ATTENTION apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting.
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 <protocols-dir>/<Name>.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 <protocols-dir>/<Name>.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
IMPORTANT MUST ATTENTION — Protocols in force (concise digest of the SYNC/shared blocks this skill carries):
Evidence: cite file:line for every claim; confidence >80% to act, <60% don't recommend.
Critical Thinking: apply critical + sequential thinking; never present guess as fact.
AI Mistake Prevention: verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity.
MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using task tracking BEFORE starting
MANDATORY IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code
MANDATORY IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act)
MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify work quality
MANDATORY IMPORTANT MUST ATTENTION READ the following files before starting:
[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using task tracking.
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.
- 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.
- ANALYZE: Choose the best option: execute directly, invoke a skill, activate a standard workflow, or compose a custom step combination.
- AUTO-SELECT: Pick the best option yourself. Do not ask the user to choose between direct execution, skill, standard workflow, or custom workflow.
- 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.
- CREATE TASKS: task tracking for ALL workflow/skill/custom steps before execution when the selected path has multiple steps.
- 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.
- 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.
- Keep reusable AI-SDD principles in
.claude; put repository-specific paths, commands, owners, products, and formats in project config/reference docs.
- Preserve cycle:
spec -> plan -> tasks -> implement -> verify -> update spec/docs.
- Trace every requirement or invariant through decision, task, TC/test, source evidence, and docs/spec update.
- Treat code-to-spec extraction as reference-only until accepted by the canonical spec owner.
- Any supported AI tool may plan, implement, review, or verify with synced context; using multiple tools is optional.
- 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
- 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:
- Name the FAILURE MODE (reasoning/assumption failure), not symptom — "assumed API existed without reading source" not "used wrong enum value".
- Generality test: does this failure mode apply to ≥3 contexts/codebases? If not, abstract one level up.
- Write as a universal rule — strip project-specific names/paths/classes. Useful on any codebase.
- Consolidate: multiple mistakes sharing one failure mode → ONE lesson.
- Recurrence gate: "Would this recur in future session WITHOUT this reminder?" — No → skip
$learn.
- Auto-fix gate: "Could
$code-review/$code-simplifier/$security-review/$lint catch this?" — Yes → improve review skill instead.
- 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 <workflowId>. 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.
1---
2name: branch-comparison
3description: '[Git] Use when the user asks to compare branches, analyze git diffs, review changes between branches, update specifications based on code changes, or analyze what changed.'
4metadata:
5 source: https://skillmd.com/skills/duc01226/branch-comparison
6---
7
8> Codex compatibility note:
9>
10> - Invoke repository skills with `$skill-name` in Codex; this mirrored copy rewrites legacy Claude `/skill-name` references.
11> - Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.
12> - User-question prompts mean to ask the user directly in Codex.
13> - Ignore Claude-specific mode-switch instructions when they appear.
14> - Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.
15> - 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.
16> - Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.
17> - For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.
18> - If a required step/tool cannot run in this environment, stop and ask the user before adapting.
19
20<!-- CODEX:PROJECT-REFERENCE-LOADING:START -->
21
22## Codex Project-Reference Loading (No Hooks)
23
24Codex uses static project-reference loading instead of runtime-injected project docs.
25When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.
26
27**Always read:**
28
29- `docs/project-config.json` (project-specific paths, commands, modules, and workflow/test settings)
30- `docs/project-reference/docs-index-reference.md` (routes to the full `docs/project-reference/*` catalog)
31- `docs/project-reference/lessons.md` (always-on guardrails and anti-patterns)
32
33**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.
34
35**Situation-based docs:**
36
37- Project structure/architecture/tech-stack/deployment/setup (any layer — backend, frontend, or infra): `project-structure-reference.md`
38- Backend/CQRS/API/domain/entity changes: `backend-patterns-reference.md`, `domain-entities-reference.md`
39- Frontend/UI/styling/design-system: `frontend-patterns-reference.md`, `scss-styling-guide.md`, `design-system/README.md`
40- Spec authoring, `docs/specs/` pathing, or TC format: `feature-spec-reference.md`, `spec-system-reference.md`, `spec-principles.md`
41- Behavior/public-contract changes or spec-test-code sync: `workflow-spec-test-code-cycle-reference.md` plus the spec docs above
42- Derived spec indexes/ERDs/reimplementation guides: `spec-system-reference.md` and source Feature Specs under `docs/specs/`
43- Integration test implementation/review: `integration-test-reference.md`
44- E2E test implementation/review: `e2e-test-reference.md`
45- Code review/audit work: `code-review-rules.md` plus domain docs above based on changed files
46
47Do not read all docs blindly. Start from `docs-index-reference.md`, then open only relevant files for the task.
48
49<!-- CODEX:PROJECT-REFERENCE-LOADING:END -->
50
51## Quick Summary
52
53**Goal:** Analyze all file changes between git branches, perform impact analysis, and update specification documents.
54
55**Workflow:**
56
571. **Discovery** — Run git diff/log, classify changes (Frontend/Backend, Feature/Bugfix)
582. **Knowledge Graph** — Document each changed file with dependencies, impact level, service context
593. **Analysis** — Code review (strengths, weaknesses, security), refactoring recommendations
604. **Approval Gate** — Present findings for explicit approval before updating specs
615. **Spec Update** — Update requirements, tests, architecture docs based on approved analysis
62
63**Key Rules:**
64
65- All analysis must be evidence-based from actual git diffs
66- Proceed past the approval gate only after explicit user approval, never before
67
68**Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).**
69
70# Branch Comparison & Specification Update
71
72You are to operate as an expert full-stack principal developer, software architect, and technical analyst to analyze all file changes between branches, perform comprehensive impact analysis, and update specification documents using the configured repository stack.
73
74**IMPORTANT**: Always thinks hard, plan step by step to-do list first before execute. Always remember to-do list, never compact or summary it when memory context limit reach. Always preserve and carry your to-do list through every operation.
75
76---
77
78## PHASE 1: EXTERNAL MEMORY-DRIVEN BRANCH ANALYSIS
79
80Build a structured knowledge model in `.ai/workspace/analysis/[comparison-name].analysis.md`.
81
82### PHASE 1A: INITIALIZATION AND DISCOVERY
83
841. **Initialize** the analysis file with standard headings
85
86### GIT BRANCH ANALYSIS DISCOVERY
87
88**GIT_DIFF_COMPREHENSIVE_ANALYSIS**: Start with systematic git change detection:
89
901. **Primary Change Detection Commands**:
91
92```bash
93git diff --name-status [source-branch]..[target-branch]
94git diff --stat [source-branch]..[target-branch]
95git log --oneline [source-branch]..[target-branch]
96```
97
98Document results under `## Git Diff Analysis` and `## Commit History`.
99
1002. **Change Impact & Scope Classification**: Document under `## Change Classification` and `## Change Scope Analysis`:
101 - Types: Frontend, Backend, Config, DB
102 - Purpose: Feature, Bug Fix, Refactor
103
104**RELATED_FILES_COMPREHENSIVE_DISCOVERY**: For each changed file, discover all related components:
105
106- Importers
107- Dependencies
108- Test files
109- API consumers
110- UI components
111
112Save ALL changed files AND related files to `## Comprehensive File List` with:
113
114- `filePath`
115- `changeType`
116- `relationshipType`
117- `impactLevel`
118- `serviceContext`
119
120**INTELLIGENT_SCOPE_MANAGEMENT**: If file list exceeds 75, prioritize by impactLevel (Critical > High > Medium > Low).
121
122### PHASE 1B: KNOWLEDGE GRAPH CONSTRUCTION
123
124**IMPORTANT: MUST ATTENTION DO WITH TODO LIST**
125
126For each file, document in `## Knowledge Graph`:
127
128- All standard fields from feature skill
129- Focus on change-specific context
130
131### PHASE 1C: OVERALL ANALYSIS
132
133Write comprehensive summary showing:
134
135- Complete end-to-end workflows discovered
136- Key architectural patterns and relationships
137- Business logic workflows affected
138- Integration points and dependencies
139
140---
141
142## PHASE 2: COMPREHENSIVE ANALYSIS AND PLANNING
143
144Generate detailed analysis under these headings:
145
146### 1. Code Review Analysis
147
148- Strengths
149- Weaknesses
150- Security concerns
151- Performance implications
152- Maintainability
153
154### 2. Refactoring Recommendations
155
156- Immediate improvements
157- Structural changes
158- Technical debt items
159
160### 3. Specification Update Plan
161
162- New Requirements Discovery
163- Test Specification Updates
164- Documentation Strategy
165
166---
167
168## PHASE 3: APPROVAL GATE
169
170**CRITICAL**: Present comprehensive analysis, code review, refactoring recommendations, and specification update plan for explicit approval. **DO NOT** proceed without it.
171
172---
173
174## PHASE 4: SPECIFICATION UPDATE EXECUTION
175
176Once approved, read existing specification document and update with:
177
178- Requirements
179- Test Specifications
180- Architecture Documentation
181- Code Review findings
182
183---
184
185## SUCCESS VALIDATION
186
187Verify updated specification accurately reflects all changes. Document under `## Specification Validation`.
188
189---
190
191## Branch Comparison Guidelines
192
193- **Evidence-Based Analysis**: Start with `git diff` and base all updates on concrete code changes
194- **Comprehensive Impact Assessment**: Analyze direct and indirect effects, including cross-service impacts
195- **Enterprise Architecture Awareness**: Respect the project's architectural patterns, CQRS, and Clean Architecture
196- **Quality-Focused Approach**: Perform thorough code review and identify refactoring opportunities
197- **Specification Completeness**: Ensure full traceability between code, requirements, and tests
198
199## Related
200
201- `commit`
202- `code-review`
203
204---
205
206> **[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.
207
208<!-- SYNC:ai-mistake-prevention -->
209
210> **AI Mistake Prevention** — Failure modes to avoid on every task:
211>
212> **Re-read files after context changes.** Context compaction, resume, or long-running work can make memory stale; verify current files before acting.
213> **Verify generated content against source evidence.** AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing.
214> **Check downstream references before deleting or renaming.** Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first.
215> **Trace the full impact chain after edits.** Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done.
216> **Verify ALL affected outputs, not just the first.** One green check is not all green checks; validate every output surface the change can affect.
217> **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.
218> **Surface ambiguity before acting — don't pick silently.** Multiple valid interpretations require an explicit question or stated assumption with risk.
219> **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.
220> **Keep shared guidance role-relevant.** Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.
221
222<!-- /SYNC:ai-mistake-prevention -->
223
224<!-- SYNC:evidence-based-reasoning -->
225
226> **Evidence-Based Reasoning** — Speculation is FORBIDDEN. Every claim needs proof.
227>
228> 1. Cite `file:line`, grep results, or framework docs for EVERY claim
229> 2. Declare confidence: >80% act freely, 60-80% verify first, <60% DO NOT recommend
230> 3. Cross-service validation required for architectural changes
231> 4. "I don't have enough evidence" is valid and expected output
232>
233> **BLOCKED until:** `- [ ]` Evidence file path (`file:line`) `- [ ]` Grep search performed `- [ ]` 3+ similar patterns found `- [ ]` Confidence level stated
234>
235> **Forbidden without proof:** "obviously", "I think", "should be", "probably", "this is because"
236> **If incomplete →** output: `"Insufficient evidence. Verified: [...]. Not verified: [...]."`
237
238<!-- /SYNC:evidence-based-reasoning -->
239
240<!-- SYNC:critical-thinking-mindset -->
241
242> **Critical Thinking Mindset** — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act.
243> **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.
244
245<!-- /SYNC:critical-thinking-mindset -->
246
247<!-- SYNC:evidence-based-reasoning:reminder -->
248
249- **MANDATORY IMPORTANT MUST ATTENTION** cite `file:line` evidence for every claim. Confidence >80% to act, <60% = do NOT recommend.
250 <!-- /SYNC:evidence-based-reasoning:reminder -->
251
252<!-- SYNC:critical-thinking-mindset:reminder -->
253
254**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.
255
256<!-- /SYNC:critical-thinking-mindset:reminder -->
257
258<!-- SYNC:ai-mistake-prevention:reminder -->
259
260**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.
261
262<!-- /SYNC:ai-mistake-prevention:reminder -->
263
264<!-- SYNC:project-protocol-overlay -->
265
266> **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 `<protocols-dir>/<Name>.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`.
267>
268> 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.
269
270<!-- /SYNC:project-protocol-overlay -->
271
272<!-- SYNC:project-protocol-overlay:reminder -->
273
274**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 `<protocols-dir>/<Name>.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.
275
276<!-- /SYNC:project-protocol-overlay:reminder -->
277
278## Closing Reminders
279
280**IMPORTANT MUST ATTENTION — Protocols in force (concise digest of the SYNC/shared blocks this skill carries):**
281
282- **Evidence:** cite `file:line` for every claim; confidence >80% to act, <60% don't recommend.
283- **Critical Thinking:** apply critical + sequential thinking; never present guess as fact.
284- **AI Mistake Prevention:** verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity.
285
286- **MANDATORY IMPORTANT MUST ATTENTION** break work into small todo tasks using task tracking BEFORE starting
287- **MANDATORY IMPORTANT MUST ATTENTION** search codebase for 3+ similar patterns before creating new code
288- **MANDATORY IMPORTANT MUST ATTENTION** cite `file:line` evidence for every claim (confidence >80% to act)
289- **MANDATORY IMPORTANT MUST ATTENTION** add a final review todo task to verify work quality
290 **MANDATORY IMPORTANT MUST ATTENTION** READ the following files before starting:
291
292**[TASK-PLANNING]** Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using task tracking.
293
294<!-- CODEX:SYNC-PROMPT-PROTOCOLS:START -->
295
296## Hookless Prompt Protocol Mirror (Auto-Synced)
297
298Source: `.claude/.ck.json` + `.claude/skills/shared/sync-inline-versions.md` (`:full` blocks) + `.claude/scripts/lib/hookless-prompt-protocol.cjs`
299
300## [WORKFLOW-EXECUTION-PROTOCOL] [BLOCKING] Workflow Execution Protocol — MANDATORY IMPORTANT MUST CRITICAL. Do not skip for any reason.
301
302**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.
303
3041. **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.
3052. **ANALYZE:** Choose the best option: execute directly, invoke a skill, activate a standard workflow, or compose a custom step combination.
3063. **AUTO-SELECT:** Pick the best option yourself. Do not ask the user to choose between direct execution, skill, standard workflow, or custom workflow.
3074. **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.
3085. **CREATE TASKS:** task tracking for ALL workflow/skill/custom steps before execution when the selected path has multiple steps.
3096. **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.
3107. **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)
311
312## Shared AI-SDD Protocol Markers
313
314Source: `.claude/skills/shared/sync-inline-versions.md`
315
316## SYNC:ai-sdd-artifact-contract
317
318> **AI-SDD Artifact Contract** — Shared spec-driven development rules stay portable and source-owned.
319>
320> 1. Keep reusable AI-SDD principles in `.claude`; put repository-specific paths, commands, owners, products, and formats in project config/reference docs.
321> 2. Preserve cycle: `spec -> plan -> tasks -> implement -> verify -> update spec/docs`.
322> 3. Trace every requirement or invariant through decision, task, TC/test, source evidence, and docs/spec update.
323> 4. Treat code-to-spec extraction as reference-only until accepted by the canonical spec owner.
324> 5. Any supported AI tool may plan, implement, review, or verify with synced context; using multiple tools is optional.
325> 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
326> 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.
327>
328> **Active reference:** `shared/sdd-artifact-contract.md` in the active skills root.
329
330---
331
332## SYNC:ai-sdd-artifact-contract:reminder
333
334- **MANDATORY** Apply `shared/sdd-artifact-contract.md`; keep reusable AI-SDD in `.claude` and local rules in project docs.
335- **MANDATORY** Code-to-spec extraction is reference-only until canonical acceptance; any supported AI tool may execute with synced context.
336- **MANDATORY** Update `.claude` source before syncing generated mirrors; do not manually edit `.agents`, `.codex`, or `AGENTS.md`.
337- **MANDATORY** Missing or stale project config, root instruction files, or required reference docs route project-specific work through `$project-init` or the narrow setup route automatically.
338 **[TASK-PLANNING] [MANDATORY]** BEFORE executing any workflow or skill step, create/update task tracking for all planned steps, then keep it synchronized as each step starts/completes.
339
340## [LESSON-LEARNED-REMINDER] [BLOCKING] Task Planning & Continuous Improvement — MANDATORY. Do not skip.
341
342Break work into small tasks (task tracking) before starting. Add final task: "Analyze AI mistakes & lessons learned".
343
344**Extract lessons — ROOT CAUSE ONLY, not symptom fixes:**
345
3461. Name the FAILURE MODE (reasoning/assumption failure), not symptom — "assumed API existed without reading source" not "used wrong enum value".
3472. Generality test: does this failure mode apply to ≥3 contexts/codebases? If not, abstract one level up.
3483. Write as a universal rule — strip project-specific names/paths/classes. Useful on any codebase.
3494. Consolidate: multiple mistakes sharing one failure mode → ONE lesson.
3505. **Recurrence gate:** "Would this recur in future session WITHOUT this reminder?" — No → skip `$learn`.
3516. **Auto-fix gate:** "Could `$code-review`/`$code-simplifier`/`$security-review`/`$lint` catch this?" — Yes → improve review skill instead.
3527. BOTH gates pass → ask user to run `$learn`.
353 **[CRITICAL-THINKING-MINDSET]** Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act.
354 **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.
355 **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.
356 **Goal-driven execution:** Define success criteria first, loop until verified, and stop only when observable checks pass.
357 **Tests verify intent:** Tests must protect business rules/invariants and fail when the protected intent breaks, not only mirror current behavior.
358
359## Common AI Mistake Prevention (System Lessons)
360
361- **Re-read files after context compaction.** Edit requires prior Read in same context; compaction wipes read state. Re-read before editing.
362- **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.
363- **Check downstream references before deleting.** Deletions cascade doc/code staleness. Map referencing files before removal.
364- **After memory loss, check existing state before creating new.** Compaction wipes prior-work memory. Query current state to resume — never blindly duplicate.
365- **Verify AI-generated content against actual code.** AI hallucinates APIs, class names, method signatures. Grep to confirm existence before documenting/referencing.
366- **Trace full dependency chain after edits.** Changing a definition misses downstream consumers. Trace the full chain.
367- **When renaming, grep ALL consumer file types.** Some file types silently ignore missing refs (no compile error). Search code, templates, configs, generated files.
368- **Trace ALL code paths when verifying correctness.** Code existing ≠ code executing. Trace early exits, error branches, conditional skips — not just happy path.
369- **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.
370- **Verify sub-agent results after context recovery.** Background agents may finish while parent compacted — grep-verify output, don't trust assumed completion.
371- **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.
372- **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).
373- **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.
374- **When debugging, ask "whose responsibility?" before fixing.** Trace caller (wrong data) vs callee (wrong handling). Fix at responsible layer — never patch symptom site.
375- **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.
376- **Grep ALL removed names after extraction/refactoring.** Primary file "done" ≠ secondary files clean. Grep entire scope for every removed symbol before declaring complete.
377- **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.
378- **Verify ALL affected outputs, not just the first.** One build green ≠ all green. Multi-stack changes (backend/frontend/tests/docs) require verifying EVERY output.
379- **Evaluate fit before copying a nearby pattern.** Closest example ≠ matching preconditions — verify the new context shares the same constraints, base classes, scope, lifetime.
380- **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.
381- **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.
382- **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.
383- **[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 <workflowId>`. NEVER answer or write code before checking. Skip = protocol violation.
384- **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".
385- **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.
386- **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.
387- **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.
388- **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.
389- **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.
390
391<!-- CODEX:SYNC-PROMPT-PROTOCOLS:END -->