Workflow End

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.

[BLOCKING] Execute skill steps in declared order. NEVER skip, reorder, or merge steps without explicit user approval. [BLOCKING] Before each step or sub-skill call, update task tracking: set in_progress when step starts, set completed when step ends. [BLOCKING] Every completed/skipped step MUST include brief evidence or explicit skip reason. [BLOCKING] If Task tools are unavailable, create and maintain an equivalent step-by-step plan tracker with the same status transitions.

Quick Summary

Goal: [Process] Close the active workflow cleanly — clear workflow tracking so the next prompt gets fresh detection, and before clearing state print a one-way developer-comprehension recap (what / purpose / how / why) of what the workflow changed so the developer understands the work without re-reading the diff.

Summary:

• Purpose: penultimate state-closure step (runs before $watzup) — close the active workflow cleanly so the next prompt gets fresh detection, AND leave the developer understanding what changed without re-reading the diff.
• Main steps (ordered): (1) integration-test coverage check on changed business-logic files; (2) spec ↔ TDD-test sync gate (spec-tdd-test-sync-gate) BEFORE task-completion verification; (3) sync knowledge graph if .code-graph/ exists; (4) mark this task completed; (5) print the diff-gated one-way comprehension recap (what / purpose / how / why); (6) announce Workflow [name] completed; (7) confirm state cleared.
• Blocking gates: coverage gap (changed handler/command/service/controller with no matching test) OR unadjudicated spec-vs-code drift → MUST surface by asking the user directly, NEVER silent-skip; workflow MUST NOT report completed while drift is unadjudicated.
• Model-driven close: completes once ALL the current task list items done AND the sync gate recorded synced-or-accepted-as-is; NO hook clears state (residual .ck-workflow-state.json cleared only by session-init on explicit /clear).
• Recap depth throttled by codingLevel (CK_CODING_LEVEL → .claude/.ck.json → default 3); skip recap ONLY when there is no diff. The recap never quizzes and never blocks — deeper explanation is the standalone $understand skill.

Workflow:

1. Detect — classify request scope and target artifacts.
2. Execute — apply required steps with evidence-backed actions.
3. Explain — print the diff-gated comprehension recap (skip only when no changes).
4. Verify — confirm constraints, output quality, and completion evidence.

Key Rules:

• MUST ATTENTION when the workflow produced a diff, print the comprehension recap (what changed / purpose / how it works / why) — depth throttled by codingLevel, but NEVER fully skip when changes exist.
• MUST ATTENTION the recap is one-way — NO quiz, NO teach-back, NEVER blocks. Deeper comprehension is handled by the standalone $understand skill, which $watzup invokes as its final handoff and which the developer can also invoke directly for any target.
• MUST ATTENTION run the spec ↔ TDD-test sync gate (spec-tdd-test-sync-gate) BEFORE task-completion verification when behavior-changing files are in the diff — the workflow MUST NOT report completed while a behavior-vs-spec divergence is unadjudicated; surface unsynced drift by asking the user directly, never silent-close.
• MUST ATTENTION keep claims evidence-based (file:line) with confidence >80% to act.
• MUST ATTENTION keep task tracking updated as each step starts/completes.
• MUST ATTENTION define success criteria before execution and loop until observable verification passes.
• MUST ATTENTION when creating/reviewing specs or tests, name Business Intent / Invariant Guarded or the protected business intent/invariant and ensure the test would fail if that intent breaks.
• NEVER skip mandatory workflow or skill gates.

When This Runs

This skill is the workflow state-closure step. In workflows including $watzup, runs after final verification/docs work and before $watzup, so active workflow closes before post-workflow summary and $understand handoff. As penultimate action — after all workflow work done, before clearing state — prints one-way developer-comprehension recap of what workflow changed. Use $understand for deep standalone explainer of any target.

NOT for: Manual invocation mid-workflow (use workflow switching via $start-workflow instead).

What To Do

1. Integration test coverage check (skip if workflow is docs/design/investigation/e2e-only, or project has no test suite):

   git diff --name-only HEAD && git ls-files --others --exclude-standard
   

(The second command lists untracked files not yet staged — catches brand-new handler files before first git add) - Scan changed files for those likely requiring integration test coverage: business logic files such as handlers, commands, queries, services, controllers, resolvers, event processors. Naming varies by stack — infer from the project's existing file patterns (e.g., *Service.*, *Handler.*, *Controller.*, *Command.*, *Query.*). - For each identified file → search for a corresponding test file. Infer the project's test naming convention from existing tests (e.g., *.test.ts, *Tests.java, *_test.py, *.spec.js, *Tests.cs). Check standard test directories (tests/, spec/, __tests__/, or adjacent test projects). - If ANY identified file lacks a corresponding test → MANDATORY: use ask the user directly: - Option A: "Run $integration-test now" (Recommended) - Option B: "Tests already written/updated — proceed" - No silent skip. Business logic changes without test coverage MUST be surfaced to the user. - If no business logic files changed, or all have matching tests → skip silently

2. Spec ↔ TDD-test sync gate (spec-tdd-test-sync-gate — runs BEFORE task-completion verification; skip with reason only if the workflow is docs/design/investigation/e2e-only OR the diff has no behavior-changing files):

   The feedback half of the loop closes HERE — a workflow MUST NOT report completed while the spec still diverges from the code that just changed. Green tests do NOT normalize that drift.

   • Scope to the behavior-changing files in the diff (same surface the coverage check above scanned — handlers/commands/queries/services/controllers/entities/event processors and behavior-bearing frontend logic).
   • Run $spec [mode=sync] over the §8 TCs ↔ executing tests for those files: reconcile every §8 TC against its covering test, and surface any §8 TC with no covering test or any business TestSpec guarding behavior with no §8 TC.
   • Re-check for unadjudicated spec-vs-code drift: any behavior-changing file whose divergence from the canonical Feature Spec was never classified CODE-WRONG / SPEC-STALE / AMBIGUOUS / in-sync (per SYNC:spec-drift-adjudication).
   • If $spec [mode=sync] finds an unsynced §8 TC, OR any behavior-vs-spec divergence is unadjudicated → MANDATORY: surface by asking the user directly:
     • Option A: "Reconcile now — run $spec [mode=sync] / $spec [update] to close the drift" (Recommended)
     • Option B: "Accept as-is — I will record the reason" (the user's accept-as-is reason is captured in the recap)
   • No silent skip, no silent close. Workflow MUST NOT report completed while a behavior-vs-spec divergence is unadjudicated — record the gate outcome (synced / accepted-as-is-with-reason) before proceeding.

3. Sync knowledge graph (skip if .code-graph/ dir doesn't exist):

   if [ -d ".code-graph" ]; then python .claude/scripts/code_graph sync --json && python .claude/scripts/code_graph update --json; fi
   

   Report results briefly.

4. Mark this task as completed via TaskUpdate

5. Explain the changes — developer comprehension recap (the final teaching step; runs after everything else is done):

   Scope what this workflow changed:

   git diff --name-only HEAD && git ls-files --others --exclude-standard
   

   • No diff (pure investigation/research/docs-only workflow with nothing built) → skip with reason "no changes to explain".
   • Diff present → ALWAYS print a one-way teaching recap so the developer understands the work without re-reading the diff. This is one-way — NO quiz, NO teach-back, NEVER blocks. For a deeper explanation of any target (a plan, subsystem, decision, concept, or bug), use $understand; $watzup invokes it as the final handoff.

   Throttle depth by coding level (resolve first found: env CK_CODING_LEVEL → .claude/.ck.json codingLevel → default 3):

   Level	Recap depth
   4–5	2–4 tight sentences on the highest-blast-radius change only
   2–3	The four-part recap below, concise
   0–1	The four-part recap, fuller, plainest language, define non-obvious terms

   Always print at least the short recap when a diff exists — NEVER fully skip.

   Structure (optimize for easiest learning — lead with high-level motivation, then drill into low-level logic; surface what a reader would NOT guess from the diff):

   1. What changed — concrete edits grouped by behaviour (not by file); cite file:line.
   2. Purpose / kind — feature / bug fix / enhancement / refactor / perf / security — and the problem it solves.
   3. How it works — mechanism, key logic, invariants relied on, edge cases preserved; focus the non-obvious.
   4. Why this way — rationale and trade-offs; why over the obvious alternative.

6. Announce to the user: "Workflow [name] completed. Next prompt will trigger fresh workflow detection."

7. Workflow end is model-driven — it completes once this skill's the current task list items are all marked done, AND the spec ↔ TDD-test sync gate (step 2) recorded synced-or-accepted-as-is. No hook clears persisted state on completion; any residual .claude/.ck-workflow-state.json is cleared by session-init on an explicit /clear.

See Also

• Skill: $start-workflow - Start/switch workflows
• Doc: CLAUDE.md → Workflow Step Advancement - model-driven advancement rule (no step-tracking hook)
• Hook: session-init.cjs - clears any residual .ck-workflow-state.json on an explicit /clear

IMPORTANT MANDATORY Steps: integration-test-coverage-check -> spec-tdd-test-sync-gate -> verify-task-completion -> verify-workflow-state -> explain-changes-recap -> announce-workflow-completion -> clear-workflow-state

IMPORTANT MANDATORY Steps: integration-test-coverage-check -> spec-tdd-test-sync-gate -> verify-task-completion -> verify-workflow-state -> explain-changes-recap -> announce-workflow-completion -> clear-workflow-state

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

Workflow End

Finalize and close the active workflow, clearing state so the next user prompt triggers fresh workflow detection.

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.

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.

Project Reference Docs Gate — Run after task-tracking bootstrap and before target/source file reads, grep, edits, or analysis. Project docs override generic framework assumptions.

1. Identify scope: file types, domain area, and operation.
2. Read docs/project-config.json first — the project's machine-readable map. It is the single source of truth for THIS repo (modules/paths, framework + search keywords, test/E2E/integration run-commands, design system, architecture rules, workflow patterns); ground exact paths, run-commands, and conventions on it before investigating, planning, or coding — never assume framework defaults (CLAUDE.md + reference docs are derived from it). If it — or the docs index, lessons.md, CLAUDE.md, AGENTS.md, or any required reference doc — is missing or stale, auto-run $project-init or the narrow route ($project-config, $docs-init, $scan-all, $scan --target=<key>, $claude-md-init) first; if Codex mirrors or AGENTS.md are stale, ask the user to run $sync-codex (never auto-run it).
3. Required docs by trigger: always docs/project-reference/lessons.md; doc lookup docs-index-reference.md; review code-review-rules.md; backend/CQRS/API backend-patterns-reference.md; domain/entity domain-entities-reference.md; frontend/UI frontend-patterns-reference.md; styles/design scss-styling-guide.md + design-system/design-system-canonical.md; integration tests integration-test-reference.md; E2E e2e-test-reference.md; feature docs/specs feature-spec-reference.md + spec-system-reference.md + spec-principles.md; behavior/public-contract/spec-test-code sync workflow-spec-test-code-cycle-reference.md; derived spec index/ERD/reimplementation guides spec-system-reference.md + source Feature Specs under docs/specs/; architecture/new area project-structure-reference.md.
4. Read every required doc, then before target work state: Reference docs read: ... | Not applicable: ....

Ready when: scope evaluated, docs/project-config.json consulted, required docs checked/read or setup route completed, lessons.md confirmed, citation emitted.

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.

• MANDATORY Before investigating, planning, or coding, read docs/project-config.json (the project map: modules/paths, run-commands, conventions, architecture/workflow rules) + the required project-reference docs, and cite Reference docs read: ....
• MANDATORY Always include lessons.md; project config + conventions override generic framework defaults.
• MANDATORY If project config, root instruction files, or any required reference doc is missing or stale, auto-run $project-init or the narrow lower-level route before ordinary project-specific work.

Prompt-Enhance Closing Anchors

IMPORTANT MUST ATTENTION follow declared step order for this skill; NEVER skip, reorder, or merge steps without explicit user approval IMPORTANT MUST ATTENTION for every step/sub-skill call: set in_progress before execution, set completed after execution IMPORTANT MUST ATTENTION every skipped step MUST include explicit reason; every completed step MUST include concise evidence IMPORTANT MUST ATTENTION if Task tools unavailable, maintain an equivalent step-by-step plan tracker with synchronized statuses

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 Goal: Close the active workflow cleanly — clear workflow tracking so the next prompt gets fresh detection, AND before clearing state leave the developer understanding what the workflow changed via the diff-gated one-way comprehension recap.

Protocols in force (concise digest of the SYNC/shared blocks this skill carries):

• AI Mistake Prevention: verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity.
• Critical Thinking: MUST ATTENTION traced file:line proof per claim; confidence >80% to act; NEVER guess as fact.
• Project Reference Docs Guide: MUST ATTENTION read required project-reference docs (ALWAYS lessons.md) before target work.

IMPORTANT MUST ATTENTION Main steps (run in order, NEVER skip/merge): (1) integration-test coverage check → (2) spec ↔ TDD-test sync gate BEFORE task-completion verification → (3) sync knowledge graph if .code-graph/ exists → (4) mark this task completed → (5) diff-gated comprehension recap → (6) announce Workflow [name] completed → (7) confirm state cleared — why: AI keeps forgetting the skill's own steps; surfacing the ordered list prevents silent step-loss under long context. IMPORTANT MUST ATTENTION when the workflow changed code (diff present), print the comprehension recap — what changed / purpose / how it works / why — grouped by behaviour not file, optimized for easiest learning; depth throttled by codingLevel (CK_CODING_LEVEL → .claude/.ck.json → default 3), NEVER fully skip when changes exist — why: the developer must understand the work without re-reading the diff IMPORTANT MUST ATTENTION the spec ↔ TDD-test sync gate runs BEFORE task-completion verification — NEVER report the workflow completed while a behavior-vs-spec divergence is unadjudicated; reconcile via $spec [mode=sync] or capture an explicit accept-as-is reason — why: green tests do not normalize spec drift; the feedback half of the loop closes here IMPORTANT MUST ATTENTION run the integration-test coverage check on changed business-logic files (handlers/commands/queries/services/controllers/resolvers/event processors) — if ANY lacks a matching test, surface by asking the user directly; NEVER silent-skip — why: business-logic change without coverage ships an unguarded regression path IMPORTANT MUST ATTENTION the recap is one-way and NEVER blocks — no quiz, no teach-back; route deeper comprehension to the standalone $understand skill — why: blocking on a teaching step would stall workflow closure IMPORTANT MUST ATTENTION workflow end is model-driven — close ONLY once every the current task list item is done AND the sync gate recorded synced-or-accepted-as-is; NEVER wait for a hook to clear state — why: no hook clears .ck-workflow-state.json on completion (only session-init on explicit /clear) IMPORTANT MUST ATTENTION break work into small todo tasks with task tracking BEFORE starting; mark one in_progress, complete it immediately after its evidence lands; add a final review todo — why: untracked steps get silently skipped under long context IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code, and verify pattern FIT (same base class, scope, lifetime, preconditions) before copying the nearest example — why: closest example ≠ matching constraints IMPORTANT MUST ATTENTION cite file:line evidence for every claim — confidence >80% to act, <60% DO NOT recommend; NEVER present a guess as fact IMPORTANT MUST ATTENTION sync the knowledge graph ONLY if .code-graph/ exists, then announce Workflow [name] completed so the next prompt triggers fresh detection

Anti-Rationalization:

IMPORTANT MUST ATTENTION Goal echo: close the workflow cleanly — diff-gated recap delivered, sync gate adjudicated, state cleared for fresh detection. IMPORTANT MUST ATTENTION NEVER silent-skip the integration-test coverage gate or the spec↔TDD-test sync gate — surface gaps by asking the user directly. IMPORTANT MUST ATTENTION cite file:line evidence (confidence >80%); print the diff-gated recap; NEVER report completed with unadjudicated drift.

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

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

Hookless Prompt Protocol Mirror (Auto-Synced)

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

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

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

1. DETECT: If the prompt starts with an explicit slash skill/workflow command, execute it directly. Otherwise match the prompt against the workflow catalog and skill list.
2. ANALYZE: Choose the best option: execute directly, invoke a skill, activate a standard workflow, or compose a custom step combination.
3. AUTO-SELECT: Pick the best option yourself. Do not ask the user to choose between direct execution, skill, standard workflow, or custom workflow.
4. ACTIVATE: For a selected workflow, call $start-workflow <workflowId>; for a selected skill, invoke that skill; for a custom workflow, sequence custom steps directly; for direct execution, proceed with the task.
5. CREATE TASKS: task tracking for ALL workflow/skill/custom steps before execution when the selected path has multiple steps.
6. 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 st

…(truncated)