Watzup

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: Hand the developer a complete, evidence-backed wrap-up — by reviewing current branch changes and summarizing impact/quality — with a change summary, doc/spec staleness flags, root-cause lessons, and a $understand review guide (diagrams, user stories, a review path, and how to test/demo it), WITHOUT mutating any file, so they decide the next step from full context.

Summary:

• READ-ONLY contract — review/summarize current-branch commits and FLAG findings only; NEVER edit, fix, implement, or update the docs/specs you flag — why: watzup is a handoff, not an edit pass.
• Main steps in order: (1) Review recent commits — what changed/added/removed; (2) Summarize impact + quality; (3) Doc-staleness gate — path→doc mapping table; (4) Spec-driven health check — feature-spec root → spec staleness → feature-docs freshness (ONLY when business code changed); (5) Root-cause lesson extraction — surface mistakes → name failure mode (not symptom) → universal rule → ask user; (6) $understand handoff — the full review guide, mandatory final; (7) ask the user directly Next Steps.
• Cost, declared: the $understand handoff produces a fuller artifact than it used to — it now derives diagrams, resolves real test-case IDs, and builds an ordered review route, so it reads more of the repo and writes a longer report. That is the deliberate price of a wrap-up that ends with a route into the work rather than a recap of it; it is stated here so it is chosen, not discovered.
• Three required gates after the change summary: doc-staleness check, spec-driven health check (business-code-only), root-cause lesson extraction — NEVER skip a gate because the change "looks small".
• Lessons go to $learn ONLY after user confirmation; surface-level "always check file X" notes are noise, not lessons.
• $understand is the mandatory final handoff and MUST run BEFORE the ask the user directly Next Steps prompt — if unavailable, STOP and report the blocker, NEVER skip — why: the developer's exit context is the explanation, not the raw diff.

Workflow:

1. Review — Analyze recent commits: what was modified, added, removed
2. Summarize — Provide detailed change summary with quality assessment
3. Doc Check — Cross-reference changed files against docs/ for staleness
4. Lesson Learned — Analyze AI mistakes/issues during the task and capture lessons
5. Understand Handoff — Invoke $understand as the final mandatory task so the developer gets the full review guide on the completed work, high level first then detail, in four parts: Orient → Route → Depth → Prove & Push Back. The section contract lives in understand/SKILL.md Step 4 and is never re-listed here — a copy of it in this file would go stale silently the next time it changes. Written to plans/reports/understand-*.md — or delivered in full in chat when no git-ignored directory is available for it — and summarized in chat

Key Rules:

• READ-ONLY: only flag findings, never implement or fix anything
• Doc staleness check is REQUIRED (see mapping table below)
• Lesson-learned analysis is REQUIRED (see section below)
• Final review task MUST ATTENTION include doc-staleness check, lesson-learned analysis, AND the final $understand handoff
• MUST ATTENTION call $understand after the watzup summary/doc/mistake analysis and before the final Next Steps prompt

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

Review my current branch and the most recent commits. Provide a detailed summary of all changes, including what was modified, added, or removed. Analyze the overall impact and quality of the changes.

IMPORTANT: Review and summarize only, never start implementing.

Doc Staleness Check (REQUIRED)

After change summary, run git diff --name-only (against base branch or recent commits), cross-reference changed files against relevant docs:

Output one of:

• A bulleted list of docs that may need updating, with a brief note on what is likely stale (e.g., "hook count changed from 31 to 32").
• No doc updates needed — if no changed file pattern maps to a doc.

Do not edit docs during watzup. Only flag. The user decides whether to fix.

Spec-Driven Development Health Check (REQUIRED when business code changed)

Run this check when git diff --name-only includes ANY changes under the backend service source paths or frontend app/domain source paths (resolve the concrete paths from the project's structure reference / docs/project-config.json).

Step 1 — Feature Spec Root Check

ls docs/specs/ 2>/dev/null

Note: Results are app-bucket names. To find a specific Feature Spec, probe ls docs/specs/{app-bucket}/ for canonical README.{Feature}.md files and derived bucket indexes/ERDs.

Step 2 — Spec Staleness Check (only if bundle exists)

For each spec file in docs/specs/:

git log --since="30 days ago" --name-only -- docs/specs/ | head -10

Step 3 — Feature Docs Freshness Check

git log --since="30 days ago" --name-only -- docs/specs/ | head -10

Output only flags that apply. Skip this section entirely if no business code changed.

AI Mistake & Lesson Learned Analysis (REQUIRED)

After doc staleness check, review entire session for AI mistakes and lessons learned.

Step 1 — Surface all mistakes

List every error made during session. For each, note:

• What happened (observable symptom — build fail, test fail, wrong output)
• Where it happened (file:line if applicable)

Common mistake categories:

• Assumed an API/type/enum value existed without reading the source
• Assumed infrastructure availability without checking requirements
• Conflated "code exists" with "code executes" — missed path tracing
• Used a pattern without verifying the new context has the same preconditions
• Reported "done" without verifying ALL affected outputs across all stacks
• Hallucinated method names, class names, or file paths

Step 2 — Extract root-cause lessons (NOT symptom fixes)

For each mistake, apply this 3-step extraction:

2a. Name the failure mode — NOT the symptom, the reasoning failure:

2b. Find the class — Where else could this SAME failure mode strike?

If failure mode applies in only one specific file or case → go up one abstraction level until it generalizes. Good lesson applies to ≥3 different contexts.

2c. Write as a universal rule — Strip ALL project-specific names:

• No file paths, class names specific to this codebase, or tool names
• Must read as useful advice on a completely different codebase in a different language
• If multiple mistakes share the same failure mode → consolidate into ONE lesson
• Test: "Would this prevent the same class of mistake in a Java, Go, or Python project?" If yes → good. If no → rewrite.

Step 3 — Ask user to persist

"Found [N] root-cause lesson(s). Should I use $learn to save them for future sessions?"

Wait for user confirmation before invoking $learn.

Output one of:

• A numbered list: failure mode → universal lesson → proposed $learn text
• No AI mistakes identified in this session — if genuinely none found

Be honest and self-critical. Surface-level symptom fixes ("always check file X") applying only to this codebase are NOT lessons — they are noise. Purpose: root-cause prevention compounding across sessions.

Next Steps

MANDATORY IMPORTANT MUST ATTENTION — NO EXCEPTIONS before presenting these options, invoke $understand as the final mandatory todo task using the watzup summary and current change set as scope. If $understand is unavailable, stop and report that blocker instead of silently skipping the handoff.

After $understand completes, MUST ATTENTION use ask the user directly to present these options. NEVER skip because task seems "simple" or "obvious" — the user decides:

• "$workflow-end (Recommended)" — Complete and close the active workflow
• "$commit" — Commit changes if not using workflow
• "Skip, continue manually" — user decides

[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.

External Memory: For complex or lengthy work (research, analysis, scan, review), write intermediate findings and final results to a report file in plans/reports/ — prevents context loss and serves as deliverable.

Evidence Gate: MANDATORY IMPORTANT MUST ATTENTION — every claim, finding, and recommendation requires file:line proof or traced evidence with confidence percentage (>80% to act, <80% must verify first).

Nested Task Expansion Contract — For workflow-step invocation, the [Workflow] ... row is only a parent container; the child skill still creates visible phase tasks.

1. Call the current task list first. If a matching active parent workflow row exists, set nested=true and record parentTaskId; otherwise run standalone.
2. Create one task per declared phase before phase work. When nested, prefix subjects [N.M] $skill-name — phase.
3. When nested, link the parent with TaskUpdate(parentTaskId, addBlockedBy: [childIds]).
4. Orchestrators must pre-expand a child skill's phase list and link the workflow row before invoking that child skill or sub-agent.
5. Mark exactly one child in_progress before work and completed immediately after evidence is written.
6. Complete the parent only after all child tasks are completed or explicitly cancelled with reason.

Blocked until: the current task list done, child phases created, parent linked when nested, first child marked in_progress.

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.

Task Tracking & External Report Persistence — Bootstrap this before execution; then run project-reference doc prefetch before target/source work.

1. Create a small task breakdown before target file reads, grep, edits, or analysis. On context loss, inspect the current task list first.
2. Mark one task in_progress before work and completed immediately after evidence; never batch transitions.
3. For plan/review work, create plans/reports/{skill}-{YYMMDD}-{HHmm}-{slug}.md before first finding.
4. Append findings after each file/section/decision and synthesize from the report file at the end.
5. Final output cites Full report: plans/reports/{filename}.

Blocked until: task breakdown exists, report path declared for plan/review work, first finding persisted before the next finding.

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.

Evidence-Based Reasoning — Speculation is FORBIDDEN. Every claim needs proof.

1. Cite file:line, grep results, or framework docs for EVERY claim
2. Declare confidence: >80% act freely, 60-80% verify first, <60% DO NOT recommend
3. Cross-service validation required for architectural changes
4. "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: [...]."

AI Mistake Prevention — Failure modes to avoid on every task:

Re-read files after context changes. Context compaction, resume, or long-running work can make memory stale; verify current files before acting. Verify generated content against source evidence. AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing. Check downstream references before deleting or renaming. Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first. Trace the full impact chain after edits. Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done. Verify ALL affected outputs, not just the first. One green check is not all green checks; validate every output surface the change can affect. Assume existing values are intentional — ask WHY before changing OR flagging one as a defect. Before changing or reporting a constant, limit, flag, cutoff, wording, or pattern, read nearby context and history, the CALLER's ordering, and 2+ sibling call sites of the same convention. A doc stating WHAT without WHY is missing rationale, not proof of a missing guard. Surface ambiguity before acting — don't pick silently. Multiple valid interpretations require an explicit question or stated assumption with risk. Assert the outcome your system owns, not the intermediate state your infrastructure owns. When verifying async work, assert the final business state — never the delivery/retry bookkeeping held in shared infrastructure that any co-running process can write. Such a check passes when run alone and flakes the moment anything else shares that infrastructure. Keep shared guidance role-relevant. Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.

IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act). NEVER speculate without proof.

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 Bootstrap task tracking before target work; transition one task at a time.
• MANDATORY Persist plan/review findings to plans/reports/ incrementally and synthesize from disk.

• 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.

• MANDATORY Parent workflow rows do not replace child phase tracking; expand phases and link the parent when nested.
• MANDATORY Orchestrators pre-expand child skill phases before invocation; use [N.M] $skill-name — phase prefixes and one-in_progress discipline.

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: Hand the developer a complete, evidence-backed wrap-up — change summary, doc/spec staleness flags, root-cause lessons, and a $understand review guide — WITHOUT mutating any file, so they decide the next step from full context.

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

• Nested Task Creation: Expand child phases, link parent, one task in_progress.
• Project Reference Docs Guide: Read required project-reference docs (always lessons.md) before work.
• Task Tracking External Report: Bootstrap task tracking; persist findings to plans/reports/ incrementally.
• Critical Thinking: Critical + sequential thinking; traced proof, no guess-as-fact.
• Evidence: Cite file:line for every claim; never speculate.
• AI Mistake Prevention: verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity.

IMPORTANT MUST ATTENTION stay READ-ONLY — only FLAG findings; NEVER edit, fix, implement, or update the docs/specs you flag — why: watzup is a review/handoff, not an edit pass; flagging-then-fixing silently breaks the read-only contract. IMPORTANT MUST ATTENTION run ALL three required gates after the change summary — doc-staleness (path→doc table), spec-driven health check (only when business code changed), root-cause lesson extraction — NEVER skip a gate because the change "looks small" — why: stale docs and missed lessons compound silently across sessions. IMPORTANT MUST ATTENTION invoke $understand as the FINAL mandatory handoff BEFORE the ask the user directly Next Steps prompt; if $understand is unavailable, STOP and report the blocker — NEVER silently skip the handoff — why: the developer's exit context is the explanation, not the raw diff.

IMPORTANT MUST ATTENTION extract lessons by ROOT CAUSE (the reasoning/assumption failure), NOT the symptom; write each as a universal rule that holds on ≥3 codebases; surface-level "always check file X" notes are noise — why: only root-cause prevention compounds across sessions. IMPORTANT MUST ATTENTION send lessons to $learn ONLY after explicit user confirmation — NEVER auto-persist or self-edit instruction files — why: lesson capture is a durable instruction change the user must own. IMPORTANT MUST ATTENTION use ask the user directly for the Next Steps decision — NEVER auto-decide the route even when it "seems obvious" — why: the user owns the workflow-end / commit / continue choice. IMPORTANT MUST ATTENTION break work into small todo tasks with task tracking BEFORE starting (one task per file read), keep exactly one in_progress, and add a final review todo to verify work quality — why: long files exhaust context; granular tasks survive compaction. IMPORTANT MUST ATTENTION cite file:line proof or traced evidence with a confidence % for every claim/finding (>80% to act, <80% verify first) — NEVER present a guess as fact — why: an unverified staleness/lesson flag misleads the developer's next decision. IMPORTANT MUST ATTENTION grep/glob to verify any referenced doc, path, or API actually exists before flagging it — NEVER hallucinate a doc mapping or count — why: AI invents file paths and method names; the change summary must match the real diff. IMPORTANT MUST ATTENTION read CLAUDE.md and the project-reference docs gate (lessons.md always) before the wrap-up — why: project conventions override generic staleness assumptions.

Anti-Rationalization:

IMPORTANT MUST ATTENTION Goal echo: evidence-backed READ-ONLY wrap-up — change summary + doc/spec staleness flags + root-cause lessons + mandatory $understand handoff, mutating NOTHING, so the user decides the next step.

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

…(truncated)