Codex compatibility note:
- Invoke repository skills with
$skill-namein Codex; this mirrored copy rewrites legacy Claude/skill-namereferences.- 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_agentsubagent(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 fulldocs/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.mdplus the spec docs above - Derived spec indexes/ERDs/reimplementation guides:
spec-system-reference.mdand source Feature Specs underdocs/specs/ - Integration test implementation/review:
integration-test-reference.md - E2E test implementation/review:
e2e-test-reference.md - Code review/audit work:
code-review-rules.mdplus 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.
[IMPORTANT] Create complete task plan before shell checks, scans, generators, edits, or skill calls. [IMPORTANT] After config exists, run
$scan-all+$workflow-code-to-specas post-config barrier; do not proceed until both return outcome/blocker/deferral. [IMPORTANT] After setup/review/verification is otherwise done, spawn background$graph-buildsub-agent and record outcome.
Quick Summary
Goal: Initialize or re-evaluate all portable project context files through one idempotent route, so any agent — with or without hooks — can discover missing context and reach a verified state with project config, reference docs, root instruction files, and Codex mirrors aligned.
Workflow:
- Plan Tasks - Before any setup action, create task-tracking entries for every project-init phase and every required final skill call.
- Assess - Classify folder state and current context-file health.
- Bootstrap - Create missing config/doc stubs when useful, then route scans/generators.
- Populate - After project config is initialized/refreshed, start the post-config parallel group: call
$scan-alland$workflow-code-to-spec. - Spec Finalization - Resolve the mandatory docs/specs gate from
$workflow-code-to-spec; only empty/no-content or no-accepted-capability projects may defer with evidence. - Review - Run
$changes-review, then$why-reviewas final quality gates after scan/spec completion. - Verify - Validate config, root files, docs, mirrors, spec workflow status, and staleness.
- Background Graph Refresh - After setup/review/verification is otherwise done, spawn a background sub-agent to run
$graph-build. - Report - List completed actions, skipped actions, and remaining manual steps.
Key Rules:
- MUST ATTENTION run this before ordinary work when required config/docs/root instruction files are missing.
- MUST ATTENTION preserve user-authored
CLAUDE.mdandAGENTS.md; use smart-merge/update paths, never blind overwrite. - MUST ATTENTION keep reusable skill text project-neutral; local rules belong in project config/reference docs.
- MUST ATTENTION use configured portability paths from
.claude/.ck.jsonwhen present. - MUST ATTENTION before any shell check, scan, generator, or file edit, create a complete task plan covering assessment, setup routes, final skill calls, verification, report, and lessons.
- MUST ATTENTION immediately after
$project-configinitializes or refreshes config, create and execute a post-config parallel task group withCall $scan-allandCall $workflow-code-to-spec. - MUST ATTENTION call
$scan-allafter config initialization for every content-bearing project; skip only empty/no-content projects with recorded evidence. - MUST ATTENTION invoke
$workflow-code-to-specfor every content-bearing project; it may run in parallel with$scan-allafter config exists, but do not treat "handoff suggested" as completion. - MUST ATTENTION end every setup run with final task-plan rows, in order:
Call $changes-review,Call $why-review,Spawn background $graph-build sub-agent, after the scan/spec parallel group is resolved. - MUST ATTENTION run
$graph-buildas a required final background sub-agent task after setup/review/verification work is otherwise done; do not run this final graph refresh inline in the main context. - MUST ATTENTION ask the user to run
$sync-codexor its standalone node runner when Codex mirrors/root files are missing or stale; do not auto-run this user-invoked-only sync route.
Scope
$project-init is the canonical coordinator for portable setup. It does not replace lower-level skills; it decides which one to run and when:
| Concern | Primary route |
|---|---|
| Project config | $project-config, then post-config parallel group: $scan-all + $workflow-code-to-spec |
| Project reference docs | $scan-all after config initialization; $docs-init or $scan --target=<key> only for stubs/focused repairs |
| Root Claude instructions | $claude-md-init |
Codex mirror, AGENTS.md, .agents, .codex |
Ask the user to run $sync-codex or its standalone node runner |
docs/specs Feature Specs + Section 8 TCs |
Mandatory $workflow-code-to-spec gate in the post-config parallel group; outcome must resolve before final review/report |
| Knowledge graph | Final background sub-agent running $graph-build after setup/review/verification is otherwise done |
Project-init test matrix — Defines setup states, routing expectations, and regression cases for post-config scan/spec and final graph behavior. MUST ATTENTION read
references/use-cases-and-test-cases.mdwhen creating plans, tests, or reviewing changes to this setup.
Phase -1: Required Task Plan
Before Phase 0 shell checks, create a full task-tracking plan. The plan MUST include many small, observable tasks and MUST NOT start execution until these rows exist.
Minimum required task rows:
- Read
project-initinstructions and setup reference files. - Assess folder classification, config, docs, root files, mirrors, graph, and spec inventory.
- Run required config setup route (
$project-config) or mark skipped with evidence. - Create a post-config parallel group with both
Call $scan-allandCall $workflow-code-to-specas sibling tasks. - Call
$scan-allafter config initialization or mark skipped only for empty/no-content evidence. - Call
$workflow-code-to-specafter config initialization and complete its Step 0 mode/scope route, or record the exact blocking user confirmation needed. - Wait at a barrier until both post-config parallel tasks are completed, blocked, or evidence-deferred.
- Run required root-instruction route (
$claude-md-init) or mark skipped with evidence. - Resolve Codex mirror route by asking for
$sync-codexwhen required. - Call
$changes-reviewafter the scan/spec barrier. - Call
$why-reviewafter$changes-review. - Run verification commands.
- Spawn a background sub-agent task named
Spawn background $graph-build sub-agentafter setup/review/verification is otherwise done. - Record the background
$graph-buildsub-agent outcome or explicit blocker. - Report files changed, routes invoked, scan/spec outcomes, review outcomes, background graph outcome, verification output, and remaining manual actions.
- Analyze AI mistakes and reusable lessons.
Keep exactly one row in_progress. Mark each row completed immediately after its evidence is recorded.
Phase 0: Assess State
Use shell checks, not memory. Record evidence for every state claim:
node -e "const h=require('./.claude/hooks/lib/session-init-helpers.cjs'); console.log(JSON.stringify({hasProjectContent:h.hasProjectContent(), isGreenfield:h.isGreenfieldProject()}, null, 2))"
node -e "const s=require('./.claude/hooks/lib/session-init-helpers.cjs'); console.log(JSON.stringify(s.checkProjectConfig(), null, 2))"
node -e "const a=require('./.claude/hooks/lib/agent-files-state.cjs'); console.log(JSON.stringify(a.getAgentFileIssues(), null, 2))"
Also check:
- Config path:
node -e "console.log(require('./.claude/hooks/lib/project-config-loader.cjs').getConfiguredProjectConfigPath())" - Docs index path:
node -e "console.log(require('./.claude/hooks/lib/project-config-loader.cjs').getConfiguredDocsIndexPath())" - Feature docs path:
node -e "console.log('docs/specs/')" - Placeholder docs: use
isPlaceholderFile()from.claude/hooks/lib/session-init-helpers.cjs. - Stale docs: use
getStaleReferenceDocs()from.claude/hooks/lib/session-init-helpers.cjs. - Reference-doc canonical-floor drift:
node -e "const h=require('./.claude/hooks/lib/session-init-helpers.cjs');const{loadProjectConfig}=require('./.claude/hooks/lib/project-config-loader.cjs');const r=h.normalizeReferenceDocs((loadProjectConfig()||{}).referenceDocs);console.log(JSON.stringify({changed:r.changed,renames:r.renames,added:r.added,removedLegacy:r.removedLegacy},null,2))".changed:true(non-emptyrenames/added/removedLegacy) means the config drifted below the canonical reference-doc floor (legacy filenames, missing canonical entries, or wrong order) and MUST be repaired in Phase 2 step 1a before the scan/spec barrier. - Spec inventory: probe the fixed feature docs path:
node -e "const p='docs/specs/'; const fs=require('fs'); console.log(JSON.stringify({path:p, exists:fs.existsSync(p)}, null, 2))"
Phase 1: Decide Route
| State | Action |
|---|---|
| Empty folder, no real project content | Do not deep-scan. Create minimal portable context stubs only when the user explicitly requested project initialization; otherwise report that there is no project content yet and continue with generic guidance. Create the post-config parallel tasks but mark $scan-all skipped and $workflow-code-to-spec deferred only with evidence: No project content or accepted capability scope; next trigger is $workflow-idea-to-spec or $greenfield, then $workflow-code-to-spec init-full. Still create final rows for $changes-review and $why-review; mark them skipped only with this evidence-backed deferral. |
| Greenfield project with manifests/code scaffold | Run $project-config, then start the post-config parallel group. $scan-all may be limited to relevant detected stack/docs. $workflow-code-to-spec runs when product/capability scope or real code exists; otherwise defer with exact missing scope. Still keep $changes-review and $why-review as final task rows. |
| Existing project, config missing or skeleton | Run $project-config first. Then immediately start the post-config parallel group ($scan-all + $workflow-code-to-spec) before nonessential setup work. |
| Config populated, reference docs missing/placeholders | Run $scan-all after config initialization. Use $docs-init or targeted $scan --target=<key> only as follow-up repair if $scan-all identifies missing/stub files. |
Config present but referenceDocs drifted (legacy filenames, missing canonical entries, or wrong order per the Phase 0 normalize probe) |
Run Reference-doc normalization (Phase 2 step 1a) BEFORE the scan/spec barrier: rewrite config.referenceDocs to normalizeReferenceDocs(...).normalized, git mv each renames[] legacy file to its canonical name (or git rm a stale duplicate), migrate downstream textual refs, then let the SessionStart hook / $scan --target=<key> create the added[] docs. Re-run the probe until changed:false. |
Config/docs populated, CLAUDE.md missing |
Run $claude-md-init --mode init after the scan/spec barrier is resolved or explicitly blocked/deferred. |
CLAUDE.md exists but lacks universal guides |
Run $claude-md-init --mode update if marker-managed. If markerless/project-only, manually merge the universal-guide blocks from claude-md-init/references/claude-md-template.md while preserving project content, then rerun update. |
AGENTS.md missing or incomplete |
Ask the user to run $sync-codex or node .claude/skills/sync-codex/scripts/run-codex-sync.mjs, then verify mirrors. |
Config/docs/root ready but docs/specs/ is missing or empty |
The post-config $workflow-code-to-spec task suggests init-full and completes Step 0 mode/bucket/capability confirmation before $project-init can report complete. |
| Config/docs/root ready and Feature Specs exist | The post-config $workflow-code-to-spec task suggests audit, unless an active diff/new requirement implies update. Then run $changes-review and $why-review. |
| Docs stale or graph missing | Run $scan-all in the post-config parallel group; queue the required final background $graph-build sub-agent task after setup/review/verification is otherwise done. Still resolve the mandatory spec workflow task before final verification. |
| Everything present | Run verification plus mandatory $workflow-code-to-spec audit/update decision; report idempotent status only after the spec workflow task is completed or explicitly deferred with evidence. |
Phase 2: Execute Order
Run phases sequentially except the explicit post-config parallel group. After each phase, re-run Phase 0 checks.
- Config -
$project-configwhen config is missing, skeleton, invalid, or stale relative to the workspace. 1a. Reference-doc normalization — canonical floor (MANDATORY when Phase 0 probe reportschanged:true) - repair reference-doc drift BEFORE the scan/spec barrier so every project converges to the framework floor regardless of starting state (no docs / partial / legacy names / wrong standard):- Rewrite
config.referenceDocstonormalizeReferenceDocs(config.referenceDocs).normalized(canonical order, legacy names resolved via the alias map, canonicaltemplatePaths preserved, genuine project-specific extras kept). Never delete or rename a canonical entry. - For each
renames[]{from,to}:git mv docs/project-reference/<from> docs/project-reference/<to>when<to>is absent; if<to>already exists,<from>is a stale duplicate → confirm<to>holds the canonical content, thengit rm docs/project-reference/<from>. Migrate every downstream textual reference (docs-index-reference.md,project-structure-reference.md)<from>→<to>, then ask the user to re-run$sync-codexso the regenerated mirrors match. added[]canonical docs missing on disk are created idempotently by the SessionStartsession-init-docs.cjshook (or$scan --target=<key>) fromDEFAULT_REFERENCE_DOCS+templatePath; do not hand-fabricate their content.- Re-run the Phase 0 normalize probe and proceed only when it reports
changed:falsewith emptyrenames/added/removedLegacy.
- Rewrite
- Post-config parallel context build (MANDATORY) - after config exists, create sibling tasks
Call $scan-allandCall $workflow-code-to-spec; run them in parallel when the environment/tooling supports parallel skill work, otherwise execute both before crossing the barrier.$scan-all: required for content-bearing projects after config initialization. Skip only empty/no-content projects with evidence. Use$docs-initor targeted$scan --target=<key>only as follow-up repair when scan output proves it is needed.$workflow-code-to-spec: required for content-bearing projects after config initialization. It may complete Step 0/mode selection in parallel with$scan-all; if it needs scan results for capability enumeration, pause inside that workflow until$scan-allevidence is available.- Barrier: do not proceed to root instruction updates, mirrors, final review, verification, or report until both sibling tasks have an outcome: completed, explicit blocker, or evidence-backed deferral.
- Root instructions -
$claude-md-init --mode init|update. - Codex mirror - ask the user to run
$sync-codexornode .claude/skills/sync-codex/scripts/run-codex-sync.mjs. - Spec workflow outcome (MANDATORY) - confirm the existing
Call $workflow-code-to-spectask has one of these outcomes before review:- Empty/no-content folder: do not deep-scan or fabricate capabilities; mark this task
Deferred: no project content or accepted capability scope, and report the next trigger ($workflow-idea-to-specor$greenfield, then$workflow-code-to-spec init-full). - Greenfield with accepted product/capability scope or real code scaffold: invoke
$workflow-code-to-spec, suggestinit-full, and let its Step 0 confirm mode/bucket/capability. - Existing/grown project with
docs/specs/missing or empty: invoke$workflow-code-to-spec, suggestinit-full, and require divide-and-conquer grouping when capability count is large. - Existing/grown project with Feature Specs already present: invoke
$workflow-code-to-spec, suggestaudit; suggestupdatewhengit diffor a new requirement/PBI is the trigger.
- Empty/no-content folder: do not deep-scan or fabricate capabilities; mark this task
- Review changes (MANDATORY) - create a final task named
Call $changes-review, invoke$changes-review, and record pass/fail or explicit blocker. - Why review (MANDATORY) - create a final task named
Call $why-review, invoke$why-reviewafter$changes-review, and record pass/fail or explicit blocker. - Enhance -
$prompt-enhanceon newly created or heavily updated skill/docs files. - Queue background graph refresh (MANDATORY FINAL) - create a final task named
Spawn background $graph-build sub-agent; do not execute it until Phase 4 verification and setup/review work are otherwise done.
Phase 2.5: Mandatory Spec Workflow Finalization
This phase starts as the Call $workflow-code-to-spec sibling task in the post-config parallel group. It is ALWAYS represented in task tracking and MUST be resolved before $changes-review, $why-review, final verification, and report.
| Scenario | Required final task outcome |
|---|---|
| Empty folder, no product/capability scope | Do not invoke heavy discovery. Mark final task deferred with evidence: No project content/capability source. Report exact next route: $workflow-idea-to-spec or $greenfield, then $workflow-code-to-spec init-full. |
| Greenfield with manifests but no accepted product scope | Ask for/route to product discovery or greenfield planning first; defer spec authoring until capability scope exists. Do not generate fake Feature Specs from package names alone. |
| Greenfield with accepted scope or code scaffold | Invoke $workflow-code-to-spec; recommend init-full for the selected bucket/capabilities; complete Step 0 or report the user confirmation blocker. |
Existing/grown project, no Feature Specs under docs/specs/ |
Invoke $workflow-code-to-spec; recommend init-full, require capability grouping (>10 split; 4-10 sub-agents) per that workflow; complete Step 0 or report the user confirmation blocker. |
| Existing/grown project with Feature Specs | Invoke $workflow-code-to-spec; recommend audit for freshness, or update when active code/requirement changes exist; complete Step 0 or report the user confirmation blocker. |
Do not mark $project-init complete while this phase is unresolved. A valid resolution is either: (1) $workflow-code-to-spec invoked and its Step 0/mode route completed, (2) $workflow-code-to-spec invoked and blocked on explicit user confirmation of mode/bucket/capability, or (3) explicit deferral with evidence that the project has no content/capability source yet. A plain recommendation or handoff without invoking $workflow-code-to-spec is NOT a valid resolution.
$scan-all and $workflow-code-to-spec are allowed to run in parallel only after project config exists. The project-init report must include both outcomes and must state whether $workflow-code-to-spec consumed scan evidence directly or paused pending scan output.
Phase 2.6: Mandatory Final Review Skills
After Phase 2.5, always create and execute these final tasks in order:
Call $changes-review- run after$workflow-code-to-specso the setup/spec changes are reviewed from the current diff.Call $why-review- run after$changes-reviewto validate rationale and avoid closing on unchallenged setup decisions.
If either skill cannot run because the environment lacks the required tool, stop and report the missing tool. Do not silently replace them with a summary.
Phase 3: Hookless Agent Rule
For Codex or any environment without Claude hooks:
- If
docs/project-config.json, the docs index,lessons.md,CLAUDE.md,AGENTS.md, or a task-required reference doc is missing or stale, invoke$project-initbefore ordinary task work. - If
$project-initcannot run because required tools are absent, report the missing tool and the exact lower-level route that remains. - Do not proceed with project-specific coding from guessed context.
Phase 4: Verification
Minimum verification before declaring setup complete:
node -e "const{validateConfig,formatResult}=require('./.claude/hooks/lib/project-config-schema.cjs');const{getConfiguredProjectConfigPath}=require('./.claude/hooks/lib/project-config-loader.cjs');const c=JSON.parse(require('fs').readFileSync(getConfiguredProjectConfigPath(),'utf-8'));console.log(formatResult(validateConfig(c)))"
node -e "const a=require('./.claude/hooks/lib/agent-files-state.cjs'); console.log(JSON.stringify(a.getAgentFileIssues(), null, 2))"
node .claude/hooks/tests/test-all-hooks.cjs
node .claude/skills/skill-creator/scripts/validate-skills.cjs --path .claude/skills/project-init
Spec workflow verification before declaring setup complete:
- Confirm the task list contains a post-config parallel group with
Call $scan-allandCall $workflow-code-to-spec. - Confirm
Call $scan-allran after$project-config, or was skipped only with empty/no-content evidence. - Confirm the task list contains
Call $changes-reviewandCall $why-reviewas the final review skill-call rows after the scan/spec barrier. - Confirm the
$workflow-code-to-specoutcome is one of:init-full,audit,update,blocked on user-confirmed mode/bucket/capability, or an evidence-backed deferral for empty/no-capability projects. - Confirm
$changes-reviewran after$workflow-code-to-spec, or stopped with an explicit missing-tool blocker. - Confirm
$why-reviewran after$changes-review, or stopped with an explicit missing-tool blocker. - Confirm
Spawn background $graph-build sub-agentran after setup/review/verification was otherwise done, or stopped with an explicit missing-tool/dependency blocker. - Confirm the Feature Spec root is the fixed path
docs/specs/. - Confirm the hook-independent Workflow-First Gate (
<!-- CK:WORKFLOW-GATE -->block) is present at the TOP ofCLAUDE.mdandAGENTS.mdso routing survives without hooks. If missing, re-run$claude-md-init(CLAUDE.md), then ask the user to run$sync-codex(AGENTS.md mirror). - For grown projects, confirm large scope is split per
$workflow-code-to-spec(>10capabilities grouped;4-10capabilities sub-agented).
If Codex mirrors were changed, run:
node .claude/skills/sync-codex/scripts/run-codex-sync.mjs --only=tests,wf-cycle,sk-proto,residue,sdd
Phase 5: Mandatory Final Background Graph Build
After Phase 4 verification and setup/review work are otherwise done, always execute this final task:
Spawn background $graph-build sub-agent- spawn a background sub-agent whose only job is to invoke$graph-buildwith default auto-detect scope, read its result, and return a concise outcome.
Rules:
- Run this final graph refresh in a sub-agent/background task, not inline in the main context.
- The task is required even if an earlier graph check found
.code-graph/graph.db; existing graph presence changes$graph-buildfrom full build to auto-detected update, not a skip. - Keep the task open until the background sub-agent returns, or record an explicit blocker such as missing Python/dependencies.
- The project-init report must include the background graph task outcome.
Output
Report:
- Folder classification: empty, greenfield, existing, or already initialized.
- Files created/updated/skipped: project config, reference docs,
CLAUDE.md,AGENTS.md, mirrors. - Lower-level skills/scripts invoked.
- Post-config parallel skill calls:
$scan-alland$workflow-code-to-spec, each with outcome and evidence. - Final review skill calls:
$changes-review,$why-review, each with outcome and evidence. - Final background graph call:
$graph-buildsub-agent outcome, scope/build type, and blocker if any. - Spec workflow finalization: invoked mode (
init-full,audit,update), user-confirmation blocker, or exact deferral reason and next trigger. - Verification commands and results.
- Remaining manual action, especially any user-confirmed
$sync-codexstep.
Parallel Sub-Agent Dispatch — Plan parallelism the moment a task breakdown exists, BEFORE executing it — running provably independent tasks sequentially wastes wall-clock. Applies to every multi-step job: workflow steps, planning, batch updates, investigation, research, scans, reviews, doc sync. Plan execution is metadata-gated, NEVER default-parallel — fan-out follows ONLY what the plan declares (
PAR/SEQtags + per-phase write set); an untagged plan runs sequentially — why: a derived write set cannot see cascade or generated writes.
- Tag every task
PARorSEQ.PAR= inputs exclude every pending task's output AND write set disjoint from every otherPAR. ElseSEQ— MUST ATTENTION name the dependency forcing it.- Group
PARinto waves. No edge between members. Two writers of one file NEVER share a wave. Read-only work (search, investigation, review, research) parallelizes freely.- Declare before dispatch:
Parallel plan: wave 1 = [...] · wave 2 = [...] · SEQ = [...] (reason).- Spawn each wave in ONE message — every
spawn_agentcall in one response, NEVER dripped per turn. Route each task to its specialist (.claude/skills/shared/sub-agent-selection-guide.md); NEVERcode-revieweras catch-all.- Brief each sub-agent self-contained: goal · scope + owned files · reference docs · return contract (summary +
Full report:path, per SYNC:subagent-return-contract) · incremental persistence toplans/reports/(per SYNC:incremental-persistence).- Barrier per wave. Advance ONLY after EVERY member returns (a skipped conditional counts as returned). Merge, mark each task completed/skipped, THEN dispatch the next wave. Mutating steps wait for the barrier.
- One level deep. A dispatched sub-agent executes its own brief; further fan-out stays the orchestrator's job unless that agent's
.claude/agents/*.mddefinition authorizes it.NEVER parallelize: tasks sharing a write target · a task consuming a pending task's output · trivial single-file work (dispatch overhead > gain) · an order a skill or workflow explicitly fixes · gates awaiting user approval.
Blocked until: MUST ATTENTION every task tagged PAR/SEQ with a named reason per SEQ · waves declared + write-set disjointness checked · each wave spawned in ONE message · barrier honored before the next wave.
- MANDATORY After planning tasks, tag each PAR/SEQ and spawn every PAR wave as parallel sub-agents in ONE message — default parallel for workflows, batch updates, investigation, research, reviews; plan execution fans out ONLY on what the plan declares.
- MANDATORY Disjoint write sets per wave · all-return barrier before the next wave · specialist routing · sub-agents NEVER fan out further unless their own agent definition authorizes it.
Project Protocol Overlay — Before executing this skill, resolve any PROJECT overlay rules layered onto it: match this skill's name against the
Targetcolumn of the project's skill-protocol index (docs/project-reference/skill-protocols-reference.mdby default; areferenceDocsentry indocs/project-config.jsonoverrides 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 bo
…(truncated)