Sync Codex

Quick Summary

Goal: Run the full Codex mirror pipeline standalone — equivalent to npm run sync:all && npm run verify:all (sync + verify) without package.json or npm. This runner is the single source of truth for the pipeline; the package.json sync:all/verify:all scripts delegate to it, so a project that only copied .claude (no root package.json) runs the identical pipeline.

Summary:

• Run the 18-stage orchestrator in order; stages 1-3 generate the Codex mirrors and stages 4-18 run tests and read-only release gates.
• Keep .claude canonical and source-owned; never hand-edit .agents, .codex, or AGENTS.md, and expect Claude slash invocations to become Codex dollar invocations only in generated mirrors.
• If a stage fails, rerun that stage with --only=<stage> --verbose, then rerun the full pipeline and inspect the generated diff before handoff.

Renamed: formerly /codex-sync — that name no longer resolves as a slash command; use /sync-codex.

Also bootstraps team-wide Codex completion notifications by copying the portable .claude/scripts/codex/codex-notify.mjs helper into .codex/scripts/codex/ and upserting notification plus TUI status-line keys into .codex/config.toml.

Workflow:

1. Run — node .claude/skills/sync-codex/scripts/run-codex-sync.mjs
2. Verify — Exit code 0 = pass; check stdout summary
3. Inspect — On failure, re-run failing stage manually with --only=<stage> and --verbose

Key Rules:

• MUST evaluate all 18 stages in order — configured stages fail fast on the first non-zero exit; optional stages emit an explicit SKIP (not configured) when the adopter has not declared their contract
• NEVER edit .agents/skills/sync-codex/** (auto-mirror) — edit .claude/skills/sync-codex/** source instead
• .claude is the source for skills/workflows/hooks; generated acceptance targets are .agents/skills/**, .codex/CODEX_CONTEXT.md, and AGENTS.md
• Stages 1-3 mutate .agents/skills/, .codex/, AGENTS.md; stages 4-18 are read-only (tooling tests, optional tech-spec freshness and feature-registry validation, 3 hook-suite gates, the other Codex verifiers, and the cross-surface divergence oracle)
• Stage 1 upserts [tui].status_line to show model+reasoning, current directory, project root, context used, five-hour limit, and weekly limit by default
• Stage 3 generates the bounded AGENTS.md projection and full .codex/CODEX_CONTEXT.md static mirror, while hook configuration remains a separate optional accelerator; both Claude and Codex must still follow the same canonical protocol when hooks are absent
• Stage 1 must not inline docs/project-reference/lessons.md content into .agents/skills/**; generated skill mirrors reference the project-reference loading gate instead
• The SYNC:ai-sdd-artifact-contract marker must appear after sync in .codex/CODEX_CONTEXT.md and AGENTS.md
• No npm dependency — pure node + spawned subprocesses
• Idempotent — safe to re-run; second run produces only timestamp diffs

Bootstrap Gate (when AGENTS.md is missing or incomplete)

This skill is the route the agent-files bootstrap gate offers for a missing — or incomplete — root AGENTS.md, the generated Codex mirror of CLAUDE.md. Claude and Codex may both support hooks, but the universal session-start and workflow guides must remain available statically; stage 3 produces the bounded root projection (with the <!-- CK:UNIVERSAL-GUIDES v1 --> sentinel when present) plus the full static-parity context. Hooks may accelerate loading, but they never replace the generated files.

"Incomplete" means the file exists but lacks the universal guides — same three-state detection as the CLAUDE.md route (missing → init, incomplete → update smart-merge preserving project content, ok → no block), decided by the shared sentinel-then-anchors check.

Detection is shared with the CLAUDE.md route via .claude/hooks/lib/agent-files-state.cjs. Opt out of completeness enforcement with portability.requireUniversalGuides: false in docs/project-config.json (default true); skip init dismisses both hooks for 24h. Generate CLAUDE.md first (via /claude-md-init) — stage 3 reads it as the mirror source.

Stages

18 stages, sequential — the full npm run sync:all && npm run verify:all pipeline (the npm scripts delegate here). Stages 1-3 mutate; 4-18 verify (read-only). Tech-spec freshness and feature-registry are optional capabilities: if their configuration contract is absent, the runner records an explicit skip and continues; if declared but malformed, their direct verifier fails closed:

Usage

# Full sync (standalone, no npm):
node .claude/skills/sync-codex/scripts/run-codex-sync.mjs

# Stream live child output:
node .claude/skills/sync-codex/scripts/run-codex-sync.mjs --verbose

# Full sync while forcing skill copy mode:
node .claude/skills/sync-codex/scripts/run-codex-sync.mjs --copy-skills

# Read-only verifiers (no mutation) — the full `npm run verify:all`:
node .claude/skills/sync-codex/scripts/run-codex-sync.mjs --only=tests,scripts-tests,tech-spec-freshness,feature-registry,hooks-count-drift,hooks-parity,hooks-doc-sync,wf-cycle,sk-proto,residue,sdd,review-validate-coverage,sync-adoption-parity,provenance-markers,sync-divergence

# Configured feature-registry adoption roots (continuation parts discovered automatically):
node .claude/scripts/codex/verify-feature-registry.mjs --configured-roots

# Explicit paths or the whole tree remain available for audits (omit paths for whole-tree mode):
node .claude/scripts/codex/verify-feature-registry.mjs docs/specs/Area/README.Feature.md

# Skip stages while debugging:
node .claude/skills/sync-codex/scripts/run-codex-sync.mjs --skip=migrate,hooks

Exit codes: 0 all pass · 1 orchestrator failure · non-zero propagates from failing stage.

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

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

Project Protocol Overlay — Before executing this skill, resolve any PROJECT overlay rules layered onto it: match this skill's name against the Target column of the project's skill-protocol index (docs/project-reference/skill-protocols-reference.md by default; a referenceDocs entry in docs/project-config.json overrides the path), taking the most specific matching tier ONLY — exact name > glob > *. That precedence orders overlays against EACH OTHER, never against this skill. Read ONLY the matched bodies, resolved as <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

Protocols in force (concise digest of the SYNC/shared blocks this skill carries) — MUST ATTENTION each canonical body below still binds:

• AI Mistake Prevention: verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity.
• Critical Thinking: traced file:line proof per claim, confidence >80% to act, never guess.

MUST ATTENTION invoke ONLY when user explicitly requests codex sync — never auto-invoke, with ONE authorized exception: /project-skill-protocol runs this pipeline automatically after its three writes, because it is the sole writer of the CLAUDE.md CK:PROJECT-PROTOCOLS block and a stale AGENTS.md would defeat that block's only purpose (cross-host reach). No other skill, agent, or workflow may auto-run it MUST ATTENTION edit source .claude/skills/sync-codex/**, NEVER the .agents/skills/sync-codex/** mirror MUST ATTENTION keep .codex/scripts/codex/codex-notify.mjs generated from .claude/scripts/codex/codex-notify.mjs; edit the .claude source first MUST ATTENTION keep Codex config upserts surgical; preserve unrelated .codex/config.toml keys and tables while updating the managed notification/status-line keys MUST ATTENTION keep AGENTS.md sync comprehensive; mirror full CLAUDE.md plus generated hook/context blocks, and preserve unmanaged AGENTS.md preface text MUST ATTENTION keep learned-lessons content out of .agents/skills/**; skills may point to docs/project-reference/lessons.md but must not embed its entries MUST ATTENTION orchestrator fails fast — re-run single failing stage with --only=<id> --verbose to debug MUST ATTENTION working directory auto-resolves to repo root from script path — do not pass --cwd MUST ATTENTION stages 1-3 mutate; stages 4-18 verify only — use --only= for non-destructive validation

Anti-Rationalization:

[FAILS FAST] First non-zero stage exit aborts chain. Re-run failing stage manually to debug. [REPO ROOT] Orchestrator auto-resolves repo root from its own path. NEVER pass --cwd.

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

MUST ATTENTION apply critical + sequential thinking — every claim needs appropriate traced evidence (file:line for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.

MUST ATTENTION apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting.