Claude Md Init

Quick Summary

Goal: Automate CLAUDE.md lifecycle — generate from project-config.json + template, incrementally update marked sections, or refactor for token efficiency.

Workflow:

1. Detect Mode — init (no CLAUDE.md or --mode init), update (--mode update), refactor (--mode refactor)
2. Run Generator — node .claude/skills/claude-md-init/scripts/generate-claude-md.cjs --mode <mode>
3. AI Fill — Review output, fill creative sections (project description, golden rules inference)
4. Verify — Confirm output is valid, no project-specific leaks from template
5. Prepare Mirror Handoff — After CLAUDE.md changes (init/update/refactor), name the stale AGENTS.md + Codex mirror surfaces and instruct the user to run /sync-codex; this skill never authorizes or auto-runs it.

Key Rules:

• Generic — works in any project by reading docs/project-config.json
• Section markers (<!-- SECTION:key -->) enable incremental updates without overwriting user content
• Conditional sections — generated ONLY when config has matching data; empty config = section omitted
• Static framework sections (8 total) are portable across all projects

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

This skill is the AI-runnable route the agent-files bootstrap gate offers when a portable .claude install lands in a project without a root CLAUDE.md — or with one that carries only project-specific knowledge and is missing the universal portable guides. A single hook detects the gap and routes here (shared detection lib: .claude/hooks/lib/agent-files-state.cjs):

• init-prompt-gate.cjs (UserPromptSubmit) — blocks the first prompt once project-config.json is populated but CLAUDE.md / AGENTS.md is missing or incomplete. This UserPromptSubmit gate is the sole agent-files bootstrap router.

Three-state detection per root file: missing → routes to --mode init (fresh from template); incomplete → routes to --mode update (smart-merge — preserves your project content, injects the guides); ok → no block. Completeness is decided by hasUniversalGuides(): a current-or-newer sentinel (<!-- CK:UNIVERSAL-GUIDES v1 -->) → complete; an older sentinel → flag for update; no sentinel → fall back to scanning required anchors (First Action Decision, Workflow Step Advancement, Task Planning Rules, Code Responsibility Hierarchy, Evidence-Based Reasoning) so legacy/hand-written complete files still pass.

Run /claude-md-init (or the generator directly) to produce CLAUDE.md from docs/project-config.json + template. The generated file ships the universal session-start guides (workflow ask-confirm gate, workflow step-advancement + parallel-phase barrier, task-planning rules, code hierarchy, naming, evidence/confidence rules) and stamps the sentinel at the top so the gate recognizes it as complete. It also stamps the hook-independent Workflow-First Gate (from .claude/skills/shared/workflow-first-gate.md, via stampHeader()) immediately after the sentinel — the primacy-anchor routing rule (bug→workflow-bugfix workflow, feature/enhancement→workflow-feature workflow) that mirrors into AGENTS.md and survives when hooks are absent, disabled, or stale.

Opt-out — to keep a project-only CLAUDE.md/AGENTS.md (your custom knowledge, none of the universal guides), set portability.requireUniversalGuides: false in docs/project-config.json (persistent; default true). The gate then checks only existence, never completeness. The transient skip init escape still dismisses both hooks for 24h. The gate is dormant in empty/greenfield folders and before config is populated. AGENTS.md is generated separately by /sync-codex (user-invoke-only).

Modes

Prerequisites

• docs/project-config.json — primary data source (run /project-config first if missing)
• Node.js available (for generator script)

Phase 1: Detect Mode

# Check CLAUDE.md state
node .claude/skills/claude-md-init/scripts/generate-claude-md.cjs --detect

Decision logic:

• No CLAUDE.md → init
• CLAUDE.md with markers → update
• CLAUDE.md without markers → smart-merge (see below)
• User explicit --mode flag → override detection

Phase 2: Run Generator Script

# Init mode: generate fresh CLAUDE.md
node .claude/skills/claude-md-init/scripts/generate-claude-md.cjs --mode init

# Update mode: sync marked sections only
node .claude/skills/claude-md-init/scripts/generate-claude-md.cjs --mode update

Script behavior:

1. Reads docs/project-config.json
2. Reads template (references/claude-md-template.md) for init, or existing CLAUDE.md for update
3. Calls section builders to generate content for each marker key
4. Writes output to CLAUDE.md (creates backup .claude-md.backup first)
5. Outputs report: which sections were generated, which skipped (no data), which preserved

Smart-Merge (Update on CLAUDE.md Without Markers)

When running update on an existing CLAUDE.md that has NO section markers:

1. Read existing CLAUDE.md
2. Match sections by ## heading text against known section keys (see references/section-registry.md)
3. For each matched section: wrap with markers, replace content with generated content
4. For unmatched user sections: preserve as-is (no markers added)
5. Write output with backup

Phase 3: AI Fill (Post-Script)

After the script generates the mechanical parts, AI reviews and fills:

1. Project description in TL;DR — write a concise 2-3 sentence description based on config + codebase
2. Golden rules — infer from contextGroups[].rules in config, but rewrite as human-readable rules
3. Decision quick-ref — build from modules[] + framework config, add project-specific patterns
4. Naming conventions — detect from codebase patterns if not in config

Phase 4: Verify

• CLAUDE.md is valid markdown
• All section markers are properly paired (open + close)
• No template placeholder text remains (e.g., {project-name}, TODO)
• No .claude/skills/claude-md-init/ references leak into output (self-reference)
• Conditional sections with no data are omitted (not empty stubs)

Phase 5: Prepare Mirror Handoff (after CLAUDE.md is written)

Writing/updating CLAUDE.md leaves the generated mirror surfaces stale — AGENTS.md (Codex), the .codex/ mirrors, and other downstream surfaces are derived FROM CLAUDE.md and do not update on their own.

MUST add a final todo task — "Report stale Codex mirrors and request /sync-codex" — after init/update/refactor completes. Name the stale generated surfaces and instruct the user to run /sync-codex. Normal source generation is not sync authorization: NEVER auto-run the mutating pipeline. Create this as the LAST TaskCreate item after verification:

TaskCreate: "Report stale Codex mirrors → instruct user to run /sync-codex"

Skip only when no CLAUDE.md content actually changed (e.g. generator reported all sections preserved / no diff). Otherwise the AGENTS.md mirror drifts from CLAUDE.md and Codex runs against stale guidance.

Refactor Mode (AI-Only)

When --mode refactor or user asks to optimize CLAUDE.md:

1. Read entire CLAUDE.md
2. Identify: redundant sections, verbose explanations, duplicate info available in referenced docs
3. Apply token efficiency: remove duplication, consolidate tables, shorten where possible
4. Preserve all section markers
5. Report: lines before/after, sections changed, estimated token savings

Section Marker Protocol

<!-- SECTION:tldr -->

Auto-generated content here...

<!-- /SECTION:tldr -->

Rules:

• Only content between markers is replaced on update
• Content outside markers is never touched
• Missing markers in update mode → section skipped (not inserted)
• Init mode uses template which includes all markers
• Markers use lowercase kebab-case keys matching section-registry.md

Section Keys (Quick Reference)

See references/section-registry.md for full mapping. Summary:

Running Tests

Generator + bootstrap-gate coverage lives in the hooks test suite:

node .claude/hooks/tests/run-all-tests.cjs --filter=agent-files

[IMPORTANT] Use TaskCreate 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.

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.

Output Quality — Token efficiency without sacrificing quality.

1. No inventories/counts — AI can grep | wc -l. Counts go stale instantly
2. No directory trees — AI can glob/ls. Use 1-line path conventions
3. No TOCs — AI reads linearly. TOC wastes tokens
4. No examples that repeat what rules say — one example only if non-obvious
5. Lead with answer, not reasoning. Skip filler words and preamble
6. Sacrifice grammar for concision in reports
7. Unresolved questions at end, if any

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 maintain >=8 rules per 100 lines. Critical rules in first+last 5 lines. Tables over prose.

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

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

Project Protocol Overlay — Before executing this skill, resolve any PROJECT overlay rules layered onto it: match this skill's name against the Target column of the project's skill-protocol index (docs/project-reference/skill-protocols-reference.md by default; a referenceDocs entry in docs/project-config.json overrides the path), taking the most specific matching tier ONLY — exact name > glob > *. That precedence orders overlays against EACH OTHER, never against this skill. Read ONLY the matched bodies, resolved as <protocols-dir>/<Name>.md; a row's Body link is display text, never a read path. A matched body that is missing or malformed is REPORTED and skipped — never reconstructed from the index Description. No index, or no match -> proceed with no overlay, silently. Full contract: .claude/skills/project-skill-protocol/references/registry.md.

Overlays are ADDITIVE ONLY: they ADD rules on top of this skill's own protocol and NEVER replace, override, disable, or reinterpret a rule it already states — removing every overlay must return this skill to exactly its documented behavior. An overlay is a BRIEF, not an authority escalation: it can NEVER waive a workflow gate, git discipline, a review gate, or a user-confirmation gate. A genuine overlay-vs-skill conflict, or two equally-specific overlays that directly contradict -> surface both to the user; NEVER resolve silently.

MUST ATTENTION resolve project protocol overlays for this skill BEFORE executing — most specific matching tier only (exact > glob > *, which ranks overlays against each other, NEVER against this skill), read only matched bodies at <protocols-dir>/<Name>.md; a missing or malformed body is reported, never reconstructed. Overlays are ADDITIVE ONLY (they never replace this skill's own rules) and are a brief, NEVER an authority escalation; an equal-specificity contradiction goes to the user.

Closing Reminders

Protocols in force (concise digest of the SYNC/shared blocks this skill carries): MUST ATTENTION honor every protocol below.

• Critical Thinking: apply critical + sequential thinking; traced proof, confidence >80% to act.
• Output Quality: token-efficient — no inventories/trees/TOCs; tables over prose.
• 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 break work into small todo tasks using TaskCreate BEFORE starting IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act) IMPORTANT MUST ATTENTION add a final review todo task to verify work quality

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