claude-md

A command for auditing and reorganizing CLAUDE.md and AGENTS.md, files that tell coding agents how a project should be worked on. It separates general instructions from detailed procedures, path-specific rules, safeguards, and current state.

In plain words
What is it for?
Use it to audit current instructions, create a starting structure for a new project, reorganize existing guidance, check the result without changes, or review optional global principles.
Why use it?
It reduces confusing or misplaced agent instructions and makes the project’s guidance easier to maintain. It offers a review-first process instead of immediately overwriting existing files.

Command for Claude Code

Part of the nova plugin — 14 skills, 19 commands, 6 agents, 5 hooks, 1 MCP server shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/teamspwk/nova/claude-md
Clone the repo
git clone --depth 1 https://github.com/TeamSPWK/nova

Made for: Claude Code.

Or install nova, the plugin that ships this one along with the rest of its 14 skills, 19 commands, 6 agents, 5 hooks, 1 MCP server.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 792 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.00792
Opus 5 $0.00017 $0.00396
Sonnet 5 $0.00007 $0.00158
Haiku 4.5 $0.00003 $0.00079

Measured 2d ago against content hash db8247143c4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/claude-md.md · 64 lines

What it actually says

/nova:claude-md

프로젝트의 에이전트 지침 표면을 설계·정리한다. CLAUDE.md를 운영 헌법 + 라우터로 유지하고, 상세 절차·경로별 규칙·강제 가드·현재 상태를 올바른 위치로 분리한다.

적용 스킬

  • skills/claude-md/SKILL.md — 신규/기존 프로젝트 지침 감사, 분리 기준, 생성 템플릿

사용법

/nova:claude-md                # 처음 사용자용 가이드 + 현재 레포 감사 시작
/nova:claude-md --check        # 수정 없이 감사만
/nova:claude-md --apply        # 승인된 재구성안 적용
/nova:claude-md --new          # 신규 프로젝트 지침 골격 생성
/nova:claude-md --adopt        # 기존 CLAUDE.md/AGENTS.md 재구성
/nova:claude-md --global-karpathy  # 개인 전역 Karpathy 압축 원칙 추가/갱신 여부 확인

인자가 없으면 Guided Mode로 실행한다. 먼저 60초짜리 짧은 안내를 보여주고, 현재 레포에 CLAUDE.md/AGENTS.md가 있는지에 따라 --check 또는 --new에 해당하는 안전한 제안 흐름으로 이어간다.

실행 규칙

  1. 먼저 skills/claude-md/SKILL.md를 읽고 그 절차를 따른다.
  2. 기존 지침 파일이 있으면 즉시 덮어쓰지 말고 섹션별 keep / move / enforce / local-only / remove 분류표를 만든다.
  3. 신규 프로젝트는 모르는 정보를 추측하지 말고 TODO(owner) 또는 질문으로 남긴다.
  4. hard guard는 현재 enforcement 상태(advisory / enforced / enforcement-optional)를 표시만 한다. 사용자가 명시적으로 요청하지 않으면 .claude/settings.json을 자동 생성·수정하지 않는다. 권한/차단 설정 적용은 사용자 결정 사항으로 안내한다.
  5. 정리 결과에는 반드시 다음 에이전트가 같은 기준을 적용할 수 있는 Instruction Placement Contract를 남긴다.
  6. 인자가 없으면 Guided Mode를 먼저 출력한다. 사용자가 플래그를 몰라도 다음 행동을 선택할 수 있게 한다.
  7. --global-karpathy는 프로젝트 파일이 아니라 ~/.claude/CLAUDE.md, ~/.codex/AGENTS.md만 대상으로 하며, 수정 전 반드시 yes/no 확인을 받는다.

Output

━━━ Agent Instructions Audit ━━━━━━━━━━━━━
Mode: Existing / New / Nested
Loaded: CLAUDE.md N lines, AGENTS.md N lines, rules N, skills N, settings yes/no

Verdict:
- Size: PASS/WARN/FAIL
- Duplication: PASS/WARN/FAIL
- Enforcement gaps: N
- Cross-agent bridge: PASS/WARN/FAIL

Placement Plan:
| Source section | Classification | Destination | Reason |

Proposed files:
| File | Action | Notes |

Questions:
- {추측하면 안 되는 정보}
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Input

$ARGUMENTS

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 64 lines · 35 tokens per session scan A db8247143c4c

Subscribe to this mod's changes

claude-md is a command published in the GitHub repository TeamSPWK/nova (2 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 792 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.