claude-md

claude-md is a skill for Claude Code, Codex from TeamSPWK/nova. It costs 91 tokens per session (5,227 once invoked), scanned A, original, MIT.

A tool for creating or reorganizing CLAUDE.md and AGENTS.md files, which give coding agents project instructions.

In plain words
What is it for?
Use it to design new agent instructions, audit existing ones, preserve their history, and decide where each rule belongs.
Why use it?
It keeps important rules, project context, and boundaries from being scattered, duplicated, or inconsistent.

Skill for Claude CodeCodex

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 skills/teamspwk/nova/claude-md
Any agent
npx skills add TeamSPWK/nova --skill claude-md
Clone the repo
git clone --depth 1 https://github.com/TeamSPWK/nova

Made for: Claude Code, Codex.

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.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for claude-md

README.md
[![agentmods](https://agentmods.dev/badge/skills/teamspwk/nova/claude-md.svg)](https://agentmods.dev/skills/teamspwk/nova/claude-md)
Your own site
<a href="https://agentmods.dev/skills/teamspwk/nova/claude-md"><img src="https://agentmods.dev/badge/skills/teamspwk/nova/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,227 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00091 $0.05227
Opus 5 $0.00046 $0.02613
Sonnet 5 $0.00018 $0.01045
Haiku 4.5 $0.00009 $0.00523

Measured 4d ago against content hash de1d76a5190f, 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 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- 성공 기준을 테스트·빌드·스크린샷·curl 등으로 검증 가능하게 정의하고, 검증될 때까지 반복하기
.claude/skills/claude-md/SKILL.md · 373 lines

How it starts

The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nova CLAUDE.md Architect

프로젝트의 에이전트 지침 표면을 설계·정리한다. Nova 5기둥 중 맥락(세션마다 필요한 지식), 환경(시크릿/인프라 경계), 협업(여러 에이전트가 같은 기준으로 일함)에 걸친 스킬이다.

핵심 원칙

  1. CLAUDE.md = 운영 헌법 + 라우터
    전체 매뉴얼이 아니라 매 세션 반드시 알아야 하는 불변 사실, 위험 경계, 진입점만 담는다. 상세 절차는 링크하거나 별도 표면으로 이동한다.

  2. 분리 기준을 파일로 남긴다
    정리 결과만 만들지 않는다. 다음 에이전트가 새 지침을 추가할 때 같은 판단을 하도록 Instruction Placement Contract를 CLAUDE.md/AGENTS.md 또는 .claude/rules/instruction-placement.md에 남긴다.

  3. 신규는 뼈대를 만들고, 기존은 이력을 보존한다
    신규 프로젝트는 빈칸을 솔직히 남기고 방향을 잡는다. 기존 프로젝트는 먼저 현재 파일을 감사한 뒤 keep / move / enforce / local-only / remove로 분류한다. 기존 규칙은 이동하더라도 잃지 않는다.

  4. 강제와 조언을 분리한다
    CLAUDE.md의 "절대 금지"는 요청일 뿐임을 사용자에게 알린다. 더 강한 차단이 필요하면 .claude/settings.json, hooks, CI, 스크립트가 가능한 위치라는 것까지만 안내한다. 강제 도구의 설치·수정은 사용자가 명시적으로 요청했을 때만 진행하며, 본 스킬이 자동으로 권한 설정을 작성하거나 적용하지 않는다.

  5. 크로스 에이전트 호환성을 설계한다
    Claude Code는 CLAUDE.md, Codex 및 여러 에이전트는 AGENTS.md를 본다. 신규 프로젝트는 가능하면 AGENTS.md를 공통 계약으로 두고 CLAUDE.md@AGENTS.md를 import한다. 기존 CLAUDE 중심 프로젝트는 얇은 AGENTS 브리지로 시작하고, 필요할 때만 canonical 전환한다.

적용 규칙 (on-demand 로드)

  • docs/nova-rules.md §1 작업 전 복잡도 + 위험도 판단
  • docs/nova-rules.md §3 검증 기준 — 요청 범위, 데이터 관통, 경계값
  • docs/nova-rules.md §8 NOVA-STATE.md 세션 상태 유지
  • docs/nova-rules.md §11 도구 제약 계약 — 하드 가드는 settings/hooks로 강제
  • docs/nova-rules.md §15 Memory Routing — 프로젝트 규칙은 개인 memory 금지, canonical로

모드 판별

조건 모드 동작
인자 없음 (/nova:claude-md) Guided 짧은 가이드 출력 후 현재 레포 기준으로 Audit/New 안전 흐름 시작
--check Audit 파일 수정 없이 현황, 중복, 과밀, 미강제 규칙을 보고
--apply Apply 사용자가 승인한 분리안을 파일에 반영
--new 또는 CLAUDE.md/AGENTS.md 없음 New Project 최소 지침 구조와 빈칸을 생성
기존 CLAUDE.md/AGENTS.md 있음 Adopt Existing 현재 지침을 감사한 뒤 재구성 제안
모노레포/하위 패키지 Nested 루트 공통 지침과 패키지별 지침을 분리
--global-karpathy 또는 사용자가 전역 Karpathy 설정 요청 Global Karpathy 개인 전역 지침에 Karpathy 압축 원칙 추가/갱신

기본은 안전하게 Audit → 제안 → 승인 후 Apply다. 사용자가 명시적으로 "바로 적용" 또는 --apply를 주면 적용까지 진행한다.

Guided Mode

Read the full file on GitHub · 373 lines

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. 4d ago First seen · 373 lines · 91 tokens per session scan A de1d76a5190f

Subscribe to this mod's changes

claude-md is a skill published in the GitHub repository TeamSPWK/nova (2 stars, last pushed 4d ago), licensed MIT. It adds 91 tokens to every session and 5,227 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

create-site

Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…

microsoft/power-platform-skills · 73 tokens

google-ads-audit

Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…

nowork-studio/notfair-plugin · 114 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

alive:system-upgrade

Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.

alivecontext/alive · 57 tokens

codex-test-gen

Generate unit tests for specified functions using Codex MCP.

sd0xdev/sd0x-harness · 15 tokens

travel-itinerary

Create, update, sanitize, route, and export structured business-trip itineraries from booking confirmations, emails, tickets, PDFs, screenshots, calendar invites, or notes. Use for day-by-day itinerary generation, privacy-safe sharing, route links, and Markdown/PDF/DOCX/Google Doc/ICS exports.

moonlight-lupin/agent-skills · 66 tokens