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.
npx skills add MSApps-Mobile/claude-plugins --skill claude-md-composergit clone --depth 1 https://github.com/MSApps-Mobile/claude-pluginsWrote 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.
[](https://agentmods.dev/skills/msapps-mobile/claude-plugins/claude-md-composer)<a href="https://agentmods.dev/skills/msapps-mobile/claude-plugins/claude-md-composer"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/claude-md-composer.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00168 | $0.01401 |
| Opus 5 | $0.00084 | $0.00700 |
| Sonnet 5 | $0.00034 | $0.00280 |
| Haiku 4.5 | $0.00017 | $0.00140 |
Grade A, and why
claude-md-composer 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md Composer
Treat CLAUDE.md as a recipe book on the counter, not a filing cabinet. Every token in CLAUDE.md is loaded into every session — so keep only what's needed for every interaction, and push everything else to Skills, docs/, or Commands.
The 200-line rule
The root CLAUDE.md should fit on one screen (~200 lines max). If it doesn't, something belongs elsewhere.
When to use this skill
- Audit — user has an existing CLAUDE.md and wants it trimmed
- Compose — user wants a fresh CLAUDE.md for a project
- Refactor — split monolith into the 4-level hierarchy
- Flip — convert negative rule lists to positive equivalents
The 4-level hierarchy
Enterprise policy ← org-wide, IT-managed, highest precedence
↓
./CLAUDE.md ← project memory (committed)
↓
~/.claude/CLAUDE.md ← user memory (personal, all projects)
↓
./CLAUDE.local.md ← project local (gitignored, private)
Feature-level CLAUDE.md files in subdirs load only when Claude touches that subtree — use them to scope per-folder conventions (/api, /frontend) without paying the token cost globally.
Workflow
Step 1 — Audit existing file
Read the target CLAUDE.md and report:
- Line count (flag if >200)
- Token estimate (~4 chars/token)
- Bloat categories found (see reference/anti-patterns.md)
- Candidates for extraction (docs dumps, file preloads, step-by-step tutorials, negative rule spirals)
Step 2 — Classify every section
For each section, decide:
| Keep in CLAUDE.md | Extract |
|---|---|
| Project identity (2-3 sentences) | API documentation → docs/api.md |
| House rules (positive form) | Step-by-step workflows → Skill |
| Output preferences | Reusable prompts → slash command |
| Hard boundaries | File preloads (@file:…) — delete |
| Quick reference (paths, entry points) | Detailed reference tables → docs/ |
Step 3 — Apply the recipe-book template
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 141 lines · 168 tokens per session scan A 5ee0f9cd5605
claude-md-composer is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed 12d ago), licensed MIT. It adds 168 tokens to every session and 1,401 once invoked, about $0.0008 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.
Other skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.
consult-gov-grant
A guide to Korean government and public-sector funding programmes for applicants such as founders, small businesses, companies, researchers, nonprofits, and individuals. It can help find suitable programmes and prepare application documents.