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.
git 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/plugins/msapps-mobile/claude-plugins/md-composer)<a href="https://agentmods.dev/plugins/msapps-mobile/claude-plugins/md-composer"><img src="https://agentmods.dev/badge/plugins/msapps-mobile/claude-plugins/md-composer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/msapps-mobile/claude-plugins/md-composer"><img src="https://agentmods.dev/badge/plugins/msapps-mobile/claude-plugins/md-composer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
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 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.
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.
What it actually says
{
"name": "md-composer",
"version": "1.0.3",
"description": "Audit, compose, and refactor CLAUDE.md files using the 'recipe book, not filing cabinet' pattern — keep memory files scannable, token-lean, and organized across the 4-level hierarchy (enterprise → project → user → local).",
"author": {
"name": "MSApps",
"url": "https://msapps.mobi"
},
"homepage": "https://github.com/MSApps-Mobile/claude-plugins/tree/main/plugins/md-composer",
"repository": "https://github.com/MSApps-Mobile/claude-plugins",
"license": "MIT",
"keywords": [
"claude-md",
"CLAUDE.md",
"memory",
"token-optimization",
"context-budget",
"audit",
"composer",
"refactor",
"recipe-book",
"200-line-rule",
"hierarchy",
"skills"
]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 166 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 4d ago First seen · 27 lines scan A 5a15eb9acec4
md-composer is a plugin published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-12.
Other plugins, from other repositories
aios
Set up an AI OS at the tier that fits — Skill OS (your entire second brain inside one Claude skill, zero infra) or Cloud OS (synced via Google Drive, OneDrive, iCloud, or Dropbox). Shares one folder structure with the Local OS (Obsidian) tier so you can graduate between them.
cigar
Deterministic, inspectable, governed context for Claude Code through public hooks and MCP.
memory-loop
A memory lifecycle for Claude Code's native file-based memory: a save gate against hallucinated memories, tiered expiry (short-tier memories archived — never deleted — when they lapse), a propose-then-confirm consolidation pass (merge/dedupe long-tier memory), a correction-signal hook that logs likely corrections for…
groundwork marketplace
A safe-by-default, batteries-included Claude Code harness starter pack — guardrails, a wiki-grounded quality loop, and a memory lifecycle.
odin-knowledge
ODIN workflows for memory, session continuity, decision records, and retrospectives.
handoff
Session quality gate for Claude Code. Health checks, resume points, and cross-machine continuity.