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 agentmods add instructions/hyperactdoting/composer-plugin/agents-mdgit clone --depth 1 https://github.com/hyperactdoting/composer-pluginWhat 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 | $0.00439 | $0.00439 |
| Opus 5 | $0.00219 | $0.00219 |
| Sonnet 5 | $0.00088 | $0.00088 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
composer-plugin AGENTS.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 yesterday.
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
Composer
Composer is a real-time collaborative markdown editor. This plugin gives your terminal agent a way to open a doc, listen to comments, and reply inline as a first-class collaborator.
What you have
When this plugin is loaded, the composer-mcp MCP server is registered
and the following are available:
- Skill:
composer— full guidance on creating rooms, handling mentions, posting suggestions, anchoring text, and the always-on monitor loop. Invoke it with/composeror load the skill on any Composer-related work. - Slash command:
/composer:join [url]— open a doc and spawn the monitor subagent. Use to start watching, pick up a doc someone shared, or re-attach after a previous monitor exits. - MCP tools under
composer_*—composer_create_room,composer_join_room,composer_next_event, plus read and write tools for sections, threads, comments, and suggestions.
When to invoke the skill
Always invoke the composer skill BEFORE calling any composer_* MCP
tool. The skill carries the conventions for naming, mention semantics,
suggestion shape, and the subagent-spawn pattern — none of which are
obvious from the tool schemas alone.
Triggers:
- The user pastes a
usecomposer.md/d/<id>URL. - The user says "send this to Composer", "create a Composer doc", "watch that doc", "rejoin Composer".
- The user
/composeror/composer:joindirectly.
What this plugin does NOT do
- It does not run a server. The MCP connects to the hosted Composer service over WebSockets.
- It does not store secrets. The agent's display name lives in
~/.composer/user.jsonon first use.
Source
- Plugin source: https://github.com/hyperactdoting/composer-plugin
- MCP source: published to npm as
@composer-app/mcp - Composer service: https://usecomposer.md
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.
- yesterday First seen · 49 lines · 439 tokens per session scan A 835f8762ef2c
composer-plugin AGENTS.md is an instructions file published in the GitHub repository hyperactdoting/composer-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 439 tokens to every session, about $0.0022 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.