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/mhattingpete/agent-composer/claude-mdgit clone --depth 1 https://github.com/mhattingpete/agent-composerWrote 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/instructions/mhattingpete/agent-composer/claude-md)<a href="https://agentmods.dev/instructions/mhattingpete/agent-composer/claude-md"><img src="https://agentmods.dev/badge/instructions/mhattingpete/agent-composer/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00198 | $0.00198 |
| Opus 5 | $0.00099 | $0.00099 |
| Sonnet 5 | $0.00040 | $0.00040 |
| Haiku 4.5 | $0.00020 | $0.00020 |
Grade A, and why
agent-composer 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 5d 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
Agent Composer
Package Managers
- Backend:
uv(Python package manager) - Frontend:
bun(JavaScript runtime and package manager)
Startup Time: Backend starts in under 5 seconds. No need to wait longer.
Development
make dev # Start both backend (7777) and frontend (3000)
make dev-backend # Backend only
make test # Run tests
Model Provider
Uses OpenRouter for LLM access. Requires OPENROUTER_API_KEY in .env.
Default model: mistralai/devstral-2512:free
Key Files
backend/src/main.py- AgentOS entry pointbackend/src/agents.py- Agent/Team configurationsbackend/src/config_routes.py- Config API endpointsbackend/config/- JSON configs (agents, teams, MCP servers)
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.
- 5d ago First seen · 30 lines · 198 tokens per session scan A 25e454e65af0
agent-composer CLAUDE.md is an instructions file published in the GitHub repository mhattingpete/agent-composer (5 stars, last pushed 6mo ago), licensed MIT. It adds 198 tokens to every session, about $0.0010 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
ILLIP AGENTS.md
Instructions for Yashwanth-pilli/ILLIP, covering illip ai - agent framework documentation, agents, 1. planner agent, 2. builder agent and 3. reviewer agent.
ILLIP CLAUDE.md
Instructions for Yashwanth-pilli/ILLIP, covering illip ai — yashwanth dharan tej pilli instructions, session startup (required) and skill routing.
gptme AGENTS.md
AGENTS.md instructions for gptme/gptme, covering agent instructions for gptme, git workflow, code style, testing and project structure.
waku-agent CLAUDE.md
Instructions for ShenSeanChen/waku-agent, covering waku-agent — working conventions, architecture map (file ↔ diagram box), rules and commands.
openhuman CLAUDE.md
Claude Code instructions for tinyhumansai/openhuman, a project described as: OpenHuman is an open source personal AI for Mac, Windows and Linux — local-first memory, agent orchestration, and deep research.
linggen CLAUDE.md
Claude Code instructions for linggen/linggen, covering claude.md, doc and spec, build, test, run, architecture and configuration.