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/leev1s/aa-mcp/agents-mdgit clone --depth 1 https://github.com/Leev1s/aa-mcpWrote 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/leev1s/aa-mcp/agents-md)<a href="https://agentmods.dev/instructions/leev1s/aa-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/leev1s/aa-mcp/agents-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 | $0.00571 | $0.00571 |
| Opus 5 | $0.00285 | $0.00285 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
aa-mcp 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 3d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This is a Python MCP server package using a src layout. Core code lives in src/aa_mcp/:
server.py: FastMCP tool definitions and CLI entry point.client.py: Artificial Analysis API client and API error types.snapshot.py: local snapshot persistence, normalization, and diff formatting.__init__.py: package metadata surface.
Project metadata and packaging configuration are in pyproject.toml; dependency locking is in uv.lock. There is currently no committed tests/ directory, so add one when introducing automated coverage.
Build, Test, and Development Commands
Use uv for all Python workflows.
uv sync: install locked dependencies for local development.uvx aa-mcp: run the published MCP server using stdio transport.uv build: build source and wheel distributions.uv run pytest: run the test suite once tests are added.
For manual server checks, set ARTIFICIAL_ANALYSIS_API_KEY before launching:
export ARTIFICIAL_ANALYSIS_API_KEY="aa_your_key_here"
uvx aa-mcp
Coding Style & Naming Conventions
Target Python 3.10+. Use type hints for public helpers and tool functions. Keep modules small and purpose-specific, following the existing split between server orchestration, API access, and snapshot logic.
Use snake_case for functions, variables, and modules; PascalCase for exception and class names. MCP tool names should keep the existing aa_ prefix, for example aa_healthcheck. Prefer official Artificial Analysis API field names in returned data and transformation code.
Testing Guidelines
Add tests under tests/ with filenames like test_client.py or test_snapshot.py. Focus unit tests on API error handling, model matching, sorting behavior, snapshot normalization, and diff output. Mock HTTP calls rather than relying on the live Artificial Analysis API. Run tests with:
uv run pytest
Commit & Pull Request Guidelines
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.
- 3d ago First seen · 53 lines · 571 tokens per session scan A 970a02402547
aa-mcp AGENTS.md is an instructions file published in the GitHub repository Leev1s/aa-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 571 tokens to every session, about $0.0029 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
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
Instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
flyto-core CLAUDE.md
Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
Plonk AGENTS.md
Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.