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/bigg01/aipod/claude-mdgit clone --depth 1 https://github.com/bigg01/aipodWrote 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/bigg01/aipod/claude-md)<a href="https://agentmods.dev/instructions/bigg01/aipod/claude-md"><img src="https://agentmods.dev/badge/instructions/bigg01/aipod/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 | $0.02418 | $0.02418 |
| Opus 5 | $0.01209 | $0.01209 |
| Sonnet 5 | $0.00484 | $0.00484 |
| Haiku 4.5 | $0.00242 | $0.00242 |
Grade A, and why
aipod 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 2d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this project is
aipod is one Python package, two modes, selected by subcommand and sharing one FROM scratch container image:
aipod server— a reference MCP server whose stated purpose is to exercise every MCP feature (tools, structured output, static + templated resources, prompts, argument completion, resource subscriptions, progress, logging levels, sampling) behind one endpoint, so client / gateway / runtime authors have a complete thing to test against. Completeness is the point: new MCP capabilities belong here, must stay working, and must be reflected in the contract + docs.aipod agent— a pydantic-aiAgentthat is an MCP client of anaipod server.
src/aipod/__main__.py is the dispatcher. --print contract / --print agent-card emit JSON and exit without starting a server.
Commands
Everything runs through uv (see make help for the full list):
| Task | Command |
|---|---|
| Install deps | uv sync |
| Run all tests | uv run pytest -q |
| Run one test | uv run pytest tests/test_server.py::test_tool_inventory |
| Server (HTTP) | make server — uv run aipod server --transport http --host 127.0.0.1 --port 8000 |
| Server (stdio) | make server-stdio |
| Agent | make agent (needs AIPOD_MODEL + provider key for /ask) |
| One-shot agent call | uv run aipod agent --ask "..." |
| Regenerate contract | make contract → examples/contract.json |
| Regenerate agent card | make card → examples/agent-card.json |
| Exercise via MCP Inspector | make inspect-cli / see docs/testing-mcp.md (uses @modelcontextprotocol/[email protected] — the v2 line; v0.x / v1 is deprecated) |
| Build container | make docker |
| Standalone binary | make binary (PyInstaller; needs the build dependency group) |
| Render / lint Helm | make helm-template / make helm-lint |
| Apply Kustomize | make k8s |
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.
- 2d ago First seen · 78 lines · 2,418 tokens per session scan A 7cda0c0dc73e
aipod CLAUDE.md is an instructions file published in the GitHub repository bigg01/aipod (0 stars, last pushed 4d ago), licensed MIT. It adds 2,418 tokens to every session, about $0.0121 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
clickup-mcp CLAUDE.md
Claude Code instructions for Npab19/clickup-mcp, covering claude.md — clickup mcp server, what this is, the one rule, clickup api facts that trip people up and adding a tool.
aks-mcp copilot-instructions.md
Instructions for Azure/aks-mcp, covering copilot instructions, project overview, architecture, high-level structure and key components.
payload-mcp-oauth CLAUDE.md
Instructions for BrainWeb/payload-mcp-oauth, covering claude.md, project overview, repository structure, commands and install (run once at root).
kalshi-mcp-server AGENTS.md
Instructions for cejor6/kalshi-mcp-server, covering agent guide, what this project is, repo layout, how authentication works and how rate limiting works.
swag-mcp CLAUDE.md
Instructions for jmagar/swag-mcp, covering swag mcp - claude memory reference, project overview, core architecture, key components and common development commands.
sbb-opendata-mcp CLAUDE.md
Instructions for malkreide/sbb-opendata-mcp, covering claude.md, teil 1 — konventionen (portfolio-weit), vor der arbeit, tests and wenn etwas rot ist.