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/philipithomas/ghost-mcp/agents-mdgit clone --depth 1 https://github.com/philipithomas/ghost-mcpWhat 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 | $0.00619 | $0.00619 |
| Opus 5 | $0.00309 | $0.00309 |
| Sonnet 5 | $0.00124 | $0.00124 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
ghost-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 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 — 20 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
The application code lives in src/, with main.py bootstrapping the MCP server, mcp_server.py defining FastAPI routes, and services such as chroma_service.py, ghost_client.py, and indexer.py handling storage, API access, and synchronization. Shared models and settings sit in models.py and config.py. Tests reside in tests/ and mirror the runtime modules (test_api.py, test_mcp_tools.py, etc.). Supporting tooling includes the project-wide pyproject.toml, Makefile, container specs (Dockerfile, Dockerfile.dev, docker-compose.yml), and helper scripts like run.sh and validate-docker.sh. Coverage artifacts land in htmlcov/; clear it before committing.
Build, Test, and Development Commands
Install dependencies with uv sync --all-extras. Use uv run python -m src.main or ./run.sh to start the server locally. make dev installs development tooling, make format and make lint apply Ruff formatting and linting, make test runs the pytest suite with coverage, and make check executes the full formatting/lint/test pipeline. When debugging a single target, run uv run pytest tests/test_api.py -vv.
Coding Style & Naming Conventions
Target Python 3.12, four-space indentation, and the Ruff defaults configured in pyproject.toml (line length 100, double-quoted strings). Keep modules and functions snake_case, classes PascalCase, and constants upper snake_case. Add type hints everywhere—mypy runs in strict mode—plus concise docstrings for public entry points such as new MCP tools.
Testing Guidelines
Write unit tests alongside new functionality under tests/ using the test_*.py pattern. Prefer pytest fixtures for external dependencies and async tests (pytest-asyncio is already configured). Maintain coverage by running make test or uv run pytest --cov=src --cov-report=term-missing; regenerate local HTML reports via pytest --cov --cov-report=html and inspect htmlcov/index.html before cleanup.
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 · 20 lines · 619 tokens per session scan A b03340cec025
ghost-mcp AGENTS.md is an instructions file published in the GitHub repository philipithomas/ghost-mcp (1 stars, last pushed 6mo ago), licensed MIT. It adds 619 tokens to every session, about $0.0031 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
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.
rosetta AGENTS.md
Instructions for tikoci/rosetta, covering codex instructions for rosetta, first reads, development defaults and mcp and client config.
pharo-smalltalk-interop-mcp-server CLAUDE.md
Instructions for mumez/pharo-smalltalk-interop-mcp-server, covering claude.md, project overview, development setup, environment variables and common commands.