Borrowing it
Nothing to install: this file belongs to jamiew/monarch-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jamiew/monarch-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/jamiew/monarch-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/jamiew/monarch-mcp/claude-md)<a href="https://agentmods.dev/instructions/jamiew/monarch-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jamiew/monarch-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/jamiew/monarch-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jamiew/monarch-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.04270 | $0.04270 |
| Opus 5.5 | $0.01708 | $0.01708 |
| Sonnet 5.5 | $0.00854 | $0.00854 |
| Haiku 4.5 | $0.00427 | $0.00427 |
Grade B, and why
monarch-mcp CLAUDE.md scanned grade B with 1 finding 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
Do not read or commit credentials, `.env`, saved sessions, or financial logs. The tracked `.mcp.json` loads credentials from `.env` when it exists; keep secrets out of it. Logs can contain tool arguments and API error de How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository guidance
Financial data and secrets
Never put real financial data in code, tests, docs, or commits. This includes account and merchant names from a user's history, transaction/category/account IDs, amounts, and spending patterns. Use synthetic examples such as Corner Deli, cat_001, and txn_123. A generic brand example is fine; data copied from an account is not.
Do not read or commit credentials, .env, saved sessions, or financial logs. The tracked .mcp.json loads credentials from .env when it exists; keep secrets out of it. Logs can contain tool arguments and API error details. Review and redact them before sharing.
Development
Use Python 3.10+ and uv. Dependency constraints live in pyproject.toml; commit uv.lock for reproducible source installs.
uv sync --locked
uv run python server.py
uv run python scripts/ci.py
The CI script runs ruff lint/format checks, mypy, and pytest. Individual checks:
uv run ruff check .
uv run ruff format --check .
uv run mypy server.py
uv run pytest tests/ -v --tb=short
Use uv run ruff format . to format and uv add / uv remove to change dependencies. CI selects Python 3.10 through 3.15 explicitly and uses locked installs.
.mcp.json is the headless dev entry (claude -p --mcp-config .mcp.json --strict-mcp-config). It runs this checkout from any directory and starts without .env. tests/test_stdio.py::test_mcp_json_launches_checkout launches it in both protocol eras.
Live integration tests are opt-in and never load .env or saved sessions themselves:
MONARCH_RUN_INTEGRATION=true uv run --env-file .env pytest tests/test_integration.py -v
That command contacts Monarch. Ordinary tests use synthetic data and skip live calls. scripts/health_check.py is a separate live diagnostic. Run it with uv run --env-file .env; it uses the client's session defaults.
Workflow
- Follow the user's task before the backlog. Make small changes and reuse existing patterns.
- Validate behavior, types, and formatting before committing.
- Commit only with explicit permission. Keep commits atomic, titles short and plain, and use the configured Git identity with
--no-gpg-sign. - Update this file for architecture changes, milestones, or new findings, not every commit. Put release history in
CHANGELOG.mdand user setup inREADME.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 Changed · +3 lines · +255 tokens per session scan A → B 90b8fed36698
- 7d ago Changed · +7 lines · +904 tokens per session ec93a9ca2d11
- 8d ago Changed · +1 lines · +134 tokens per session 6670fec5ee45
- 1mo ago Changed · +6 lines · +246 tokens per session 7e3d5e7813f3
- 1mo ago Changed · +5 lines · +266 tokens per session c87e1e1dc514
- 1mo ago Changed · -306 lines · -4,219 tokens per session da89f7f091fc
- 2mo ago First seen · 446 lines · 6,684 tokens per session scan A 37c1e7a1036b
monarch-mcp CLAUDE.md is an instructions file published in the GitHub repository jamiew/monarch-mcp (29 stars, last pushed 2d ago), licensed MIT. It adds 4,270 tokens to every session, about $0.0171 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
monarch-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| monarch-mcp CLAUDE.mdjamiew/monarch-mcp | Instructions file | 29 | 2d ago | MIT | B | 4,270 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |