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/makeplane/plane-mcp-server/claude-mdgit clone --depth 1 https://github.com/makeplane/plane-mcp-serverWhat 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 | $0.02250 | $0.02250 |
| Opus 5 | $0.01125 | $0.01125 |
| Sonnet 5 | $0.00450 | $0.00450 |
| Haiku 4.5 | $0.00225 | $0.00225 |
Grade A, and why
plane-mcp-server 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 — 137 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.
Project Overview
Plane MCP Server — a Python-based Model Context Protocol server that exposes Plane's project management API as MCP tools. Built on FastMCP with the official plane-sdk. Supports three transport modes: stdio (local), HTTP (with OAuth or header auth), and SSE (legacy).
Common Commands
# Install dependencies (uses uv)
uv pip install -e ".[dev]"
# Run the server locally (stdio mode)
PLANE_API_KEY=... PLANE_WORKSPACE_SLUG=... python -m plane_mcp stdio
# Run HTTP server
python -m plane_mcp http
# Run all tests
pytest
# Run a single test
pytest tests/test_integration.py::test_full_integration -v
# Run tests with env vars from file
export $(cat .env.test.local | xargs) && pytest tests/ -v
# Format code (line length: 120)
ruff format plane_mcp/
# Lint (rules: E, F, I, UP, B; line length: 120)
ruff check plane_mcp/
Architecture
Entry Point & Transport Modes
plane_mcp/__main__.py parses a positional arg (stdio, http, or sse) and launches the corresponding server:
- stdio: Requires
PLANE_API_KEY+PLANE_WORKSPACE_SLUGenv vars. Runs locally. - http: Starts on port 8211 with two auth endpoints — OAuth (
/oauth/mcp) and header-based PAT (/http/api-key/mcp). - sse: Legacy OAuth-only SSE transport.
Server Factories (server.py)
Three factory functions (get_oauth_mcp, get_header_mcp, get_stdio_mcp) each create a FastMCP instance and configure the appropriate auth provider, then hand it to _configured() for the middleware stack and tools — one place, so a transport cannot be left a middleware behind. OAuth/HTTP modes use Redis for token storage (falls back to in-memory).
Middleware (middleware.py)
Ordered as registered; the earlier one wraps the later:
| Middleware | Does |
|---|---|
PlaneLoggingMiddleware |
structured logging, plus the tool name |
CoerceArguments |
repairs arguments a client encoded as strings, before validation (coercion.py) |
ValidateActionArguments |
refuses a call with no action, and arguments the chosen action does not accept, from the ACTIONS declaration |
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 · 137 lines · 2,250 tokens per session scan A ac3d175f3b6e
plane-mcp-server CLAUDE.md is an instructions file published in the GitHub repository makeplane/plane-mcp-server (300 stars, last pushed 7d ago), licensed MIT. It adds 2,250 tokens to every session, about $0.0112 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 2026-08-30.
Other instructions, from other repositories
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
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).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.