MotionMCP: Instructions file for Claude Code

CLAUDE.md

MotionMCP CLAUDE.md is an instructions file for Claude Code from devondragon/MotionMCP. It costs 1,678 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for MotionMCP, a server that lets language models use Motion's task-management API through the Model Context Protocol.

In plain words
What is it for?
They are for building, running unit, integration, and worker tests, checking types, and developing or deploying the Worker.
Why use it?
They provide the commands and test procedures needed to verify changes across the local server and Cloudflare Worker deployment.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is devondragon/MotionMCP's own configuration. It tells Claude Code how to work on MotionMCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MotionMCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to devondragon/MotionMCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/devondragon/MotionMCP/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/devondragon/MotionMCP

Made for: Claude Code.

Wrote 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.

agentmods badge for MotionMCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/devondragon/motionmcp/claude-md/github.svg)](https://agentmods.dev/instructions/devondragon/motionmcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/devondragon/motionmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/devondragon/motionmcp/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.

agentmods 80×15 button for MotionMCP CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/devondragon/motionmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/devondragon/motionmcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,678 This file is loaded in full into every session.
When invoked 1,678 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01678 $0.01678
Opus 5.5 $0.00671 $0.00671
Sonnet 5.5 $0.00336 $0.00336
Haiku 4.5 $0.00168 $0.00168

Measured 29d ago against content hash 6b695a3d920e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

MotionMCP 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 29d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

CLAUDE.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 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.

Motion MCP Server

MCP server bridging Motion's task management API with LLMs via the Model Context Protocol. Supports both local (stdio) and remote (Cloudflare Workers) deployment.

Common Commands

# Build & Run
npm run build              # Compile TypeScript to dist/
npm run mcp                # Start MCP server (compiled)
npm run mcp:dev            # Start MCP server (ts-node, no build needed)
npm run type-check         # Type checking without emitting files

# Testing (vitest)
npm test                   # Run all unit tests (node + worker projects)
npm test -- handlers.task  # Run a single test file by name fragment
npm test -- --reporter=verbose  # Run with verbose output
npm run test:worker        # Worker tests only: auth gate + stateless MCP handler (runs in workerd)
npm run test:integration   # Integration tests (requires MOTION_API_KEY in .env)

# Worker (Cloudflare)
npm run worker:dev             # Local Worker at http://localhost:8787
npm run worker:deploy          # Deploy to Cloudflare
npm run worker:type-check      # Type-check Worker code (separate tsconfig)

# Verify both entry points compile
npm run build && npm run worker:type-check

# Quick startup smoke test
timeout 3s npm run mcp

Releasing (version bump, tag, GitHub release, npm publish, Worker deploy) is documented step by step in DEVELOPER.md under "Releasing".

Testing

Uses vitest. vitest.config.mts defines two projects that both run under npm test:

  • node — unit tests in tests/**/*.spec.ts, 10s timeout, mocked services, tests/setup.ts silences console.error
  • worker — tests/worker/**/*.spec.ts, run inside workerd via @cloudflare/vitest-pool-workers

Integration tests live in tests/integration/**/*.integration.test.ts and use their own config.

  • Integration tests: 60s timeout, sequential execution (rate limits), requires MOTION_API_KEY env var
  • Handler tests mock MotionApiService and WorkspaceResolver; service returns use ListResult<T> shape ({ items, truncation })
  • Worker tests cover src/worker.ts authentication. They must run in workerd, not Node: crypto.subtle.timingSafeEqual is a Workers extension Node does not implement, and the path rewrites depend on Workers Request/URL semantics. Bindings come from wrangler.toml with fake MOTION_API_KEY/MOTION_MCP_SECRET values injected in the config. The auth tests stub mcpTransport.handle so authorized requests are observable; a second block runs unstubbed through the real createMcpHandler (initialize, tools/list, schema rejection, 405 on GET/DELETE) and stops short of any tool call that would reach Motion.
  • The config is .mts because @cloudflare/vitest-pool-workers is ESM-only and the package is CommonJS.

Read the full file on GitHub · 127 lines

Changes

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.

  1. 29d ago Changed · +2 lines · +126 tokens per session 6b695a3d920e
  2. 1mo ago First seen · 125 lines · 1,552 tokens per session scan A f7ddfb982592

Subscribe to this mod's changes

MotionMCP CLAUDE.md is an instructions file published in the GitHub repository devondragon/MotionMCP (30 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,678 tokens to every session, about $0.0067 per session on Opus 5.5. 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,581 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens