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/koki-develop/todoist-mcp-server/claude-mdgit clone --depth 1 https://github.com/koki-develop/todoist-mcp-serverWrote 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/koki-develop/todoist-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/koki-develop/todoist-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/koki-develop/todoist-mcp-server/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 | $0.03360 | $0.03360 |
| Opus 5 | $0.01680 | $0.01680 |
| Sonnet 5 | $0.00672 | $0.00672 |
| Haiku 4.5 | $0.00336 | $0.00336 |
Grade A, and why
todoist-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 4d 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 — 237 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
This is a Todoist MCP (Model Context Protocol) server built with TypeScript and Bun. The project integrates Todoist with AI assistants like Claude through the MCP standard, allowing AI to interact with Todoist tasks and projects.
Development Commands
# Install dependencies and setup tools
bun install # Install Node.js dependencies
mise install # Install required tool versions (Bun, Node.js, linting tools)
# Build and run
bun run build # Build the MCP server to dist/index.js
bun dist/index.js # Run the built MCP server
# or for development: bun run src/index.ts
# Docker
docker build -t todoist-mcp-server . # Build Docker image
docker run -e TODOIST_API_TOKEN=token todoist-mcp-server # Run in container
# Testing
bun test # Run all tests
bun test src/lib/todoist/client.spec.ts # Run specific test file
# Code quality
bun run lint # Check code with Biome
bun run format # Format and fix code with Biome
bun run typecheck # Run TypeScript type checking
# MCP Server Testing
bun run inspector # Build and launch MCP Inspector for visual testing
bun run preinspector # Build server (runs automatically before inspector)
# GitHub Actions linting (requires mise tools)
actionlint # Lint GitHub Actions workflow files
ghalint run # Check GitHub Actions policies
zizmor . --persona=auditor # Security audit GitHub Actions
# Action version management
pinact run -u # Update GitHub Actions to latest versions
# Development workflow
bun run prepare # Install git hooks (runs automatically on install)
Project Structure
src/ # Source code
├── index.ts # Minimal entry point (delegates to server.ts)
├── server.ts # MCP server initialization and configuration
├── mcp/ # Modular MCP architecture with colocation
│ └── tools/ # Tool handlers with co-located schemas
│ ├── index.ts # registerTools() aggregator
│ ├── projects.ts # Project tools (CRUD + read operations)
│ ├── sections.ts # Section tools (CRUD + read operations)
│ ├── tasks.ts # Task tools (CRUD + close/reopen + read operations)
│ ├── labels.ts # Label tools (create + update + individual/list read + delete operations)
│ ├── comments.ts # Comment tools (separate task/project creation + read with pagination + update/delete)
└── lib/
└── todoist/ # Todoist API client wrapper
├── client.ts # TodoistClient class with CRUD operations
├── types.ts # TypeScript types and interfaces
└── client.spec.ts # Comprehensive test suite
scripts/ # Build and utility scripts
├── build.ts # Bun.build configuration
dist/ # Built output (Bun runtime compatible)
Dockerfile # Multi-stage Docker build with Bun
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.
- 4d ago First seen · 237 lines · 3,360 tokens per session scan A 91655c1e208c
todoist-mcp-server CLAUDE.md is an instructions file published in the GitHub repository koki-develop/todoist-mcp-server (7 stars, last pushed 5mo ago), licensed MIT. It adds 3,360 tokens to every session, about $0.0168 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
todoist-mcp CLAUDE.md
Claude Code instructions for amattas/todoist-mcp, covering claude.md, project overview, quick reference, architecture and main entry points.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
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).
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
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
Claude Code instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.