What is omnifocus-mcp CLAUDE.md?

Claude Code instructions are project guidance for working on kip-d/omnifocus-mcp, including its user guidance, development process, and API design. They also refer to TDD, which means writing tests before or alongside the code they check.

Use them when changing the unified API, handling its two schema formats, interpreting OmniFocus requests, or following the project's clarification, debugging, and testing rules.

They help an agent resolve requests consistently, reuse existing patterns, debug through the right interface, and verify work before finishing.

How kip-d/omnifocus-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kip-d/omnifocus-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.

Copy the file

curl -O https://raw.githubusercontent.com/kip-d/omnifocus-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kip-d/omnifocus-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kip-d/omnifocus-mcp/claude-md.svg)](https://agentmods.dev/instructions/kip-d/omnifocus-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/kip-d/omnifocus-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kip-d/omnifocus-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 3,940 This file is loaded in full into every session.

When invoked 3,940 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.

Model	Per session	Once invoked
Fable 5.1	$0.03940	$0.03940
Opus 5	$0.01970	$0.01970
Sonnet 5	$0.00788	$0.00788
Haiku 4.5	$0.00394	$0.00394

Measured 7d ago against content hash 9b6ed067b0d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

omnifocus-mcp 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 7d 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.

CLAUDE.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Essential Guide for Claude Code

🧠 User-Facing Guidance

For intent interpretation, GTD methodology, date conversion, and result interpretation, see docs/skills/omnifocus-assistant/SKILL.md (installed as a user-level Claude Code skill via symlink). This CLAUDE.md focuses on developer implementation details.

🔄 Process Rules

(Extracted 2026-07-14 from the retired CLAUDE-PROCESSES.dot — transcript audit showed the DOT was never read in-session; prose here is the delivery mechanism that works. TDD (superpowers:test-driven-development), debugging discipline including the stuck→escalate-after-third-failed-attempt protocol (superpowers:systematic-debugging), and pre-completion verification (superpowers:verification-before-completion) arrive via those skills — not restated here.)

Ambiguous request? Ask targeted clarifying questions before acting — don't guess at intent.
Before writing code: grep src/omnifocus/scripts/shared/ for an existing pattern; read any match completely before reinventing. Symptom-driven work starts at docs/dev/PATTERNS.md.
Debugging is MCP-first: when a tool returns wrong data, do NOT open the generated script. Test the tool call at the MCP seam first (via MCPTestClient — see tests/; a raw echo | node dist/index.js pipe drops the last in-flight response). If the script output is correct, the bug is in the wrapper/tool layer.
Public field/operation changes walk the Vertical Contract Matrix below — every layer done or explicitly N/A.
Measure before optimizing; bulk operations are NOT the same as multiple single queries — check how the batch route actually lowers before assuming equivalence.
Before declaring a task complete: npm run build, npm run lint (--max-warnings=0 — warnings fail), npm run format:check, and npm run test:unit pass locally — format:check covers **/*.{ts,js,json,md}, so it is the ONLY one of these that sees markdown and JSON (lint is eslint over src/ alone); a docs-only change can pass every other check here and still fail CI without it. npm run ci:local runs the whole set; grep -rn 'console\.log' src/ shows no hits beyond the known --help printer in src/utils/cli.ts (runs and exits before stdio mode) — ESLint's no-console is deliberately off here, and a stray console.log on a stdio MCP server corrupts JSON-RPC framing for every client (console.error/console.warn write to stderr and are safe); TODO comments you touched still reflect reality. Features additionally need integration tests before they're considered complete (long-running — see tests/integration/PERFORMANCE.md; run in the background, never inside fleet builds).
Changes spanning >10 files: STOP and get explicit approval of the blast radius before proceeding.

Read the full file on GitHub · 300 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.

7d ago First seen · 300 lines · 3,940 tokens per session scan A 9b6ed067b0d9

Subscribe to this mod's changes

omnifocus-mcp CLAUDE.md is an instructions file published in the GitHub repository kip-d/omnifocus-mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 3,940 tokens to every session, about $0.0197 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.

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 · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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 · 6,785 tokens

omnifocus-mcp: Instructions file for Claude Code