Omnifocus-Agent-MCP: Instructions file for Codex

AGENTS.md

Omnifocus-Agent-MCP AGENTS.md is an instructions file for Codex, OpenCode from GlassyWorld/Omnifocus-Agent-MCP. It costs 1,409 tokens per session, scanned A, original, MIT.

Repository instructions for an OmniFocus integration that lets an AI agent work with tasks and projects through a controlled server. OmniFocus is a task-management app for Apple devices.

In plain words
What is it for?
Use them when changing tools, resources, profiles, or domain logic in the server. They require reading project-status and source-map documents first and validating affected registrations and tests.
Why use it?
They define which changes are allowed, which documents show the real current state, and which safety checks must protect user data.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex.

This is GlassyWorld/Omnifocus-Agent-MCP's own configuration. It tells Codex and OpenCode how to work on Omnifocus-Agent-MCP 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 Omnifocus-Agent-MCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to GlassyWorld/Omnifocus-Agent-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/GlassyWorld/Omnifocus-Agent-MCP/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/GlassyWorld/Omnifocus-Agent-MCP

Made for: Codex, OpenCode.

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 Omnifocus-Agent-MCP AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/glassyworld/omnifocus-agent-mcp/agents-md.svg)](https://agentmods.dev/instructions/glassyworld/omnifocus-agent-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/glassyworld/omnifocus-agent-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/glassyworld/omnifocus-agent-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,409 This file is loaded in full into every session.
When invoked 1,409 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 $0.01409 $0.01409
Opus 5 $0.00705 $0.00705
Sonnet 5 $0.00282 $0.00282
Haiku 4.5 $0.00141 $0.00141

Measured 7d ago against content hash d9578875098f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Omnifocus-Agent-MCP AGENTS.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.

AGENTS.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

本文件用于指导 Codex / AI coding agent 在本仓库中工作。

本仓库是一个 safety-controlled OmniFocus MCP Server。任何修改都必须优先保持:

  • 受控 mutation
  • 显式用户授权
  • Domain correctness
  • 可验证行为
  • fail-closed 安全边界

先读文件

开始修改前,先阅读:

  • docs/PROJECT_STATUS.md
  • docs/SOURCE_MAP.md

如果涉及具体功能,再阅读对应 ADR、设计文档和测试。

语言与沟通

默认使用中文进行对话、工作更新、审计结论和面向维护者的说明。代码标识符、命令、错误码、外部英文原文或已有英文规范可保持原文;用户明确要求英文时再切换。

真实状态判断

遵循 docs/SOURCE_MAP.md 中定义的真实状态判断顺序。

不要把旧 Phase 文档中的限制直接理解为当前能力。旧文档可能描述的是当时阶段边界,而不是当前生产状态。

当前生产边界

personal-production 是当前生产 Profile。当前生产 MCP surface 以 docs/PROJECT_STATUS.md 和注册测试为准。

稳定约束:

  • personal-production 不暴露 Resources。
  • create_taskcreate_project_skeleton 是当前允许进入 personal-production 的受控 mutation capabilities;两者均受各自 schema、feature gate、Ledger、lock 与 verification 约束。
  • upstream-full 是更宽的兼容 surface,不代表生产默认能力。
  • 不得从已有 primitive、legacy Tool 或 upstream-full 能力推断可以进入 personal-production

涉及 Tool / Resource / Profile 变化时,必须检查:

  • src/serverRegistration.ts
  • src/serverRegistration.test.ts

架构边界

保持 Domain-first 架构:

Raw Query
-> Strict Adapter
-> Domain Semantics
-> Mapper / Composer
-> MCP Tool

规则:

  • MCP handler 不承载核心业务语义。
  • 不绕过 Adapter、Domain schema、Mapper、Composer 或 verifier。
  • 不因为 Tool 输出缺字段而直接暴露 generic raw query。
  • direct / effective / source 语义必须保持可测试。
  • Domain 层表达事实,不写入 AI recommendation、priority、risk 或 health 判断。

Change Scope

默认保持小范围修改,优先解决当前目标问题,并沿用现有架构边界。

未经明确要求,不进行:

  • 大规模重构
  • 目录重组
  • API 统一
  • 抽象层合并
  • 将相邻但未授权的能力顺手纳入本次改动

如果发现更大的结构问题,先记录和说明,不要把它混入当前任务。

Mutation 安全边界

不要把分析、建议、计划、推断或未来意图转换为 mutation。

任何新增或扩展 mutation 能力,必须先有明确设计评审,并满足:

  • 显式用户授权
  • 有限 mutation set
  • preview / confirmation 或等价的目标绑定证据
  • auditability
  • fail-closed 行为
  • 幂等 / replay / duplicate protection
  • 写后 verification
  • 清晰的 mayHaveWritten / retrySafe 语义

未经明确设计批准,禁止:

  • generic CRUD framework
  • generic mutation executor
  • name/path mutation resolver
  • fuzzy matching
  • fallback 到 Inbox / Project
  • 自动创建 Tag
  • 静默省略用户要求的 Tag
  • edit / move / reparent / complete / delete existing task
  • batch CRUD
  • repeat / notifications

Read the full file on GitHub · 193 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. 7d ago First seen · 193 lines · 1,409 tokens per session scan A d9578875098f

Subscribe to this mod's changes

Omnifocus-Agent-MCP AGENTS.md is an instructions file published in the GitHub repository GlassyWorld/Omnifocus-Agent-MCP (0 stars, last pushed 29d ago), licensed MIT. It adds 1,409 tokens to every session, about $0.0070 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.

Related

Other instructions, from other repositories

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

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

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 · 4,469 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens