Proposal: TASKS.md as a companion standard for agent task queues
まだ誰も着手していません。
評価
- 難易度
- 3/5
- 見積もり時間
- 1〜2日
- 初心者へのやさしさ
- 55/100
- issue の種類
- ドキュメント
- 明瞭さ
- おおむね明確
- 活発さ
- 静か
- 技術スタック
- markdown
調査の方向性
Start with the repository documentation or website entry point mentioned in the proposal, then read issue #71 and the linked TASKS.md specification to compare the conventions. Done means adding an appropriate companion-standard reference, if the project agrees on the scope and placement, with the documentation still rendering correctly.
索引モデルが issue の本文から書いたものです。
説明
Summary
AGENTS.md tells agents how to work. I've built TASKS.md to tell them what to work on — a lightweight, Markdown-based task queue spec that any agent can read and write.
This is related to #71 (.agent directory proposal), which includes a tasks.md file inside .agent/spec/. I think task queues deserve a top-level, standalone standard that works alongside AGENTS.md, just like AGENTS.md works alongside README.md.
The Core Idea
You think faster than agents can code. Ideas come in bursts — while an agent implements one feature, you've already thought of three more. Without a queue, those ideas live in your head or scatter across chat windows. TASKS.md is your buffer: write tasks down as they come, and agents work through them at their own pace.
Planning first leads to better results. Writing a task down — even a one-liner — forces you to think about what you actually want before the agent starts coding. That small act of planning is the difference between an agent that builds the right thing and one that guesses. TASKS.md makes planning the natural first step, not an afterthought.
What is TASKS.md?
# Tasks
## P0
- [ ] Fix authentication crash on token refresh
- **ID**: auth-fix
- **Details**: JWT refresh returns 500 on expired tokens
- **Files**: `src/auth/refresh.ts`, `src/middleware/auth.ts`
- **Acceptance**: Refresh works, tests pass, regression test added
## P1
- [ ] Add rate limiting to public API endpoints
- **Blocked by**: auth-fix
- [ ] Migrate database queries to prepared statements
## P2
- [ ] Update README with new API endpoints
How it works:
- Plan — Write tasks as ideas come to you
- Delegate — Agent claims a task, implements it
- Remove — Delete when done; history lives in git log
- Repeat — You keep adding, agents keep draining
Key properties:
- Async queue — you add tasks faster than agents complete them; nothing gets lost
- Git-native — version-controlled, next to the code, survives sessions
- Vendor-neutral — works with any agent, any IDE, today
The spec (v1.0) covers priorities (P0–P3), metadata fields (ID, Tags, Details, Files, Acceptance, Blocked by), multi-agent claiming, blocker resolution, sub-tasks, and multi-file discovery for monorepos.
The Ecosystem
- Website — single-page site explaining the convention
- Spec v1.0 — full specification
- 8 examples — web app, CLI, monorepo, multi-agent, Python API, Rust CLI, mobile app, complex tasks
- Agent commands for Claude Code, Codex, Cursor, Gemini CLI, and Windsurf — drop-in
/next-taskcommand - @tasks-md/cli — unified CLI for pick, lint, stats, diff, sync, and install
- tasks-mcp — MCP server with list/pick/claim/unclaim/complete/add tools
- tasks-lint — linter with
--fixmode (completed tasks, tag casing) - @tasks-md/parser — shared parser library for all packages
- CI — validates examples, runs linter, builds and tests all packages on every push/PR (206 tests)
Proposal
I'd love to see AGENTS.md reference TASKS.md as a companion standard — something like a "See also" section in the docs or website. The two specs complement each other naturally:
- AGENTS.md = instructions for agents (how to work)
- TASKS.md = work queue for agents (what to work on)
Happy to discuss format alignment, naming, or any changes that would make this a better fit.
- 主要言語
- TypeScript
- スター
- 24.8k
- フォーク
- 1.9k
- PR マージ指標
- 30日以内にマージされた PR はありません
環境構築
このプロジェクトには開発コンテナ、Dockerfile、コントリビューションガイドがありません。まず README を読み、一般的な手順ははじめてのコントリビューションガイドを参照してください。
はじめの一歩
- issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
- 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
- リポジトリをフォークし、ブランチを切って変更します。
- issue 番号を参照したプルリクエストを送ります。
agentsmd/agents.md のほかの issue
-
難易度 1/5 1時間未満 初心者へのやさしさ 75/100
-
openai/codex & PlutoLang/Pluto removed AGENTS.md再び着手できるかも @vincedprime が 36 日前に担当しましたが、オープン中のプルリクエストはありません。 オープン
難易度 1/5 1時間未満 初心者へのやさしさ 78/100
-
難易度 2/5 1〜3時間 初心者へのやさしさ 72/100
-
難易度 2/5 1〜3時間 初心者へのやさしさ 68/100
-
難易度 1/5 1時間未満 初心者へのやさしさ 68/100
agentsmd/agents.md の issue をすべて見る
似ている issue
-
idea-scout idea:453
難易度 2/5 1〜3時間 初心者へのやさしさ 83/100
jeanibarz/agent-notebook#453 ·
メンテナーはふだん 1 日以内に返信
-
level/task
難易度 1/5 1時間未満 初心者へのやさしさ 95/100
wazuh/wazuh-dashboard-plugins#9642 ·
メンテナーはふだん 1 日以内に返信
-
bug
難易度 2/5 1〜3時間 初心者へのやさしさ 91/100
unicef/adt-studio#1112 ·
メンテナーはふだん 2 日以内に返信
-
feature request good first issue
難易度 2/5 1〜3時間 初心者へのやさしさ 88/100
TabularisDB/tabularis#1513 ·
メンテナーはふだん 2 日以内に返信
-
Autocomplete still accepts an option after becoming disabled対応中かも @Xapollon430 が今日担当しました。 オープン
難易度 2/5 1〜3時間 初心者へのやさしさ 67/100
メンテナーはふだん 1 日以内に返信