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 skills/chachamaru127/codex-harness/ultraworknpx skills add Chachamaru127/codex-harness --skill ultraworkgit clone --depth 1 https://github.com/Chachamaru127/codex-harnessWrote 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/skills/chachamaru127/codex-harness/ultrawork)<a href="https://agentmods.dev/skills/chachamaru127/codex-harness/ultrawork"><img src="https://agentmods.dev/badge/skills/chachamaru127/codex-harness/ultrawork.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 | $0.00066 | $0.01175 |
| Opus 5 | $0.00033 | $0.00588 |
| Sonnet 5 | $0.00013 | $0.00235 |
| Haiku 4.5 | $0.00007 | $0.00118 |
Grade A, and why
ultrawork 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 5d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ultrawork Skill
Plans.md の指定範囲を完了まで自動的に反復実行する。
/work の長期版として、Ralph Loop + Ultrawork のコンセプトを採用。
Philosophy
「人間介入は失敗シグナル」
システムが正しく設計されていれば、ユーザーが介入する必要はない。 反復 > 完璧性。失敗はデータ。粘り強さが勝つ。
Quick Reference
# 自然言語で範囲を指定
/ultrawork 認証機能からユーザー管理まで完了して
/ultrawork ログイン機能を終わらせて
/ultrawork Header, Footer, Sidebar を作って
# シンプルに全部
/ultrawork 全部やって
/ultrawork Plans.md 完了まで
# 前回の続きから
/ultrawork 続きやって
/work との違い
| 特徴 | /work | /ultrawork |
|---|---|---|
| 実行範囲 | cc:TODO / pm:requested | 指定範囲の全タスク |
| 反復 | 1回 | 完了まで自動反復 |
| 完了条件 | タスク実装完了 | 全タスク + ビルド + テスト + Review |
| 自己学習 | なし | 前回の失敗から学習 |
| 用途 | 1-2タスク | 大規模な実装を放置実行 |
Feature Details
| Feature | Reference |
|---|---|
| Execution Flow | See references/execution-flow.md |
| Self-Learning | See references/self-learning.md |
| Security & Guards | See references/security-guards.md |
| Session State | See references/session-state.md |
| Codex Mode (Experimental) | See references/codex-mode.md |
--codex モード時の役割分担
--codex フラグ使用時、Claude と Codex Worker の役割は明確に分離されます。
| 操作 | Claude (PM) | Codex Worker |
|---|---|---|
| タスク分析・分割 | ✅ | - |
| 実装（Edit/Write） | ❌ 禁止 | ✅ |
| レビュー・品質チェック | ✅ | - |
| Plans.md マーカー更新 | ✅ | - |
| Worktree 管理 | ✅ | - |
重要: --codex 使用時、Claude の Edit/Write は pretooluse-guard.sh によってブロックされます。
すべての実装は mcp__codex__codex 経由で Codex Worker に委譲してください。
Completion Conditions
以下の全てを満たしたとき完了:
- ✅ 指定範囲の全タスクが
cc:done - ✅ 全体ビルド成功
- ✅ 全テスト通過
- ✅ harness-review で APPROVE
- ✅
review_status === "passed"
VibeCoder Hints
| What You Want | How to Say |
|---|---|
| 全部終わらせて | /ultrawork 全部やって |
| この機能だけ | /ultrawork ログイン機能を完了して |
| ここからここまで | /ultrawork 認証からユーザー管理まで |
| 前回の続きから | /ultrawork 続きやって |
| もっと粘って | 「もっと粘って」「諦めないで」 |
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 95 lines · 66 tokens per session scan A 11501840a661
ultrawork is a skill published in the GitHub repository Chachamaru127/codex-harness (2 stars, last pushed 6mo ago), licensed MIT. It adds 66 tokens to every session and 1,175 once invoked, about $0.0003 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 skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.