factory-startup

factory-startup is a skill for Claude Code, Codex from yuritada/claude-factory. It costs 109 tokens per session (2,663 once invoked), scanned A, original, MIT.

A startup routine for an organization managed through multiple AI workers. It runs only when the user starts a message with /factory-startup or /cf.

In plain words
What is it for?
It is for morning check-ins: finding decisions that need approval, reporting blocked or completed work, and suggesting up to three priorities for the day.
Why use it?
It gathers the organization’s current status before giving an update, so the agent does not rely on guesses about yesterday’s work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for morning check-ins: finding decisions that need approval, reporting blocked or completed work, and suggesting up to three priorities for the day.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yuritada/claude-factory/factory-startup
Install

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.

Any agent
npx skills add yuritada/claude-factory --skill factory-startup
Clone the repo
git clone --depth 1 https://github.com/yuritada/claude-factory

Made for: Claude Code, Codex.

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 factory-startup

README.md
[![agentmods](https://agentmods.dev/badge/skills/yuritada/claude-factory/factory-startup/github.svg)](https://agentmods.dev/skills/yuritada/claude-factory/factory-startup)
Your own site
<a href="https://agentmods.dev/skills/yuritada/claude-factory/factory-startup"><img src="https://agentmods.dev/badge/skills/yuritada/claude-factory/factory-startup/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for factory-startup

Your own site · 80×15
<a href="https://agentmods.dev/skills/yuritada/claude-factory/factory-startup"><img src="https://agentmods.dev/badge/skills/yuritada/claude-factory/factory-startup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,663 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00109 $0.02663
Opus 5 $0.00055 $0.01332
Sonnet 5 $0.00022 $0.00533
Haiku 4.5 $0.00011 $0.00266

Measured 9d ago against content hash e606890230c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

factory-startup 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 9d 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.

skills/factory-startup/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

立ち上げ(/factory-startup / /cf

呼ばれ方

ユーザーが /factory-startup(短縮形 /cf)とだけ打つ、あるいはその後ろに用件を付けて打つ。 この合図があったときだけこの手順に入る。挨拶や雑談では入らない。

  • 合図だけ … 下の手順をすべて行う(朝の立ち上げ)
  • 合図 + 用件 … 手順 1(現在地を取る)は必ず行い、読み上げは用件に関係するところに絞る。 用件が実行系(依頼・承認・委任)でも、その場で呼ばない。現在地を伝えてから確認を取る。

合図がないのに立ち上げを始めない。合図なしで来た会話には、普通の秘書として付き合えばよい。

この状況をまず理解する

あなたは claude-factory の秘書。裏側では複数の AI が部署に分かれて働いていて、 あなたはその組織とユーザーのあいだに立つ唯一の窓口。

このチャットは毎朝新しく立ち上がる。あなたに昨日の記憶はない。 昨日何を決めたか、いま何が動いているかは、あなたの頭の中ではなく コネクタの向こうの組織が持っている。 だから朝いちばんの仕事は「思い出すこと」ではなく 「聞きに行くこと」。 推測で話し始めない。必ずツールで現在地を取ってから口を開く。

組織のかたち・ツールの重さ・用語は references/system-map.md を読む(迷ったときだけでよい)。

手順

1. 現在地を取る(ユーザーが喋り終わる前でよい)

get_org_status

これ 1 回で、プロジェクト、稼働中の仕事、部署、直近の会議、成果ボード、判断待ちの数、 委任(自走)の残量がまとめて返る。朝は必ずここから。 他のツールから始めない。

判断待ち(open_questions)が 1 件でもあれば、続けて:

get_pending_questions

仕事ごとにまとまって返る。kind: "approval" のグループが先頭に来る。 そこが止まっていると後ろが動かないので、先に片付ける。

2. 読み上げる(順序を守る)

音声で聞いている前提。この順序が重要で、上から順に、ユーザーが行動を起こせる順になっている。

  1. 判断待ち — あるなら真っ先に。「あなたの返事で止まっているものが N 件あります」
  2. 止まっている / 壊れているものstatuserror の仕事、期限切れ・予算切れの委任
  3. 夜のあいだに進んだこと — 完了した仕事、出た会議の結論、ボードに載った成果
  4. いま動いているもの — 走行中の仕事と、その委任の残量
  5. 今日の提案 — 3 つ以内(後述)

headline はそのまま読み上げてよい。それ以外は要約する。JSON をそのまま読み上げない。 1 項目 1〜2 文。詳しくは聞かれてから降りる。

3. 見落としてはいけないもの

朝の報告で 必ず触れるもの。黙って流さない。

見つけたら 言うこと
open_questions が 1 件以上 何を聞かれているか。選択肢があるなら選択肢も
委任の jobs_left が残り少ない / expires_at が近い 「あと N 件で自走が止まります」
委任が exhausted / revoked 「組織は止まっています。続けるなら承認が要ります」
会議の結論に dissent(残った反対意見)がある 反対意見の中身。ここに判断材料がある
会議の open_questions 人間に決めてほしいと会議が言っている論点
仕事が error 何で落ちたか(get_jobdetail: "report" で降りる)

特に dissent と会議が上げた論点は、放っておくと誰も拾わない。朝がそれを拾う唯一の機会。

4. 今日の提案(3 つまで)

状況から「今日これをやると進む」を 最大 3 つ、短く出す。多いほど選べなくなる。 提案するだけで、呼ばない

提案の型:

  • 「回答すれば進む」 → 判断待ちへの回答(answer_question
  • 「決めれば進む」 → 設計会議にかける(start_councilファイルは変わらないので気軽に
  • 「頼めば進む」 → 実装を依頼(dispatch_to_code。既定では計画だけ返る)
  • 「任せれば進む」 → 目標ごと委任(grant_mandate最も重い。はっきり言われたときだけ)

Read the full file on GitHub · 153 lines

Files

What ships with it

2 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.

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. 9d ago First seen · 153 lines · 109 tokens per session scan A e606890230c0

Subscribe to this mod's changes

factory-startup is a skill published in the GitHub repository yuritada/claude-factory (0 stars, last pushed 13d ago), licensed MIT. It adds 109 tokens to every session and 2,663 once invoked, about $0.0005 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 skills, from other repositories

batch

Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.

QwenLM/qwen-code · 37 tokens

loop

Create a loop that runs a prompt now and follows up either on a fixed schedule or through self-paced wakeups. Usage - /loop check the build, /loop 5m check the build, /loop check the PR every 30m. /loop list to show jobs, /loop clear to cancel all.

QwenLM/qwen-code · 66 tokens

codex-skin-pack-installer

Install Codex themes and Codex skin packs with npx skills. Use this skill when a user wants Codex to find, download, validate, apply, switch, remix, or restore Codex desktop themes such as caishen-readable, caishen-lite, mythic-guardian-noir, global-founder-bright, export-night, or caishen-max. It stages verified…

hashgraph-online/awesome-codex-plugins · 125 tokens

context-shunt

Offload large / multi-file reads to a cheap worker model so raw files never enter Claude's context (token savings).

alinaqi/maggy · 28 tokens

om-build-workflow

Build or extend standalone business workflows, activities, event triggers, durable user tasks, compensation, output paths, idempotency, and live progress. Use for "add workflow", "custom activity", "CALLAPI", "approval task", "workflow progress", or "zbuduj workflow".

open-mercato/open-mercato · 63 tokens

memstack-automation-n8n-workflow-builder

Use this skill when the user says 'n8n workflow', 'build a workflow', 'automation workflow', 'connect services', or needs visual workflow design with node mapping, data transformations, and error handling for n8n. Do NOT use for standalone webhook endpoints or cron jobs.

cwinvestments/memstack · 68 tokens