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 skills add eaglesakura/agent-skills --skill decompose-fat-pr-to-stacked-prsgit clone --depth 1 https://github.com/eaglesakura/agent-skillsWrote 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/eaglesakura/agent-skills/decompose-fat-pr-to-stacked-prs)<a href="https://agentmods.dev/skills/eaglesakura/agent-skills/decompose-fat-pr-to-stacked-prs"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/decompose-fat-pr-to-stacked-prs/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.
<a href="https://agentmods.dev/skills/eaglesakura/agent-skills/decompose-fat-pr-to-stacked-prs"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/decompose-fat-pr-to-stacked-prs.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00173 | $0.02986 |
| Opus 5 | $0.00086 | $0.01493 |
| Sonnet 5 | $0.00035 | $0.00597 |
| Haiku 4.5 | $0.00017 | $0.00299 |
Grade A, and why
decompose-fat-pr-to-stacked-prs 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 12d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decompose Fat PR to Stacked PRs
既存の巨大な Pull Request(またはその tip ブランチ上の大きな差分)を、ジュニアが追える粒度の PR 群へ再分割し、GitHub 上に公開する。依存がある塊は Stacked PR、独立できる塊は独立 PR にする。
いつ使うか
- ユーザーが本 SKILL を明示的にコールしたとき
- 既存の Pull Request(番号・URL・「この巨大 PR」)の分割・再スタックが指示されたとき
- 「fat PR を Stacked に」「巨大 PR を分解して出し直して」など、既存差分の再分割が論点のとき
いつ使わないか
- まだ PR が無く、作業中差分を初めて小さく切るだけのとき → 方針は
split-pull-request-rule、実行は/split-to-prs - 単純な 1 本 PR の作成・本文更新だけ →
/github.create-pull-request - Stacked PR の日常運用(rebase / sync / merge)だけ →
gh-stackSKILL - 元の巨大 PR を閉じる・本文を直すだけの依頼(本 SKILL は元 PR を変更しない)
役割分担
| 役割 | 担当 |
|---|---|
| 分割粒度・依存・ブランチ名のルール | split-pull-request-rule(必読) |
| 実行時の安全規則(スナップショット、指名ステージ、承認) | /split-to-prs |
| Stacked ブランチ / PR の CLI | gh stack(github/gh-stack。運用詳細は gh-stack SKILL) |
| 各 PR の本文テンプレ・作成手順 | /github.create-pull-request と {assets}/template.md |
| 本 SKILL | 既存 fat PR の調査 → 方針レビュー →(承認後)再分割実行 → 報告 |
開始時に同パッケージの split-pull-request-rule を読み、方針判断の正本とする。
ハードルール
- 元の巨大 PR は触らない: close / edit / comment / base 変更 / force 更新を行わない。クローズはユーザー自身が行う。
- 承認制(既定): ブランチ作成・コミット・push・PR 作成は、分割案の承認後にだけ行う。
- 自律確定の例外: 次のいずれかが文脈上明らかなときだけ、承認待ちを省略して実行してよい。
/loopと組み合わせて本 SKILL が回っている- ユーザーが決定権を移譲した(「任せる」「承認不要で進めて」「自律で確定して」等)
- 破壊的 git は禁止(明示承認なし):
reset --hard、clean -fdx、履歴書き換え、force push、ブランチ削除はしない。 - ステージは指名のみ:
git add ./git add -Aは使わない。含めるパスを明示して stage する。 - 移動前に復旧可能なスナップショットを取る(作業ツリーを変えずに):
SHA=$(git stash create "pre-decompose-fat-pr")
if [ -n "$SHA" ]; then
git update-ref "refs/backup/pre-decompose-fat-pr-$(date +%s)" "$SHA"
fi
- CI のための差分は許容: 各分割 PR が単独で CI Success になるために必要な最小修正(import、fixture、ビルド設定の追随など)は、元 PR に無い変更でも入れてよい。意図しない機能追加はしない。入れた場合は報告で明示する。
前提
gh(推奨 2.90.0 以上)が認証済み- Stacked 用:
gh extension install github/gh-stack - 複数 remote がある場合は
git config remote.pushDefault origin等で push 先を確定する gh stackは非対話で呼ぶ(エージェントがハングしないため):init/add/checkoutにはブランチ名(または PR 番号)を必ず渡すsubmitは--autoを付けるviewは--jsonを付ける- 詳細はインストール済みの
gh-stackSKILL に従う
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.
- 12d ago First seen · 198 lines · 173 tokens per session scan A bbf1749cf35c
decompose-fat-pr-to-stacked-prs is a skill published in the GitHub repository eaglesakura/agent-skills (2 stars, last pushed 6d ago), licensed MIT. It adds 173 tokens to every session and 2,986 once invoked, about $0.0009 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
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…