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/sei-newbear/xp-harness/git-workflownpx skills add sei-newbear/xp-harness --skill git-workflowgit clone --depth 1 https://github.com/sei-newbear/xp-harnessWhat 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 | $0.00198 | $0.05624 |
| Opus 5 | $0.00099 | $0.02812 |
| Sonnet 5 | $0.00040 | $0.01125 |
| Haiku 4.5 | $0.00020 | $0.00562 |
Grade A, and why
git-workflow 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 2d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Workflow — worktree / branch 運用と Git 操作規律
なぜこの skill があるか
開発タスクの開始から push まで、Git 操作はあらゆる skill の context で発生する。各 skill に Git ルールを重複させると DRY 違反になり、project 固有の override も難しい。
この skill は Git 運用全般のデフォルト動作と override 機構を 1 か所に集約する。各 skill は自分の責務に集中し、Git 操作はこの skill に従う。
中核哲学
- 守備範囲は「確認を取った統合」と
git pushまで: 完了時に user の affirmative な確認を取った上で、main への統合 (ローカル merge) と push まで行う。PR 作成・PR 上の merge は依頼者の責務。あなたが PR を立ててはいけない - worktree 運用を推奨: 新規 task は repo の外に worktree を切って進めると、user が元 repo で並行作業できる (あなたの作業と踏み合わない)。branch のみの軽量運用も同じ軽さで選べる
- 完了時は main へ統合が既定: 開発完了 (テスト含む) → 報告 → 確認 → main へ統合 & worktree / branch 削除 → push の流れ。branch は task の間だけの短命なもので、完了時に main へ戻す。「branch のまま push (PR 運用)」「保留」も選べる
- Project 固有ルールで override 可能: PR 必須運用など、現場ルールが違えば project 固有の instruction が優先
セッション開始時の同期確認
新セッション / /clear 直後 / user の最初の依頼を処理する前に必ず実行:
git fetch origin— 副作用なし、必ず最初に叩く（remote の差分が見えるだけ）git branch --show-current— 現 branchgit status— working treegit log --oneline origin/main..main main..origin/main— 同期差分git worktree list --porcelain— worktree の有無（下記の掃除提案の入力）
git status の "up to date with origin/main" は前回 fetch 時点での比較。fetch しないと古い情報のまま "up to date" を返すので信用できない。fetch を先に叩く理由はそこ。
結果を user に簡潔に共有
確認結果を 1 メッセージにまとめる:
- 現 branch
- remote との同期状況 (N commit ahead / behind / 同期済)
- modified の有無
- untracked のサマリー (件数 + 代表的なファイル名、長ければ "他 N 件")
- worktree があれば件数とパス
使い終わった worktree の掃除提案
git branch --merged main と git worktree list --porcelain を突き合わせ、main に取り込まれ済みの branch を持つ worktree (使い終わったもの) を列挙する。見つかったときだけ AskUserQuestion で削除を提案する:
- 消す対象の worktree (branch 名とパス) を質問文に列挙し、一括削除でよい
- 「worktree のみ消す / branch も一緒に消す (
git branch -d)」の選択を含める - 「作業中の別セッションがいないか」を user に問わない (user にも判断材料がない)。安全は機械的装置で担保する: main 取り込み済みしか提案しない (消しても成果は失われない) / 未コミット変更があれば
git worktree remove自体が拒否する (拒否されたら force せず報告) / 万一中にセッションが居ても worktree から抜ける操作で復旧できる - squash merge された branch は「取り込まれ済み」と検出できない。その worktree は提案されず残るだけ (user の手動削除で補う)
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.
- 2d ago First seen · 265 lines · 198 tokens per session scan A 11d8628fa25f
git-workflow is a skill published in the GitHub repository sei-newbear/xp-harness (9 stars, last pushed 25d ago), licensed MIT. It adds 198 tokens to every session and 5,624 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.