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 kopp0510/claude-dd --skill worktree-managergit clone --depth 1 https://github.com/kopp0510/claude-ddWrote 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/kopp0510/claude-dd/worktree-manager)<a href="https://agentmods.dev/skills/kopp0510/claude-dd/worktree-manager"><img src="https://agentmods.dev/badge/skills/kopp0510/claude-dd/worktree-manager/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/kopp0510/claude-dd/worktree-manager"><img src="https://agentmods.dev/badge/skills/kopp0510/claude-dd/worktree-manager.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 | $0.00051 | $0.01403 |
| Opus 5.5 | $0.00020 | $0.00561 |
| Sonnet 5.5 | $0.00010 | $0.00281 |
| Haiku 4.5 | $0.00005 | $0.00140 |
Grade A, and why
worktree-manager 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 yesterday.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Worktree Manager
原生優先（Claude Code ≥ 2.1.198）：原生
EnterWorktree工具、CLI--worktree與 subagentisolation: worktree已涵蓋建立、會話遷移與自動清理 — 先用原生。 本 skill 只處理原生不覆蓋的場景：自訂位置慣例、依賴安裝與基線測試、舊版 Claude Code。
收尾第 1 步借鑑 michael-denyer/pstack-claude 的 worktree-cleanup playbook（被 ignore 的 .env 算「刪了就沒了」）。
建立流程
- 前置檢查：確認在 git repo 內、
git status --porcelain乾淨（有未提交變更先提示處理）、git worktree list無同名衝突 - 確認設定（AskUserQuestion 一次問完）：分支名（建議
feature/<name>前綴）、 位置（慣例：主 repo 平行目錄../<project>-worktree-<branch>）、是否裝依賴 - 建立：
git worktree add -b <branch> <path> <base-branch> - 環境設定：裝依賴（npm/pip 等，依專案）、複製
.env.example→.env（如存在） - 基線測試：跑既有測試記錄基線 — 失敗時警告但不阻止建立（帶著已知紅燈開發， 之後才分得清是誰弄壞的）
- 記錄：在 worktree 根寫
WORKTREE_INFO.md（分支、base、路徑、基線結果）
收尾
開發完成後：
- 先看 worktree 裡還剩什麼：
git -C <path> status --porcelain --ignored，每一行照下面的規則處理過再往下 （git 2.42.0 與 2.54.0 實測，2026-10-19）。!!那幾行處理完還是會留在輸出裡，這是正常的：M、A這類（還沒 commit 的變更）與??（沒追蹤的檔）：git worktree remove會拒絕 （「包含修改或未追蹤的檔案，使用 --force 刪除」，英文是contains modified or untracked files, use --force to delete it）。 不要直接加--force—— 它會把這些連同下一種一起刪掉!!（被 gitignore 的）：remove 不會拒絕，會跟著整個目錄直接刪掉、不提示。node_modules/這種裝得回來的不用管；要留意的是只有這裡才有的檔，例如步驟 4 複製出來、之後又改過的.env（用cmp -s <path>/.env <path>/.env.example比，只看結束碼：0 是一樣、1 是改過、2 是比不了（例如.env.example不在）， 1 和 2 都列進去問。-s什麼都不印。不要用diff—— 它會把填進去的金鑰印出來。macOS 與 busybox 的cmp實測，2026-10-19）- 上面兩種裡要留的、拿不準的：列出來用 AskUserQuestion 一次問完，不要自己選。
M、??可選 commit、搬到哪、刪掉；!!只給搬到哪、刪掉 —— 被 ignore 的檔多半本來就不該進 git（例如.env）。 步驟 6 寫的WORKTREE_INFO.md每次都會出現在??；它只記這個 worktree 的分支、路徑與基線結果，問的時候可以建議刪掉
- 回主 repo
git worktree remove <path>→git worktree prune
merge 與分支刪除由使用者決定，本 skill 不代決。
限制備忘
- 一個分支只能有一個 worktree；已被 worktree 佔用的分支不能再 checkout
- 子模組專案需特殊處理，先確認再建
- worktree 共用主 repo 的
.gitignore，info/exclude也是共用的 —— 它住在 common dir， 在哪一邊加規則，主 repo 與所有 worktree 都會生效（git 沒有 per-worktree exclude 機制； 實測寫進.git/worktrees/<name>/info/exclude根本不被讀取） - worktree 內不可寫死
.git/info/exclude：worktree 的.git是一個指向 gitdir 的檔案、 不是目錄，照字面路徑寫入必定not a directory失敗（已複現，exit 1）。 要取真實路徑用git rev-parse --path-format=absolute --git-path info/exclude（--path-format需 git ≥ 2.31，見該版 release notes；更早的版本只有git rev-parse --git-path info/exclude，回的是相對路徑）
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.
- yesterday Changed · +17 lines f198d754bd46
- 1mo ago Changed · +7 lines 88e47556d3cb
- 1mo ago First seen · 35 lines · 51 tokens per session scan A 29fc69d73608
worktree-manager is a skill published in the GitHub repository kopp0510/claude-dd (12 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,403 once invoked, about $0.0002 per session on Opus 5.5. 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
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…