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/alleneubank/claude-code/git-worktree-tidynpx skills add alleneubank/claude-code --skill git-worktree-tidygit clone --depth 1 https://github.com/alleneubank/claude-codeWhat 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 | $0.00043 | $0.01222 |
| Opus 5 | $0.00022 | $0.00611 |
| Sonnet 5 | $0.00009 | $0.00244 |
| Haiku 4.5 | $0.00004 | $0.00122 |
Grade A, and why
git-worktree-tidy 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
git-worktree-tidy
Routine hygiene for bare-repo + worktree layouts. Fetches origin, prunes gone branches and orphaned worktrees, and fast-forwards important local branches.
When to use
User asks to "fetch prune", "clean up stale branches/worktrees", or "update main/dev to latest" in a worktree-based repo.
Hard Rules
- All destructive actions (worktree remove, branch delete) require user confirmation. Present the full list and wait.
- Never force-delete a worktree with uncommitted changes without explicit approval. Flag dirty worktrees separately.
- Use
--ff-onlywhen updating branches. If ff-only fails, stop and ask. - Operate from the
.baredirectory (or repo root) for branch/worktree management commands. - Never infer "merged/shipped" from
git rev-list origin/main..<branch>orgit merge-base --is-ancestoralone. Squash- and rebase-merges land the work under a new SHA, so a fully-shipped branch still shows commits "not in main" and a non-ancestor tip. Verify ship status against the forge's PR merge state (step 3a) before classifying a gone branch as unmerged.
Workflow
1) Locate the bare root
Determine the bare repo directory:
- If cwd contains
.bare/, use it - Otherwise:
git rev-parse --git-common-dir
All branch and worktree management commands run from this directory.
2) Fetch + prune
git fetch --prune origin
Report what was pruned (deleted remote-tracking branches, updated refs).
3) Discover stale branches
git branch -vv | grep ': gone]'
Collect branch names whose upstream is gone.
3a) Verify ship status (gone upstream ≠ merged)
A deleted upstream ("gone") does NOT prove the work shipped, and git ancestry is unreliable here: squash- and rebase-merges land the work under a new SHA, so a fully-shipped branch still shows commits "not in main" and a non-ancestor tip. Verify against the forge before deleting — gone-but-unmerged branches are the only ones that lose real work.
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 · 166 lines · 43 tokens per session scan A bc62f67263b8
git-worktree-tidy is a skill published in the GitHub repository alleneubank/claude-code (52 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,222 once invoked, about $0.0002 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 2026-08-30.
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.