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 alexei-led/cc-thingz --skill using-git-worktreesgit clone --depth 1 https://github.com/alexei-led/cc-thingzWrote 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/alexei-led/cc-thingz/using-git-worktrees)<a href="https://agentmods.dev/skills/alexei-led/cc-thingz/using-git-worktrees"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/using-git-worktrees/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/alexei-led/cc-thingz/using-git-worktrees"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/using-git-worktrees.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00081 | $0.00728 |
| Opus 5.5 | $0.00032 | $0.00291 |
| Sonnet 5.5 | $0.00016 | $0.00146 |
| Haiku 4.5 | $0.00008 | $0.00073 |
Grade A, and why
using-git-worktrees 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 15d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Worktrees
A worktree gives parallel work its own folder and branch while the main worktree stays clean on the integration branch. Each project gets one sibling root, <project>.worktrees/, with one directory per branch named by its slug (/ → -, so feature/auth → feature-auth). Remove the worktree and branch after the PR merges.
A plain branch switch with no parallel work needs no worktree: check git status --short, then git switch <branch>. Trivial solo one-liners may also stay in the main worktree.
Create
Check git status --short and git worktree list first. Leave uncommitted changes where they are and never stash them silently; pass --allow-dirty only when the user has authorized isolating new work while keeping them.
scripts/setup-worktree.sh <branch> [--base <ref>] [--allow-dirty] [--setup] [--test]
The script runs git worktree add from the main worktree root. It checks out an existing local or origin branch instead of recreating it, and refuses an existing path, a branch checked out in another worktree, or a dirty tree without --allow-dirty. It reports base divergence from local refs without fetching.
--setupdoes a frozen install with the declared package manager and lockfile (uv for Python). Conflicting lockfiles or manager declarations stop it. A setup failure exits non-zero but still prints the path.--testruns the detected baseline tests. Failures only warn.- A skipped setup or test is not a pass.
Clean up one worktree
scripts/cleanup-worktree.sh [branch]
A cleanup request authorizes removal of a clean, verified merged worktree and its branch without another confirmation. The script fetches first and verifies Git ancestry, a merged PR bound to the repository/base/head, or an equivalent squash patch without gh. It preserves new commits and uncommitted files, including ignored files. For an exception, show the exact target, full tip OID, commits and files at risk, then ask once. After consent, recheck the tip and files and run --force <branch> yourself; never require the user to copy and run the command. Main, protected, and locked worktrees remain guarded even with force. For bulk or stale cleanup and command-local hook consent, use cleanup-git. Leave git pull out of cleanup; update the integration worktree separately only when clean and requested.
What ships with it
4 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.
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.
- 15d ago Changed f9e62ffe1ebd
- 20d ago Changed · +3 lines · +23 tokens per session 5e5c663cd6d6
- 22d ago Changed · -57 lines 4b1166b43c85
- 1mo ago Changed · +5 lines 1cf7875eb455
- 1mo ago First seen · 101 lines · 58 tokens per session scan A 695fa96c973a
using-git-worktrees is a skill published in the GitHub repository alexei-led/cc-thingz (38 stars, last pushed 11d ago), licensed MIT. It adds 81 tokens to every session and 728 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
triage
Gatekeep and review GitHub issues and pull requests for Qwen Code maintainers. Use for GitHub Action issue triage, PR admission checks, product-direction review, KISS-focused PR review, and staged bilingual GitHub comments.
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
chained-pr
Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.