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 MithunWijayasiri/dotclaude --skill git-worktreegit clone --depth 1 https://github.com/MithunWijayasiri/dotclaudeWrote 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/mithunwijayasiri/dotclaude/git-worktree)<a href="https://agentmods.dev/skills/mithunwijayasiri/dotclaude/git-worktree"><img src="https://agentmods.dev/badge/skills/mithunwijayasiri/dotclaude/git-worktree/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/mithunwijayasiri/dotclaude/git-worktree"><img src="https://agentmods.dev/badge/skills/mithunwijayasiri/dotclaude/git-worktree.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 | $0.00070 | $0.01881 |
| Opus 5.5 | $0.00028 | $0.00752 |
| Sonnet 5.5 | $0.00014 | $0.00376 |
| Haiku 4.5 | $0.00007 | $0.00188 |
Grade A, and why
git-worktree 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 11d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Worktree
Windows + PowerShell only. Worktrees live at <repo>/.claude/worktrees/<name>. Add .claude/worktrees/ to the repo's .gitignore — Claude Code doesn't.
Scripts: scripts/wt-create.ps1, scripts/wt-remove.ps1 (PowerShell 5.1+). Run as powershell -NoProfile -File <skill dir>\scripts\<script>.ps1 .... Below, $SKILL = this skill's directory (e.g. $HOME\.claude\skills\git-worktree).
Commands: create (/git-worktree feature-login), switch (/git-worktree switch), remove (/git-worktree remove). Bare /git-worktree → switch.
Hard rules
- Never
npm install/npm ciin a worktree whosenode_modulesis a junction — mutates main repo's deps. Only the drift path (Create step 3,npm cioption) makes a realnode_moduleswhere installing is safe. - Never delete a worktree directory while a
node_modulesjunction is live. Unlink first (Remove step 3) — a recursive delete that follows the junction can eat main'snode_modules. - Removal always user-confirmed. Never automatic, never inferred from "PR raised" or "work done".
- Copy
.env, never link it. A link → worktree edit silently rewrites the real secrets file.
Create
1. Guard. Record MAIN = git rev-parse --show-toplevel first — after entering, cwd is the worktree and this resolves differently.
powershell -NoProfile -File "$SKILL\scripts\wt-create.ps1" -Main "$MAIN"
Exit 1 → already inside .claude/worktrees/; worktrees don't nest. Tell user to /git-worktree remove or exit first.
2. Enter. EnterWorktree(name: "<name>") → creates .claude/worktrees/<name> on a new branch, switches session cwd. Set WT = returned path. Report the branch name from the result.
Base ref = worktree.baseRef setting: fresh (default) branches from origin/<default-branch>, head from current local HEAD. Don't change it. User wants to stack on unpushed local work → worktree.baseRef must be head in settings first; don't flip it silently.
3. node_modules + .env (one script):
What ships with it
2 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.
- 11d ago First seen · 118 lines · 70 tokens per session scan A 87e1114f39a9
git-worktree is a skill published in the GitHub repository MithunWijayasiri/dotclaude (4 stars, last pushed 6d ago), licensed MIT. It adds 70 tokens to every session and 1,881 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 2026-10-09.
Other skills, from other repositories
dockerized-service-release-deployment-workflow
Create a Dockerized-service release contract with clean GitHub Actions builds, main-anchored tags, immutable digest manifests, published-release deployments, production approval, health checks, and exact-digest rollback.
coordinate-worktrees-and-threads
Assign worktree, branch, write, validation, integration, and cleanup ownership before parallel repository work. Use when a worker will inspect or modify repository state outside the coordinator's worktree.
opencode-github
This skill covers OpenCode's GitHub integration, enabling you to use OpenCode directly within GitHub issues and pull requests. OpenCode integrates with your GitHub workflow — mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub Actions runner.
release-prep
Checks that the current branch is ready for a release-please release PR — conventional commit types, version manifest sync, findings-store state, and CI status. Use when preparing or verifying a release, cutting a release PR, or confirming a branch is safe to merge for release.
datalad
Retrieves, versions, and publishes scientific datasets with DataLad and git-annex, and captures computational provenance with datalad run, rerun, and containers-run. Use when cloning or fetching data from OpenNeuro, DANDI, datasets.datalad.org, or any DataLad dataset; when a file in a dataset reads as a broken symlink…
git-workflow
A guide for handling Git repository work safely, including status checks, branches, commits, pushes, pull requests, and rebasing. Git is a version-control system that records code changes and coordinates work between developers.