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 OutlineDriven/odin-claude-plugin --skill worktreegit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/worktree)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/worktree"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/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/outlinedriven/odin-claude-plugin/worktree"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/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 | $0.00073 | $0.04094 |
| Opus 5.5 | $0.00029 | $0.01638 |
| Sonnet 5.5 | $0.00015 | $0.00819 |
| Haiku 4.5 | $0.00007 | $0.00409 |
Grade C, and why
worktree scanned grade C with 1 finding 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
f. Reconcile: list git worktrees with `git worktree list --porcelain` and compare paths under `.loop-worktrees/` against the manifest. Worktrees registered with git but missing from the manifest are orphans: report them, How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Worktree isolation
Contract
| Field | Bound contract |
|---|---|
| Trigger | A new isolated worktree or branch is requested, an existing ref or PR needs isolation, feature work needs a gated workspace with setup and baseline tests (feature-gate mode), a run needs a manifest-tracked worktree (loop-run mode), or a candidate patch must be captured from an ephemeral worktree without touching the current checkout (capture-isolated-patch mode). |
| Authority | Reversible local: writes only the worktree directory, .worktrees/ or .loop-worktrees/ entries, a gitignore entry, symlinked hooks, manifest bookkeeping, or (capture-isolated-patch mode) a fresh temporary worktree and binary-safe patch under its parent temporary directory; rollback is removing the worktree and reverting those entries. Capture-isolated-patch mode never writes the original checkout. Loop-run mode never passes --force to git worktree remove. No remote mutation. |
| Side effect | Local write: creates or attaches an isolated git worktree and reports its exact path and status. Feature-gate mode also runs setup and the baseline test suite. Loop-run mode also maintains a status manifest under .loop-worktrees/. Capture-isolated-patch mode runs the command in an ephemeral worktree, captures stdout/stderr/exit code, and writes and returns a binary-safe patch file path or preserves the worktree on extraction failure. |
| Done | new-work and isolate-existing-ref modes have an isolated workspace the harness can see and manage, with no phantom state. feature-gate adds a green baseline suite or surfaces a failure. loop-run adds a manifest where every worktree has a legal status and no removal used --force. capture-isolated-patch writes and returns a binary-safe patch file path and command results, removes its temporary worktree after successful extraction, or preserves it and reports extraction failure; the original checkout is unchanged either way. |
Inputs
- Mode (required): one of
new-work,isolate-existing-ref,feature-gate,loop-run,capture-isolated-patch. Defaultnew-workwhen no ref is named and no gate, lifecycle, or patch capture is requested. - Ref to isolate (
isolate-existing-refonly): a PR head, branch, or commit. - New branch name (optional): derived from the work description when omitted.
- Base branch (optional): defaults to origin's default branch, else
main. - Setup command (
feature-gate, optional): project setup to run inside the worktree, for examplepnpm install --frozen-lockfile. When omitted, no setup step runs. runId(loop-run, required): unique run identifier used verbatim as a path segment and branch suffix; a single path segment (no/, not.or..).pattern(loop-run, required at create): short work-pattern label kept on the manifest entry for audit.- Status for mark (
loop-run, required): exactly one ofactive,rejected,escalated,merged,stale. - Cleanup set (
loop-run, optional): status CSV, defaultrejected,escalated, plus an optional age cutoff<n>+s|m|h|d(for example24h). - Command (
capture-isolated-patch, required): shell command that produces the candidate change; run it inside the ephemeral worktree with that worktree as its working directory. - Base ref (
capture-isolated-patch, optional): git ref used to create the detached worktree; defaults to the currentHEAD. - Repo path (
capture-isolated-patch, optional): repository path for validation and worktree creation; defaults to the current working directory.
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.
- 1mo ago Changed · +10 lines · +27 tokens per session 5e6eef3c32d5
- 1mo ago Changed · +35 lines · -13 tokens per session scan A → C 6fbf77903531
- 1mo ago First seen · 42 lines · 59 tokens per session scan A f5489f035196
worktree is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (38 stars, last pushed 24d ago), licensed Apache-2.0. It adds 73 tokens to every session and 4,094 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…