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 git-cleanupgit 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/git-cleanup)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/git-cleanup"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/git-cleanup.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.01064 |
| Opus 5 | $0.00017 | $0.00532 |
| Sonnet 5 | $0.00007 | $0.00213 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade B, and why
git-cleanup scanned grade B 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 today.
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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
5. Present the full categorized list and, for each recommended deletion, the exact quoted command the user must confirm (for example `git branch -d <name>` or `git worktree remove <path>`). Do not execute any command yet How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git cleanup
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user explicitly invokes branch/worktree cleanup for a repository with accumulated local branches or worktrees. |
| Authority | Reversible local: writes only VCS-tracked local branches and clean worktrees; rollback is git reflog and remote refs. No remote mutation. Show the exact set before any deletion. |
| Side effect | Delete confirmed local git branches and clean worktrees only; dirty worktrees and protected branches are refused. |
| Done | Every local branch is categorized or surfaced as unanalyzed, every recommended deletion has evidence, exact quoted commands receive final confirmation, and each command is reported as deleted or failed. |
Inputs
A local git repository path (defaults to the current working directory). No remote credentials, no force-push targets, no protected-branch list beyond the repository's own configuration. The user supplies final confirmation for each deletion command; nothing is deleted without it.
Procedure
- Run
git branch -vvandgit worktree listto enumerate every local branch and worktree. Record the current branch and the default upstream branch as protected; never propose their deletion. Done when: every local branch and worktree is enumerated and the current branch plus default upstream are marked protected. - For each local branch, determine merge status against its upstream and against the current branch: run
git branch --mergedandgit branch --no-merged, thengit log <branch> --not <upstream> --onelineto surface unmerged commits. Categorize each branch asmerged,unmerged-with-evidence, orunanalyzedwhen the upstream is missing or the comparison is ambiguous. Done when: each branch carries one ofmerged,unmerged-with-evidence, orunanalyzedwith its evidence. - For each worktree, run
git -C <path> status --porcelainto classify it ascleanordirty. Mark dirty worktrees as refused for deletion. Done when: every worktree is classifiedcleanordirty. - For every branch or clean worktree recommended for deletion, attach the evidence that justifies it: the merge commit SHA, the empty
git logoutput proving no unique commits, or the worktree's clean status. Branches categorizedunanalyzedare surfaced with their reason and never recommended for deletion. Done when: each recommended deletion has its evidence attached and nounanalyzedbranch is recommended. - Present the full categorized list and, for each recommended deletion, the exact quoted command the user must confirm (for example
git branch -d <name>orgit worktree remove <path>). Do not execute any command yet. Done when: the categorized list and every recommended deletion's exact quoted command are shown, with nothing executed. - Wait for explicit human confirmation of each exact quoted command. Refuse to batch, abbreviate, or infer confirmation. Done when: the user confirms each exact quoted command individually, or declines.
- Execute only the confirmed commands, one at a time, in the order confirmed. After each command, record whether it succeeded (
deleted) or failed, capturing the exact git error message. Done when: each confirmed command ran and is recordeddeletedorfailedwith its git error message.
What ships with it
1 file 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.
- today First seen · 41 lines · 35 tokens per session scan B be988d622243
git-cleanup is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 1,064 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…