vibing-worktree-finish

vibing-worktree-finish is a skill for Claude Code from shabaraba/vibing.nvim. It costs 67 tokens per session (301 once invoked), scanned A, original, MIT.

A cleanup guide for removing a Git worktree used by a vibing.nvim chat. It removes the separate working folder without forcing Git to discard uncommitted changes.

In plain words
What is it for?
Cleaning up a finished branch's worktree and safely handling cases where uncommitted changes still exist.
Why use it?
It prevents accidental loss of unfinished work by stopping when Git reports local changes. It also clears the chat's folder setting when removal succeeds.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the vibing-nvim plugin — 12 skills, 1 agent shipped together

Good fit Cleaning up a finished branch's worktree and safely handling cases where uncommitted changes still exist.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shabaraba/vibing.nvim/vibing-worktree-finish
Install

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.

Any agent
npx skills add shabaraba/vibing.nvim --skill vibing-worktree-finish
Clone the repo
git clone --depth 1 https://github.com/shabaraba/vibing.nvim

Made for: Claude Code.

Or install vibing-nvim, the plugin that ships this one along with the rest of its 12 skills, 1 agent.

Wrote 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.

agentmods badge for vibing-worktree-finish

README.md
[![agentmods](https://agentmods.dev/badge/skills/shabaraba/vibing.nvim/vibing-worktree-finish/github.svg)](https://agentmods.dev/skills/shabaraba/vibing.nvim/vibing-worktree-finish)
Your own site
<a href="https://agentmods.dev/skills/shabaraba/vibing.nvim/vibing-worktree-finish"><img src="https://agentmods.dev/badge/skills/shabaraba/vibing.nvim/vibing-worktree-finish/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.

agentmods 80×15 button for vibing-worktree-finish

Your own site · 80×15
<a href="https://agentmods.dev/skills/shabaraba/vibing.nvim/vibing-worktree-finish"><img src="https://agentmods.dev/badge/skills/shabaraba/vibing.nvim/vibing-worktree-finish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 301 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.00301
Opus 5 $0.00034 $0.00151
Sonnet 5 $0.00013 $0.00060
Haiku 4.5 $0.00007 $0.00030

Measured 9d ago against content hash ef0fb22f1feb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

vibing-worktree-finish 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 9d 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.

claude-plugin/skills/vibing-worktree-finish/SKILL.md · 26 lines

What it actually says

vibing-worktree-finish

Git worktrees provide isolated working directories for parallel development. This skill removes one via plain git worktree remove — no bespoke helper script, no metadata file to update beyond this chat's own frontmatter.

Finish — "clean up this worktree"

git worktree remove <path>

Never add --force. If git refuses because of uncommitted changes, that's it protecting the user from losing work — report the exact error and let them decide whether to commit, stash, or discard those changes themselves, rather than retrying with --force on their behalf.

If the removed path was this chat's own working_dir, clear that frontmatter field once removal succeeds (reverting to the main repo root) — leaving it pointed at a now-deleted directory would break the next turn. Follow the vibing-nvim MCP buffer-editing approach described in steps 3-4 of the vibing-worktree-create skill to edit the live buffer rather than the file on disk.

Changes

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.

  1. 9d ago First seen · 26 lines · 67 tokens per session scan A ef0fb22f1feb

Subscribe to this mod's changes

vibing-worktree-finish is a skill published in the GitHub repository shabaraba/vibing.nvim (13 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 301 once invoked, about $0.0003 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.