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 shabaraba/vibing.nvim --skill vibing-worktree-creategit clone --depth 1 https://github.com/shabaraba/vibing.nvimWrote 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/shabaraba/vibing.nvim/vibing-worktree-create)<a href="https://agentmods.dev/skills/shabaraba/vibing.nvim/vibing-worktree-create"><img src="https://agentmods.dev/badge/skills/shabaraba/vibing.nvim/vibing-worktree-create/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/shabaraba/vibing.nvim/vibing-worktree-create"><img src="https://agentmods.dev/badge/skills/shabaraba/vibing.nvim/vibing-worktree-create.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 | $0.00067 | $0.00756 |
| Opus 5.5 | $0.00027 | $0.00302 |
| Sonnet 5.5 | $0.00013 | $0.00151 |
| Haiku 4.5 | $0.00007 | $0.00076 |
Grade A, and why
vibing-worktree-create 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 16d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibing-worktree-create
Git worktrees provide isolated working directories for parallel development. This skill uses
plain git commands and this chat's own frontmatter — no bespoke helper script, no metadata
file. A worktree's existence on disk is its entire state.
Directory convention
Worktrees created for isolated work go under .vibing/worktrees/<branch-name>/ at the git
root — flat, one worktree per directory, nothing else stored alongside it. This convention is
also stated in every vibing.nvim chat's system prompt; follow it so git worktree list stays
predictable for later listing (see the vibing-worktree-list skill).
Create — "split this off into its own worktree"
-
Derive a short, English, lowercase, kebab-case branch name from the task being discussed (e.g. "認証セッションのバグを直したい" →
fix-auth-session-bug). Confirm it with the user if the mapping isn't obvious — a wrong name is annoying to rename later. -
Create the worktree:
git worktree add -b <branch> .vibing/worktrees/<branch>If this fails (branch already checked out elsewhere, etc.), the error is self-explanatory — surface it verbatim rather than retrying blindly with a different name.
-
Give the worktree its own CodeGraph index, if the repository uses one. CodeGraph keeps its index at the repository root, so a tool running inside the worktree is answered from the main checkout — another branch's symbols, and none of the ones changed here. That is wrong information, not merely stale information. Only when the git root has a
.codegraph/directory andcodegraphis onPATH:(cd .vibing/worktrees/<branch> && codegraph init -i)Skip it silently otherwise — a repository that does not use CodeGraph has nothing to index — and surface a failure verbatim rather than retrying. The index lands under
.vibing/worktrees/, which the repository's.vibing/ignore rule already covers, so it adds nothing to the chat's### Modified Files.
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.
- 16d ago Changed · +15 lines 9fa732de2198
- 1mo ago Changed · -5 lines 59f85c4a0df7
- 1mo ago First seen · 50 lines · 67 tokens per session scan A a55fe83adbb3
vibing-worktree-create 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 756 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
nav-pilot
Dispatch a Navigator task doc to Pilot as a labeled GitHub issue. Use when user says "dispatch TASK-XX to Pilot", "hand off to Pilot", "send to Pilot", or "queue for Pilot". One-way handoff (Navigator authors the spec, Pilot executes autonomously).
dex-rollback
Rewind one receipt-backed Dex adoption through the frozen lifecycle service. Use when the user says 'undo the update', 'go back', 'that broke something after updating'. Not for applying an update; use dex-update.
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
security-pipeline
Use when security verification is needed - pre-commit security checks, vulnerability scanning, STRIDE threat analysis. Integrates with /handoff-verify --security and /commit-push-pr. CWE Top 25 based.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
git-ai-archaeology
Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.