Borrowing it
Nothing to install: this file belongs to ahonn/dotfiles. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ahonn/dotfiles/master/.claude/skills/branch/SKILL.mdgit clone --depth 1 https://github.com/ahonn/dotfilesWrote 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/ahonn/dotfiles/branch)<a href="https://agentmods.dev/skills/ahonn/dotfiles/branch"><img src="https://agentmods.dev/badge/skills/ahonn/dotfiles/branch/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/ahonn/dotfiles/branch"><img src="https://agentmods.dev/badge/skills/ahonn/dotfiles/branch.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 | $0.00017 | $0.00483 |
| Opus 5.5 | $0.00007 | $0.00193 |
| Sonnet 5.5 | $0.00003 | $0.00097 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
branch 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 20d 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.
What it actually says
Conventional Branch Names
Branch names use the same type vocabulary as conventional commits:
<type>/<short-kebab-description>
Examples: feat/user-auth, fix/login-crash, refactor/api-client, chore/update-deps.
Rules
- Type — the conventional-commit type the dominant commit on this branch would have:
feat,fix,refactor,perf,docs,test,build,ci,chore,revert. - Description — 2–4 words, kebab-case, specific: what the branch delivers, not how. Lowercase only, no spaces.
- Ticket IDs — if the work has a ticket, put its ID after the type:
feat/lin-123-user-auth. - No agent-branded prefixes — never
codex/...,claude/..., oragent/.... The branch describes the work, not the tool that wrote it. - Base — use the user's requested starting point. Otherwise prefer the up-to-date default branch, except when the task clearly continues current branch work. Inspect repository state before choosing it; preserve uncommitted work.
Procedure
If the user only asks for a branch name, propose the name without changing repository state. Use the creation steps when creating a branch is within the requested work.
- Derive type and description from the requested work (or "$ARGUMENTS" if provided).
- Validate:
git check-ref-format --branch <name>. - Inspect
git status --short --branchand the available refs. Resolve the requested base; if a fresh remote base is needed, fetch that ref and verify it before proceeding. Do not assume the current checkout is the default branch or up to date. - Create with
git switch -c <name> <verified-base>; omit the base only when intentionally branching from current HEAD. If switching would disturb unrelated edits, use an isolated worktree when appropriate or ask for the unresolved starting-point decision. Do not stash, discard, reset, or overwrite work implicitly.
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.
- 20d ago Changed · +3 lines · -47 tokens per session d7435f3bda10
- 1mo ago First seen · 31 lines · 64 tokens per session scan A 22a667d27bc2
branch is a skill published in the GitHub repository ahonn/dotfiles (63 stars, last pushed 6d ago), licensed MIT. It adds 17 tokens to every session and 483 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
scan-commit
Automatically scan the repository for unstaged/untracked changes, group them into logical commits using hunk-level analysis, stage and commit them following Conventional Commits.
smart-commit
Analyze staged changes and split them into multiple logical commits following Conventional Commits.
create-pr
Rebase from the latest origin/main, squash the commits from it, and then create a PR on github with intelligent commit messages based on staged changes.
pr-review
Intelligent PR code review with dynamic agent allocation based on change types. Analyzes PR changes and generates targeted review tasks.
analyze-pr
Analyze a GitHub/GitLab Pull Request by fetching its diff, reading its web description, and generating a comprehensive document. Use when the user provides a PR link and wants to understand what changes the PR introduces, or asks to review/analyze/summarize a pull request.
gen-commit-msg
Generate intelligent commit messages based on staged changes following Conventional Commits format.