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 agentmods add skills/sleeyax/promptfiles/git-branchnpx skills add sleeyax/promptfiles --skill git-branchgit clone --depth 1 https://github.com/sleeyax/promptfilesWrote 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/sleeyax/promptfiles/git-branch)<a href="https://agentmods.dev/skills/sleeyax/promptfiles/git-branch"><img src="https://agentmods.dev/badge/skills/sleeyax/promptfiles/git-branch.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 | $0.00082 | $0.01174 |
| Opus 5 | $0.00041 | $0.00587 |
| Sonnet 5 | $0.00016 | $0.00235 |
| Haiku 4.5 | $0.00008 | $0.00117 |
Grade A, and why
git-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 4d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Branch
Suggest a branch name for the current work. If on the default branch, create the branch after confirmation. If on a custom branch, offer to rename it or branch off it. Whichever branch gets created, record the base it was cut from.
Hard requirement: never create or rename a branch without an explicit user choice. Use the AskUserQuestion tool when it's available in the session; where it isn't (e.g. Codex), ask in plain text with the same numbered options and stop until the user replies.
Steps
- Detect the default branch with
git symbolic-ref refs/remotes/origin/HEAD(strip therefs/remotes/origin/prefix). Fall back tomainif that fails. - Detect the current branch with
git rev-parse --abbrev-ref HEAD. - Inspect recent branch names to determine the repo's naming style. Use
git for-each-ref --sort=-committerdate --count=20 --format='%(refname:short)' refs/heads refs/remotesand study:- Whether names use a prefix/type convention (e.g.
feat/,fix/,chore/) or are freeform - Separator style (kebab-case, snake_case, slashes)
- Use of ticket/issue references
- Typical length and level of detail
- Whether names use a prefix/type convention (e.g.
- Determine what the branch is about:
- Run
git diff --cachedandgit diffto see changes in progress. - Consider the full conversation context — task, intent, relevant discussion. Use this to write a more meaningful name than the diff alone would produce.
- If there are no changes and no useful conversation context, ask the user what the branch is for before proceeding.
- Run
- Produce up to 3 branch names, ordered from best to worst. If only one is appropriate, suggest just one. Each name should read like the existing branches from step 3 produced it — indistinguishable in style from the repo's history.
- Keep names concise but descriptive
- Match the repo's prefix/separator conventions exactly
- Branch off the right base:
- If on the default branch: the base is the default branch. Run
git fetch originandgit pull --ff-onlyfirst to bring it up to date. Ask which suggested name (if any) to use, with a Custom name option. On confirmation, rungit checkout -b <name>and verify withgit rev-parse --abbrev-ref HEAD. - If on a custom branch: ask what to do, with these options:
- Rename this branch to one of the suggested names — run
git branch -m <new-name>. If the branch tracks a remote, warn the user that the remote branch will need to be updated separately (git push origin -u <new-name>and delete the old remote branch) and ask whether to do that now. - Branch off this one — the current branch is the base (e.g. branching a feature off
develop). Rungit checkout -b <name>and verify withgit rev-parse --abbrev-ref HEAD. - Custom name and Cancel.
- Rename this branch to one of the suggested names — run
- If on the default branch: the base is the default branch. Run
- Record the base so later skills don't have to guess it:
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.
- 4d ago First seen · 52 lines · 82 tokens per session scan A eda5794ab3ca
git-branch is a skill published in the GitHub repository sleeyax/promptfiles (2 stars, last pushed 6d ago), licensed MIT. It adds 82 tokens to every session and 1,174 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…