birre: Command for Claude Code

.github/prompts/commit.prompt.md

commit is a command for Claude Code, GitHub Copilot from boecht/birre. It costs 12 tokens per session (787 once invoked), scanned A, original, Unlicense.

A command that turns staged Git changes into one or more commits. Git commits are saved snapshots of project changes, each normally describing one focused piece of work.

In plain words
What is it for?
Use it to inspect staged changes, group related code, tests, and documentation, and write imperative commit messages.
Why use it?
It reduces back-and-forth when committing and helps keep unrelated changes separate. It also checks the staged diff so unstaged files remain out of scope.

Command for Claude CodeGitHub Copilot

Written for Claude Code and GitHub Copilot: argument-hint in frontmatter, but also a Copilot chat mode or prompt. Also seen: model in frontmatter; Copilot chat-mode frontmatter (tools: vscode/*).

This is boecht/birre's own configuration. It tells Claude Code and GitHub Copilot how to work on birre itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything birre configures →

View source ↗ boecht/birre
Reuse

Borrowing it

Nothing to install: this file belongs to boecht/birre. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/boecht/birre/main/.github/prompts/commit.prompt.md
Clone the repo
git clone --depth 1 https://github.com/boecht/birre

Made for: Claude Code, GitHub Copilot.

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 commit

README.md
[![agentmods](https://agentmods.dev/badge/commands/boecht/birre/commit/github.svg)](https://agentmods.dev/commands/boecht/birre/commit)
Your own site
<a href="https://agentmods.dev/commands/boecht/birre/commit"><img src="https://agentmods.dev/badge/commands/boecht/birre/commit/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 commit

Your own site · 80×15
<a href="https://agentmods.dev/commands/boecht/birre/commit"><img src="https://agentmods.dev/badge/commands/boecht/birre/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 787 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.
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 $0.00012 $0.00787
Opus 5 $0.00006 $0.00394
Sonnet 5 $0.00002 $0.00157
Haiku 4.5 $0.00001 $0.00079

Measured today against content hash d9cf4c08f3e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

commit 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 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.

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.

.github/prompts/commit.prompt.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal

You finalize staged work with minimal back‑and‑forth.

Rules

Treat every invocation as brand new: never reuse prior answers, cached data, or previous command output.

Playbook

Follow this playbook exactly and in order; do every step during this run, even if it feels redundant.

Inspect the staged index

  • Use runCommands to execute the following commands in order during this invocation:
    • git diff --cached --numstat --shortstat && git diff --cached --name-status
    • git diff --cached -U2 --minimal --no-color
  • Do not alter the commands or add any others, use them exactly as given
  • If the commands show nothing staged, report that no commit is needed and stop
  • Read the diff output so you understand what will be committed

Plan logical commit groupings

  • Pair code with its matching tests and docs; split when changes target different features, packages, or directories
  • Auto-split obvious mixes (e.g., feature + tests vs. README tweak, refactor vs. version bump)
  • Keep “one topic per commit”; err on clarity over granularity
  • Treat unstaged files as out of scope

Draft commit messages

  • Subject format: <scope>: <imperative summary> (≤ 50 chars, no trailing period)
  • Scope can be a module/package name or docs(<area>) for documentation-only commits
  • Leave one blank line between subject and body; wrap body text at ~72 chars
  • Skip ticket/issue IDs in the subject; reference them in the body if needed
  • Write in imperative, present tense, focusing on user or maintainer impact

Record and validate commits

  • Create the planned commits; never push
  • Afterwards run git status --short via runCommands. If anything remains staged, loop back to Step 2 to regroup

Report results

  • Output one block per commit using the template below.
  • Do not add introductions, validation summaries, next-step offers, or any other commentary unless a previous step failed. When a failure occurs, report the failure instead of commit details

Read the full file on GitHub · 102 lines

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. today First seen · 102 lines · 12 tokens per session scan A d9cf4c08f3e2

Subscribe to this mod's changes

commit is a command published in the GitHub repository boecht/birre (2 stars, last pushed today), licensed Unlicense. It adds 12 tokens to every session and 787 once invoked, about $0.0001 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 2026-09-08.