carve-harness: Command for Claude Code

.claude/commands/commit-branch.md

commit-branch is a command for Claude Code from claude-code-expert/carve-harness. It costs 19 tokens per session (652 once invoked), scanned A, original, MIT.

A command that creates a commit following Conventional Commits, a shared format for writing commit messages, and pushes it to the current branch.

In plain words
What is it for?
Use it when you want to record and publish the current changes using the Conventional Commits format.
Why use it?
It avoids inconsistent commit messages and combines committing and pushing into one step.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

This is claude-code-expert/carve-harness's own configuration. It tells Claude Code how to work on carve-harness 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 carve-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to claude-code-expert/carve-harness. 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/claude-code-expert/carve-harness/main/.claude/commands/commit-branch.md
Clone the repo
git clone --depth 1 https://github.com/claude-code-expert/carve-harness

Made for: Claude Code.

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-branch

README.md
[![agentmods](https://agentmods.dev/badge/commands/claude-code-expert/carve-harness/commit-branch/github.svg)](https://agentmods.dev/commands/claude-code-expert/carve-harness/commit-branch)
Your own site
<a href="https://agentmods.dev/commands/claude-code-expert/carve-harness/commit-branch"><img src="https://agentmods.dev/badge/commands/claude-code-expert/carve-harness/commit-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.

agentmods 80×15 button for commit-branch

Your own site · 80×15
<a href="https://agentmods.dev/commands/claude-code-expert/carve-harness/commit-branch"><img src="https://agentmods.dev/badge/commands/claude-code-expert/carve-harness/commit-branch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 652 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 $0.00019 $0.00652
Opus 5.5 $0.00008 $0.00261
Sonnet 5.5 $0.00004 $0.00130
Haiku 4.5 $0.00002 $0.00065

Measured 1mo ago against content hash 2b446834721b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

commit-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 1mo 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/commands/commit-branch.md · 28 lines

What it actually says

현재 브랜치의 변경을 Conventional Commits 규칙에 맞춰 커밋하고 원격 같은 브랜치로 푸시한다. $ARGUMENTS가 있으면 메시지 요지로 반영한다.

절차

  1. 브랜치 가드 (필수): git branch --show-current 확인. main·master면 즉시 중단하고 보고 — 기본 브랜치 직접 푸시 금지(feature/develop → PR). 그 외 브랜치만 진행한다.
  2. 변경 확인·스테이징: git status --short·git diff로 검토. 스테이징된 게 없으면 관련 tracked 변경만 git add한다(무관 파일·.DS_Store·.env·시크릿 제외). 어떤 파일을 담는지 1줄 고지.
  3. 메시지 작성: 변경을 요약해 제목 type(scope)?: subject.
    • type ∈ {feat, fix, docs, style, refactor, perf, test, build, ci, chore, revert}
    • 제목은 영어, 50자 이하 권장·72자 하드캡, 마침표 없음, 명령형.
    • "왜"가 자명하지 않으면 -m 본문에 근거를 담는다(여러 변경이면 불릿).
    • $ARGUMENTS가 있으면 그 요지를 제목/본문에 반영한다.
  4. 커밋: git commit. pre-commit(보호경로·하드코딩 시크릿·VERSION↔CHANGELOG)·commit-msg(형식·길이) 게이트가 자동 실행된다.
    • 차단되면 원인을 고치고 재시도한다. --no-verify 우회는 절대 금지.
    • VERSION을 바꿨다면 CHANGELOG에 해당 [X.Y.Z] 항목이 함께 스테이징돼야 통과한다(/version-changelog).
  5. 푸시: git push origin <현재브랜치>. --force·히스토리 재작성 금지.
  6. 보고: 커밋 해시·제목·푸시 결과를 보고한다. 그 브랜치의 열린 PR이 있으면 자동 반영됨을 알린다.

금지

  • main/master 직접 커밋·푸시.
  • push --force, commit --no-verify, 히스토리 재작성(reset --hard·rebase 후 강제 푸시).
  • 무관 파일·시크릿·.env·.DS_Store 스테이징.
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. 1mo ago First seen · 28 lines · 19 tokens per session scan A 2b446834721b

Subscribe to this mod's changes

commit-branch is a command published in the GitHub repository claude-code-expert/carve-harness (15 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 652 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 2026-08-30.