commit

Split working changes into multiple logical git commits.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/kavo-labs/kavo/commit
Clone the repo
git clone --depth 1 https://github.com/kavo-labs/kavo

Made for: Claude Code.

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 543 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00008 $0.00543
Opus 5 $0.00004 $0.00271
Sonnet 5 $0.00002 $0.00109
Haiku 4.5 $0.00001 $0.00054

Measured today against content hash daf2c1d7bd83, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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.

.claude/commands/commit.md · 52 lines

What it actually says

You are creating one or more well-scoped git commits from the current working changes.

Context

  • Current status: !git status --short
  • Current branch: !git rev-parse --abbrev-ref HEAD
  • Staged diff stat: !git diff --cached --stat
  • Unstaged diff stat: !git diff --stat
  • Recent commits (for style): !git log --oneline -10

Your task

Split every change in the working tree — staged and unstaged — into cohesive logical commits, grouped by intent rather than by folder, until the tree is clean or only intentionally-excluded files remain.

Message format is Conventional Commits; the type vocabulary is in the conventions skill.

Rules

These are the parts that are specific to this repo, or that differ from what you would otherwise do by default:

  • Stage with explicit pathspecs. git reset to clear the index, then git add <specific files> per group. Never git add -A or git add . — they silently sweep in whatever else is in the tree.
  • Config and tooling go in their own commit, ahead of the code that depends on them, and docs stay separate from implementation unless the two are trivially coupled.
  • Do NOT push, and do NOT amend. This command only ever creates new commits; /pr is what pushes.
  • No co-author trailers unless this repo's recent commits already use them — check git log, do not assume.
  • Keep nested parentheses out of commit messages. release-please parses the whole message and a outer(inner()) code span can defeat its parser (fix commit could not be parsed → the commit is dropped from the changelog). Write metadataFor of relation.target(), not metadataFor(relation.target()).
  • Keep a file whole in its best-fitting commit rather than reaching for patch staging; split a single file across commits only when its changes are genuinely unrelated.
  • Finish by printing each commit (hash + subject) and confirming git status is clean.

$ARGUMENTS

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 · 52 lines · 8 tokens per session scan A daf2c1d7bd83

Subscribe to this mod's changes

commit is a command published in the GitHub repository kavo-labs/kavo (12 stars, last pushed today), licensed Apache-2.0. It adds 8 tokens to every session and 543 once invoked, about $0.0000 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 2026-09-02.