commit

A command that stages appropriate Git changes and creates a commit. Git is a tool for tracking changes to source code and other project files.

In plain words
What is it for?
Use it to commit tracked changes and approved untracked files with a conventional commit message. It does not push the commit to a remote repository.
Why use it?
It reduces the risk of accidentally committing ignored or unintended files by checking what can be staged before committing.

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/nguyennguyenit/multiclaude/commit
Clone the repo
git clone --depth 1 https://github.com/nguyennguyenit/MultiClaude

Made for: Claude Code.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 315 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00014 $0.00315
Opus 5 $0.00007 $0.00158
Sonnet 5 $0.00003 $0.00063
Haiku 4.5 $0.00001 $0.00032

Measured 2d ago against content hash b971e8108424, 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 2d 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.md · 32 lines

What it actually says

Context

  • Current git status: !git status
  • Staged changes: !git diff --cached --stat
  • Unstaged changes: !git diff --stat
  • Current branch: !git branch --show-current
  • Recent commits: !git log --oneline -5

Rules

  1. NEVER use git add . or git add -A - these will fail on gitignored files
  2. Only stage files that are NOT gitignored:
    • Modified tracked files: use git add -u (safe, only updates tracked files)
    • New untracked files: check each with git check-ignore -q <path> before adding
  3. For untracked files: Run git status --porcelain | grep '^??' | cut -c4- to list them, then for each file run git check-ignore -q <file> || git add <file>
  4. DO NOT push to remote repository unless explicitly requested

Task

Based on the above context:

  1. Stage modified tracked files with git add -u
  2. For any untracked files, check if gitignored before adding
  3. Create a commit with conventional commit message based on changes
  4. Show final git status to confirm

Use a single message with multiple tool calls where possible.

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. 2d ago First seen · 32 lines · 14 tokens per session scan A b971e8108424

Subscribe to this mod's changes

commit is a command published in the GitHub repository nguyennguyenit/MultiClaude (22 stars, last pushed 21d ago), licensed MIT. It adds 14 tokens to every session and 315 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 2026-08-30.