commit

commit is a command for Claude Code from walterra/claude-code-helpers. It costs 0 tokens per session (340 once invoked), scanned A, original, Apache-2.0.

A commit command that saves only files already selected for the next Git change. Git is a tool for tracking file history and sharing code changes.

In plain words
What is it for?
It identifies the selected files, creates a short one-line commit message, checks pre-commit errors, and helps fix lint or type-check problems without selecting extra files.
Why use it?
It prevents unrelated files from being included and requires the commit message to accurately describe the staged work.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit It identifies the selected files, creates a short one-line commit message, checks pre-commit errors, and helps fix lint or type-check problems without selecting extra files.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/walterra/claude-code-helpers/commit
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.

Clone the repo
git clone --depth 1 https://github.com/walterra/claude-code-helpers

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/walterra/claude-code-helpers/commit/github.svg)](https://agentmods.dev/commands/walterra/claude-code-helpers/commit)
Your own site
<a href="https://agentmods.dev/commands/walterra/claude-code-helpers/commit"><img src="https://agentmods.dev/badge/commands/walterra/claude-code-helpers/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/walterra/claude-code-helpers/commit"><img src="https://agentmods.dev/badge/commands/walterra/claude-code-helpers/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 340 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 $0.00000 $0.00340
Opus 5.5 $0.00000 $0.00136
Sonnet 5.5 $0.00000 $0.00068
Haiku 4.5 $0.00000 $0.00034

Measured 1mo ago against content hash 739f76ac6b6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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.

commands/commit.md · 17 lines

What it actually says

You are about to commit staged files only.

    1. Identify staged files using git diff --cached --name-only.
    1. git commit -m "<message>" just the currently staged files with a proper one-liner commit message. it must be a one-liner message without any credit information like "generated with" or "co-authored by". 60 max char length. no semantic prefix. IMPORTANT: Analyze the actual changes (use git show --name-status or git diff --cached) to craft an accurate message that describes what was done - don't default to generic verbs like "add" when files were modified or updated.
    1. Check if any pre-commit hooks found issues (for example linting or TS errors).

If pre-commit hooks found issues:

  • 3.1 Use the repos maintenance commands like pnpm lint, pnpm tsc:check or similar to fix formatting, linting or type issues automatically.
  • 3.2 Fix any remaining issues manually.
  • 3.3 If you have to stage files, ONLY stage files you identified in step 1 (identify staged files).
  • 3.4 NEVER stage files that are not part of the list created in step 1 (identify staged files).
  • 3.5 If a maintenance script modified an unstaged file, leave it unstaged
  • 3.6 NEVER use git add . or similar bulk staging commands

Example: If only A.ts was originally staged, but the formatter also modified B.ts (which was unstaged), only stage A.ts for the commit. Leave B.ts unstaged.

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 · 17 lines · 0 tokens per session scan A 739f76ac6b6e

Subscribe to this mod's changes

commit is a command published in the GitHub repository walterra/claude-code-helpers (5 stars, last pushed 1y ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 340 tokens. 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.