commit

A command for creating Git commits, which are saved checkpoints of changes in a code project. It can generate messages using the Conventional Commits format, a shared style for describing changes.

In plain words
What is it for?
Use it to inspect changes, check tests and linting readiness, choose a commit type and scope, and create a suitably formatted Git commit.
Why use it?
It checks the repository, reviews the changes and can compare them with the project's existing commit style before creating a commit. This helps produce consistent, reviewable history.

Command

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/dhofheinz/open-plugins/commit
Clone the repo
git clone --depth 1 https://github.com/dhofheinz/open-plugins
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,772 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 $0.00011 $0.04772
Opus 5 $0.00005 $0.02386
Sonnet 5 $0.00002 $0.00954
Haiku 4.5 $0.00001 $0.00477

Measured yesterday against content hash 6e4a3eea6ed2, 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 yesterday.

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.

plugins/git-commit-assistant/commands/commit.md · 656 lines

How it starts

The opening of the file, as written. The whole thing — 656 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intelligent Git Commit Assistant

Create well-formatted git commits with optional automatic message generation following conventional commits standards.

Overview

The /commit command provides a simplified workflow that orchestrates multiple specialized skills to create intelligent, well-formatted commits following conventional commits standards.

Skills Orchestrated

This command coordinates these granular skills:

  1. commit-error-handling - Validates git repository state and checks for issues

    • Operation: /commit-error-handling diagnose-issues
    • Purpose: Ensure repository is in a clean state before committing
  2. commit-analysis - Analyzes changes to determine type, scope, and atomicity

    • Operation: /commit-analysis analyze
    • Purpose: Understand what changes are being committed
  3. history-analysis (optional) - Learns project commit conventions

    • Operation: /history-analysis analyze-style
    • Purpose: Match team's existing commit style
  4. commit-best-practices - Validates commit readiness

    • Operation: /commit-best-practices check-pre-commit
    • Purpose: Ensure tests pass, no debug code, lint clean
  5. message-generation - Generates conventional commit messages

    • Operation: /message-generation complete
    • Purpose: Create well-formatted conventional commit message
  6. atomic-commit (conditional) - Suggests splitting if needed

    • Operation: /atomic-commit analyze
    • Purpose: Determine if changes should be split into multiple commits

For Granular Control

If you need precise control over individual operations:

  • Use /commit-error-handling for error diagnosis
  • Use /commit-analysis for change analysis
  • Use /message-generation for message generation
  • Use /atomic-commit for commit splitting
  • Use /commit-best-practices for validation
  • Use /history-analysis for project conventions

See the commit-assistant agent for complete skill documentation.

Usage

/commit                    # Analyze changes and generate commit message
/commit "feat: add login"  # Use provided message directly

Read the full file on GitHub · 656 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. yesterday First seen · 656 lines · 11 tokens per session scan A 6e4a3eea6ed2

Subscribe to this mod's changes

commit is a command published in the GitHub repository dhofheinz/open-plugins (9 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 4,772 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 2026-08-31.