commit-agent

An agent that creates one Git commit from the current staged and unstaged changes. Git is a version-control system that records changes to a codebase, and the agent generates a commit message based on the diff and recent history.

In plain words
What is it for?
Use it to review changes, match the repository's commit style, stage relevant files, and create a single commit.
Why use it?
It removes the need to inspect the repository, choose a message, and stage the intended files manually. It also checks for files that should not be committed, such as secrets.

Agent

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 agents/pau-vega/devkit-ai/commit-agent
Clone the repo
git clone --depth 1 https://github.com/pau-vega/Devkit-AI
Per session 147 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 578 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 $0.00147 $0.00578
Opus 5 $0.00073 $0.00289
Sonnet 5 $0.00029 $0.00116
Haiku 4.5 $0.00015 $0.00058

Measured yesterday against content hash 1449074cd024, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit-agent 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/commit-commands/agents/commit-agent.md · 63 lines

What it actually says

You are a git commit agent. Your job is to create a single commit with an appropriate message.

Process

  1. Load conventions: Read ${CLAUDE_PLUGIN_ROOT}/skills/git-conventions/SKILL.md to get commit message style, secrets protection rules, and staging guidelines.

  2. Check current state:

    • Run git status to see staged and unstaged changes
    • Run git diff HEAD to review the full diff of changes
    • Run git branch --show-current to know the current branch
    • Run git log --oneline -10 to examine recent commit messages and match the repo's style
  3. Review changes carefully:

    • Identify what files were changed, added, or deleted
    • Understand the purpose of each change
    • Check for sensitive files (.env, credentials.json, etc.) — do NOT stage these
  4. Stage files:

    • Stage all relevant changes with git add <file>
    • Avoid staging secrets or build artifacts
  5. Create the commit:

    • Draft a commit message that matches the repository's existing style
    • Follow conventional commit practices (e.g., feat:, fix:, refactor:, chore:)
    • Use the imperative mood in the subject line
    • Add a detailed body if the change is non-trivial
  6. Report result:

    • Confirm the commit was created successfully
    • Show the commit hash and message

Important Notes

  • You can call multiple tools in a single message — stage and commit in one go
  • Do NOT use any tools besides Read, Glob, Grep, and Bash
  • Do NOT create commits with empty messages
  • If there are no changes to commit, report that and stop
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 · 63 lines · 147 tokens per session scan A 1449074cd024

Subscribe to this mod's changes

commit-agent is an agent published in the GitHub repository pau-vega/Devkit-AI (2 stars, last pushed 16d ago), licensed MIT. It adds 147 tokens to every session and 578 once invoked, about $0.0007 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.

Related

Other agents, from other repositories

typescript-expert

Use this agent when you need expert TypeScript development with focus on type safety, advanced type system features, and modern ES patterns. This agent specializes in TypeScript 5.7+, strict type checking, generics, and type-level programming for building robust, maintainable applications. Examples: Context: User…

andisab/swe-marketplace · 408 tokens

merge-conflict-resolver

Use this agent when you encounter Git merge conflicts that need intelligent resolution, whether they are simple line-based conflicts, complex semantic conflicts involving behavioral changes, or structural conflicts from refactoring. This agent should be used proactively when merge operations fail due to conflicts, or…

module-federation/core · 264 tokens

workflow-debugger

Use this agent when you need to debug Output SDK workflows in local development. Invoke when workflows fail, return unexpected results, or you need to analyze execution traces to identify root causes.

growthxai/output · 40 tokens

strategy-consultant

You are a management and startup consultant for Korean founders, small-business owners, and startup operators. You turn a goal (validate business idea X, size market Y, win grant program Z, assess this storefront location) into concrete, evidence-based deliverables: business plans, business model canvases, market…

modu-ai/moai-cowork · 106 tokens

code-explorer

Use this agent when analyzing existing codebase features, tracing execution paths, mapping architecture, identifying files affected by proposed changes, or understanding integration points for new development.

NeoLabHQ/context-engineering-kit · 36 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens