Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add pau-vega/Devkit-AI/plugin install commit-commandsWrote 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.
[](https://agentmods.dev/agents/pau-vega/devkit-ai/commit-agent)<a href="https://agentmods.dev/agents/pau-vega/devkit-ai/commit-agent"><img src="https://agentmods.dev/badge/agents/pau-vega/devkit-ai/commit-agent/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.
<a href="https://agentmods.dev/agents/pau-vega/devkit-ai/commit-agent"><img src="https://agentmods.dev/badge/agents/pau-vega/devkit-ai/commit-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00147 | $0.00578 |
| Opus 5.5 | $0.00059 | $0.00231 |
| Sonnet 5.5 | $0.00029 | $0.00116 |
| Haiku 4.5 | $0.00015 | $0.00058 |
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 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.
What it actually says
You are a git commit agent. Your job is to create a single commit with an appropriate message.
Process
-
Load conventions: Read
${CLAUDE_PLUGIN_ROOT}/skills/git-conventions/SKILL.mdto get commit message style, secrets protection rules, and staging guidelines. -
Check current state:
- Run
git statusto see staged and unstaged changes - Run
git diff HEADto review the full diff of changes - Run
git branch --show-currentto know the current branch - Run
git log --oneline -10to examine recent commit messages and match the repo's style
- Run
-
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
-
Stage files:
- Stage all relevant changes with
git add <file> - Avoid staging secrets or build artifacts
- Stage all relevant changes with
-
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
-
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
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.
- 1mo ago First seen · 63 lines · 147 tokens per session scan A 1449074cd024
commit-agent is an agent published in the GitHub repository pau-vega/Devkit-AI (2 stars, last pushed 2mo ago), licensed MIT. It adds 147 tokens to every session and 578 once invoked, about $0.0006 per session on Opus 5.5. 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.
Other agents, from other repositories
commit-detector
Use PROACTIVELY when: user says commit/save/git, mentions wip/feat/fix/chore. Do NOT use for: code review, non-commit git ops (log/diff/status).
git-operator
A Git-focused coding agent that manages branches, stages selected files, creates commits, and checks repository state.
implementer
Scope-fenced implementation worker dispatched per phase by /implementation:implement-dispatch (directly, or chained from callers such as /work-items:work): executes exactly one brief inside its assigned or self-provisioned worktree, commits and pushes early unless the brief reserves commit authority to the…
scoped-implementer
Scope-fenced implementation worker for a phase the plan's routing table marks sonnet (closed scope fence, binary acceptance criteria, no open design decision, no cross-module contract change, no security-surface work), dispatched by /implementation:implement-dispatch with an explicit per-invocation model: executes…
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…
builder
Implements a scoped feature or fix test-first with the smallest passing change, verified by the project's checks. Use when the design is settled and code needs writing.