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.
git clone --depth 1 https://github.com/pau-vega/Devkit-AIWrote 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/plugins/pau-vega/devkit-ai/commit-commands)<a href="https://agentmods.dev/plugins/pau-vega/devkit-ai/commit-commands"><img src="https://agentmods.dev/badge/plugins/pau-vega/devkit-ai/commit-commands/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/plugins/pau-vega/devkit-ai/commit-commands"><img src="https://agentmods.dev/badge/plugins/pau-vega/devkit-ai/commit-commands.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
commit-commands 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
{
"name": "commit-commands",
"version": "0.1.5",
"description": "Streamline git workflow with /commit, /commit-push-pr, and /clean-gone commands",
"author": {
"name": "Anthropic"
},
"license": "MIT",
"keywords": [
"git",
"commit",
"pull-request",
"workflow",
"productivity"
]
}
What it installs
The manifest is a name and a version. 1 skill, 3 commands, 3 agents travel with it, and installing the plugin installs all of them — 559 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 17 lines scan A 6be7e29af4f2
commit-commands is a plugin published in the GitHub repository pau-vega/Devkit-AI (2 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
release-conductor
Owns everything around the diff: craft Conventional Commits and PR descriptions, recommend the right semver bump by reasoning about behavioral breaking changes, assemble changelogs from messy history, and guide merge-conflict resolution, rebase planning, and git-history archaeology.
han-github
Github specific extensions to the Han plugin for agentic planning and coding. Provides skills to post code reviews as PR comments, update a PR description with a consistent format, etc.
release-tools
Release workflow tools - auto-versioning, release notes, changelog updates.
review
PR review, interactive git diff annotation review, and writing style guide.
contributor-writing
Writing skills for Shopware core contributors: Architecture Decision Records, PR descriptions (trunk and feature-branch formats), commit messages, and RELEASEINFO/UPGRADE entries. Analyzes branch diffs, classifies changes, and writes content calibrated to change magnitude.
dark-factory
Curie's default dark factory agent: one labelled GitHub issue in, one reviewed pull request or one stated reason out. One agent reads the issue through the platform's getissue tool, pins acceptance criteria, plans, gets the plan reviewed by an Opus plan-reviewer subagent, writes a failing test where feasible, implemen.