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/fusengine/agentsWrote 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/fusengine/agents/commit-pro)<a href="https://agentmods.dev/plugins/fusengine/agents/commit-pro"><img src="https://agentmods.dev/badge/plugins/fusengine/agents/commit-pro/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/fusengine/agents/commit-pro"><img src="https://agentmods.dev/badge/plugins/fusengine/agents/commit-pro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
fuse-commit-pro 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 7d 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": "fuse-commit-pro",
"version": "1.2.29",
"description": "Professional git commits with Conventional Commits, GitHub Flow branch enforcement, auto PR creation, security validation, and auto-detection",
"author": {
"name": "Fusengine",
"email": "[email protected]",
"url": "https://github.com/fusengine"
},
"homepage": "https://github.com/fusengine/agents",
"repository": "https://github.com/fusengine/agents",
"license": "MIT",
"keywords": [
"git",
"commit",
"conventional-commits",
"security",
"automation"
]
}
What it installs
The manifest is a name and a version. 4 skills, 10 commands, 1 agent travel with it, and installing the plugin installs all of them — 343 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill git-flow A 20 tokens
- Skill post-commit A 33 tokens
- Skill commit-detection A 26 tokens
- Skill commit-optimization B 20 tokens
- Command commit A 31 tokens
- Command amend A 20 tokens
- Command chore A 18 tokens
- Command docs A 18 tokens
- Command feat A 17 tokens
- Command fix A 21 tokens
- Command refactor A 18 tokens
- Command test A 19 tokens
- Command undo A 18 tokens
- Command wip A 18 tokens
- Agent commit-detector A 46 tokens
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.
- 7d ago Changed a7e3522d8eb3
- 21d ago Changed e9566bf4bf43
- 22d ago Changed ac026adcdde0
- 25d ago Changed 3acfee72f5c5
- 1mo ago Changed d6de8a1b8218
- 1mo ago First seen · 21 lines scan A 51c57c46d1fc
fuse-commit-pro is a plugin published in the GitHub repository fusengine/agents (33 stars, last pushed 7d 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 2026-09-03.
Other plugins, from other repositories
github
Skills for GitHub pull request workflows — creating PRs, addressing review feedback, and resolving threads.
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.
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.
github-activity
Read-only GitHub activity reporter for program managers. One hosted connector reads merged pull requests, opened and closed issues, and milestone movement across several repositories since a point in time. It holds no write tool, the tool policy allows only the read tool so anything else fails closed, and the…
pr-voice
Rewrites a thin or empty pull-request description in the repo's own PR voice, measured from its merged history (title convention, length per diff size, recurring headings, issue-closing style). Grounded in the diff; never invents testing claims. Applies with gh pr edit only on explicit confirmation.
gates
Three stateless PreToolUse gates, a PostToolUse JSON-config guard, a 1Password signing nudge, and a docs-consolidation trigger. Denies a git commit that changes code without staging its covering docs (per-plugin README/CLAUDE.md pairs, or the nearest README/CLAUDE/AGENTS walking up); denies a high-fan-out Workflow…