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/bengous/claude-code-pluginsWrote 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/bengous/claude-code-plugins/git)<a href="https://agentmods.dev/plugins/bengous/claude-code-plugins/git"><img src="https://agentmods.dev/badge/plugins/bengous/claude-code-plugins/git/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/bengous/claude-code-plugins/git"><img src="https://agentmods.dev/badge/plugins/bengous/claude-code-plugins/git.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
git 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 today.
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": "git",
"version": "1.1.0",
"description": "Local history without an editor: commit with an optional issue-closing trailer, interactive rebase, squash by pattern or hash",
"author": {
"name": "Augustin BENGOLEA",
"email": "[email protected]"
},
"homepage": "https://github.com/bengous/claude-code-plugins",
"repository": "https://github.com/bengous/claude-code-plugins",
"license": "MIT",
"keywords": [
"git",
"commit",
"rebase",
"squash",
"history"
]
}
What it installs
The manifest is a name and a version. 3 skills travel with it, and installing the plugin installs all of them — 154 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.
- today First seen · 20 lines scan A 2272109f5c1f
git is a plugin published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed today), 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 2026-09-11.
Other plugins, from other repositories
csw
Ship a tracker ticket: dispatch it into a worktree, drive it to a pull request, merge it after review, and clean up after itself.
prflow
Turn feature requests into review-ready pull requests: issue, implementation, tests, a review-and-fix loop, and docs. Runs locally or on GitHub Actions, and is built for complex brownfield repos. Each week its retrospective reads what you actually merged and proposes improvements to your skill extensions.
repo-gate
What runs between "the code works" and "it is pushed": trunk setup, conventional-commit splitting, dependency vulnerability triage, spell-check and markdownlint triage, and babysitting CI until it is green.
cas
Evidence-driven research, guarded Codex delegation, explicit native parallelism, secret protection, and approval gates for rm, commit, and push.
ratchet
Verified, resumable engineering loops for Claude Code — audit a codebase into an acceptance-gated backlog, route each item to the right model, execute one verified commit at a time.
g-forge
Educated, enforced project management for AI development - a PM layer, parallel implementation waves, and a git-hook commit gate that can't be skipped. Make any model ship like a senior team.