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/karlkfi/claude-bouncerWrote 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/karlkfi/claude-bouncer/branch-guard)<a href="https://agentmods.dev/plugins/karlkfi/claude-bouncer/branch-guard"><img src="https://agentmods.dev/badge/plugins/karlkfi/claude-bouncer/branch-guard/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/karlkfi/claude-bouncer/branch-guard"><img src="https://agentmods.dev/badge/plugins/karlkfi/claude-bouncer/branch-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
branch-guard 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 8d 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": "branch-guard",
"version": "1.10.0",
"description": "Cut routine git/gh approval prompts: auto-approve safe commands (read-only, staging, branch/worktree create, feature-branch commits & pushes) and confirm protected-branch or destructive ones.",
"author": {
"name": "Karl Isenberg",
"url": "https://github.com/karlkfi"
},
"homepage": "https://github.com/karlkfi/claude-bouncer/tree/main/plugins/branch-guard",
"repository": "https://github.com/karlkfi/claude-bouncer",
"license": "MIT",
"keywords": [
"claude-code",
"hooks",
"guardrail",
"permissions",
"safety",
"git",
"gh",
"worktree",
"push",
"break-glass",
"rebase",
"merge-queue"
]
}
What it installs
The manifest is a name and a version. 2 hooks travel with it, and installing the plugin installs all of 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.
- 8d ago First seen · 27 lines scan A 8ebf92e2a17e
branch-guard is a plugin published in the GitHub repository karlkfi/claude-bouncer (3 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 2026-08-31.
Other plugins, from other repositories
block-no-verify
PreToolUse hook that prevents AI agents from using --no-verify, --no-gpg-sign, and other bypass flags that skip git hooks.
auto-stage
Automatic git staging for Claude Code. A PostToolUse hook on Edit|Write runs git add on every file Claude modifies, so git status always shows exactly what Claude touched and pre-commit review needs no manual staging. Files outside a git repo are skipped, .gitignore is respected (ignored files fail to stage and the.
pr-provenance-stamp
Embeds a reviewer-facing provenance receipt into your PR body when Claude runs gh pr create (or glab mr create). A PostToolUse hook (async, zero added latency) records a per-session ledger: tool calls, agent-authored lines, and every test/typecheck command with its real exit code; a PreToolUse (Bash) hook then rewr.
forgedock
Autonomous AI development pipeline that uses GitHub as a structured knowledge graph for Claude Code agents. Adds /work-on, /review-pr, /quality-gate, /orchestrate, and 20+ pipeline commands.
branch-recap
Tells you what your branch actually changed — what was done, why, and what deserves a second look, instead of the diff — then files the fixes into the commits they belong to.
slack-changelog
Turns what changed in a release into a Slack changelog a non-technical audience can read — filtered to what they'd notice, one theme, one bullet per idea, no code vocabulary.