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/closedloop-ai/claude-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/closedloop-ai/claude-plugins/code-review)<a href="https://agentmods.dev/plugins/closedloop-ai/claude-plugins/code-review"><img src="https://agentmods.dev/badge/plugins/closedloop-ai/claude-plugins/code-review/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/closedloop-ai/claude-plugins/code-review"><img src="https://agentmods.dev/badge/plugins/closedloop-ai/claude-plugins/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
code-review 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 yesterday.
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": "code-review",
"description": "Code review plugin",
"version": "3.10.5",
"author": {
"name": "ClosedLoop",
"email": "[email protected]"
}
}
What it installs
The manifest is a name and a version. 5 skills, 4 commands, 2 agents travel with it, and installing the plugin installs all of them — 926 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill spawn-reviewers A 191 tokens
- Skill fix A 27 tokens
- Skill present-local A 136 tokens
- Skill singleton-dispatch A 142 tokens
- Skill verify-findings A 171 tokens
- Command start A 15 tokens
- Command cost A 51 tokens
- Command deep A 30 tokens
- Command shallow A 28 tokens
- Agent code-review-worker-graph A 90 tokens
- Agent code-review-worker A 45 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.
- yesterday Changed 4fb9f431888b
- 8d ago Changed 8aaffac7bc34
- 14d ago Changed dbbf55c0c9ad
- 17d ago Changed f8a2a56c4167
- 24d ago Changed 2c69e906a85b
- 1mo ago Changed c2f53678635e
- 1mo ago Changed f3fb9277b991
- 1mo ago First seen · 10 lines scan A b454e8c5998b
code-review is a plugin published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. 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 2026-08-30.
Other plugins, from other repositories
diffctx
Selects the minimum code an LLM needs to review a git diff.
adversarial-review
Requires a task result to survive two consecutive independent adversarial reviews before completion.
code-review
Automated code review for pull requests using multiple specialized agents with confidence-based scoring.
agentic-code-review
Multi-agent code review that fans out to specialized subagents (bugs, security, CLAUDE.md compliance, git history, test coverage), scores findings by confidence, filters noise, and reports to the terminal or as inline GitHub PR comments.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.