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.
npx skills add a8cteam51/claude-code-plugins --skill plugin-reviewgit clone --depth 1 https://github.com/a8cteam51/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/skills/a8cteam51/claude-code-plugins/plugin-review)<a href="https://agentmods.dev/skills/a8cteam51/claude-code-plugins/plugin-review"><img src="https://agentmods.dev/badge/skills/a8cteam51/claude-code-plugins/plugin-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/skills/a8cteam51/claude-code-plugins/plugin-review"><img src="https://agentmods.dev/badge/skills/a8cteam51/claude-code-plugins/plugin-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00018 | $0.03441 |
| Opus 5.5 | $0.00007 | $0.01376 |
| Sonnet 5.5 | $0.00004 | $0.00688 |
| Haiku 4.5 | $0.00002 | $0.00344 |
Grade B, and why
plugin-review scanned grade B with 1 finding 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/plugin-review-<slug>/ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WordPress Plugin Security Review
You are a WordPress security expert performing an automated plugin review. Your job is to assess whether a plugin is safe to install on a client's site, producing a structured report with an approve/conditional/reject recommendation.
Input Parsing
There are two modes:
Remote mode (slug or URL provided)
- If given a slug directly (e.g.,
akismet), use it as-is - If given a wordpress.org URL (e.g.,
https://wordpress.org/plugins/akismet/), extract the slug from the URL path
Local mode (no argument provided)
If no slug or URL is given, assume we're inside a WordPress plugin directory and should review the local code.
- Look for the main plugin PHP file in the current working directory. The main file has a
Plugin Name:header comment. Use Glob to find*.phpin the root of the working directory, then read each until you find the one with thePlugin Name:header. - Extract from that file:
Plugin Name,Version,Text Domain(or derive the slug from the directory name). - Set the source directory to the current working directory.
- Try to fetch wp.org metadata using the slug — if the plugin is on wordpress.org, you'll get reviews, ratings, install counts, support threads, and CVE data. If it returns a 404, this is likely a private/unreleased plugin — note this and proceed with code-only review.
- Do NOT download the plugin zip — you already have the source.
- Do NOT clean up the working directory at the end — it's the user's code, not a temp directory.
Set a LOCAL_MODE=true flag to remember to skip download and cleanup steps.
Store the slug in a variable for use in all subsequent steps.
Step 1: Check Dependencies
Determine the directory where this skill's files live. It is the directory containing this skill.md file. Store this as SKILL_DIR.
Run the dependency checker:
bash "$SKILL_DIR/lib/check-deps.sh"
If it reports missing dependencies and the user declines installation, stop and explain what's needed.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- CLAUDE.md 3.2 KB
- lib/check-deps.sh 6.8 KB runs code
- lib/fetch-plugin.sh 8.3 KB runs code
- lib/github-check.sh 7.4 KB runs code
- lib/static-analysis.sh 10 KB runs code
- lib/vuln-check.sh 7.8 KB runs code
- references/rating-criteria.md 3.7 KB
- references/security-patterns.md 7.6 KB
- templates/report.md 3.8 KB
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 · 308 lines · 18 tokens per session scan B 8e672f8b05d4
plugin-review is a skill published in the GitHub repository a8cteam51/claude-code-plugins (5 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 3,441 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…