plugin-review

plugin-review is a command for Claude Code from basher83/lunar-claude. It costs 16 tokens per session (3,559 once invoked), scanned A, original, MIT.

A repeatable workflow for reviewing a Claude Code plugin against documented best practices. It tracks review progress in a local file so the work can continue later.

In plain words
What is it for?
It is for checking a plugin’s files and components, recording recommended improvements, and tracking commits made during the review.
Why use it?
It prevents plugin reviews from becoming an unstructured checklist and preserves decisions, evidence, and completed work across sessions.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; names the TodoWrite tool; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the plugin-dev plugin — 7 skills, 5 commands, 3 agents shipped together

Good fit It is for checking a plugin’s files and components, recording recommended improvements…

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add basher83/lunar-claude
Claude Code
/plugin install plugin-dev

Made for: Claude Code.

Or install plugin-dev, the plugin that ships this one along with the rest of its 7 skills, 5 commands, 3 agents.

Wrote 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.

agentmods badge for plugin-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/basher83/lunar-claude/plugin-review.svg)](https://agentmods.dev/commands/basher83/lunar-claude/plugin-review)
Your own site
<a href="https://agentmods.dev/commands/basher83/lunar-claude/plugin-review"><img src="https://agentmods.dev/badge/commands/basher83/lunar-claude/plugin-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,559 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.03559
Opus 5 $0.00008 $0.01780
Sonnet 5 $0.00003 $0.00712
Haiku 4.5 $0.00002 $0.00356

Measured 3d ago against content hash a9175ad69c13, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

plugin-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 3d 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.

plugins/meta/plugin-dev/commands/plugin-review.md · 512 lines

How it starts

The opening of the file, as written. The whole thing — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plugin Review Workflow

Systematically review a Claude Code plugin against best practices from plugin-dev skills. Creates a state file to track progress and enables resumable reviews.

Target plugin: $ARGUMENTS


Core Principles

  • State file tracking: Create .claude/<plugin-name>-review.local.md to track all progress
  • Skill-based validation: Load relevant plugin-dev skills and validate against documented patterns
  • Proof-based decisions: When recommending changes, cite specific guidance from skills
  • Incremental commits: Commit improvements as they're made, track commit SHAs in state file
  • Resumable: If session ends, next session can continue from state file

Phase 0: Setup

Goal: Validate plugin path and create state file

Actions:

  1. Validate the plugin path exists and has .claude-plugin/plugin.json
  2. Read plugin.json to get plugin name and version
  3. Auto-discover plugin components:
    # Commands
    ls <plugin-path>/commands/*.md 2>/dev/null | wc -l
    
    # Agents
    ls <plugin-path>/agents/*.md 2>/dev/null | wc -l
    
    # Skills
    find <plugin-path>/skills -name "SKILL.md" 2>/dev/null | wc -l
    
    # Hooks
    test -f <plugin-path>/hooks/hooks.json && echo "yes" || echo "no"
    
  4. Create state file at .claude/<plugin-name>-review.local.md:
---
workflow: plugin-review
plugin: <plugin-name>
plugin_path: <plugin-path>
status: in_progress
started: <date>
last_updated: <date>
phase: discovery
plugin_version: <version>
---

# <Plugin-Name> Plugin Review

Comprehensive review against plugin-dev best practices.

## Component Inventory

| Component | Path | Count | Status |
|-----------|------|-------|--------|
| plugin.json | `.claude-plugin/plugin.json` | 1 | pending |
| README.md | `README.md` | 1 | pending |
| Commands | `commands/` | <n> | pending |
| Agents | `agents/` | <n> | pending |
| Skills | `skills/` | <n> | pending |
| Hooks | `hooks/` | <yes/no> | pending |

## Review Progress

### Phase 1: Commands
(to be filled during review)

### Phase 2: Agents
(to be filled during review)

### Phase 3: Skills
(to be filled during review)

### Phase 4: Metadata
(to be filled during review)

### Phase 5: Advanced Patterns
(to be filled during review)

## Commits
(to be filled as changes are committed)

## Next Steps
1. [ ] Phase 1: Review commands
2. [ ] Phase 2: Review agents
3. [ ] Phase 3: Review skills
4. [ ] Phase 4: Review metadata
5. [ ] Phase 5: Advanced patterns analysis
6. [ ] Commit changes
7. [ ] Version bump
8. [ ] Push to remote

Read the full file on GitHub · 512 lines

Changes

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.

  1. 3d ago First seen · 512 lines · 16 tokens per session scan A a9175ad69c13

Subscribe to this mod's changes

plugin-review is a command published in the GitHub repository basher83/lunar-claude (22 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 3,559 once invoked, about $0.0001 per session on Opus 5. 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.