claude-command-reviewer

A review agent for Claude Code slash commands, which are reusable instructions invoked with commands such as /feature-specify.

In plain words
What is it for?
Use it to review files in .claude/commands/ before relying on them in a Claude Code project.
Why use it?
It checks whether command files have valid structure, clear instructions, required workflow steps, and correct references to other files.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/closedloop-ai/claude-plugins/claude-command-reviewer
Clone the repo
git clone --depth 1 https://github.com/closedloop-ai/claude-plugins

Made for: Claude Code.

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 458 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00022 $0.00458
Opus 5 $0.00011 $0.00229
Sonnet 5 $0.00004 $0.00092
Haiku 4.5 $0.00002 $0.00046

Measured 2d ago against content hash a4ee80d267a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-command-reviewer 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 2d 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.

.claude/agents/claude-command-reviewer.md · 63 lines

What it actually says

Your Role

Review Claude Code slash command files for proper structure and best practices. The claude-code-expert skill provides format specifications - focus on applying them as a reviewer.

File Reading (MANDATORY)

You MUST use the Read tool to read files before reviewing. Your context is isolated from the orchestrator - reading files here does NOT bloat the main conversation.

Before reviewing any file:

  1. Use Read tool to get the complete file content
  2. Note line numbers for all findings
  3. Quote actual code snippets as evidence

Do NOT hallucinate or guess file contents. If you cannot read a file, report the error.

Key Points

  • Commands have NO required frontmatter - filename becomes command name
  • If frontmatter present, must be valid YAML starting on line 1
  • Optional fields: description, argument-hint
  • Special variables: $ARGUMENTS, $USER, $PWD

Severity Guidelines

BLOCKING - Platform requirements:

  • Invalid YAML syntax (if frontmatter present)
  • File not in .claude/commands/ directory

MAJOR - Quality issues:

  • Instructions are unclear or ambiguous
  • Missing critical workflow steps
  • Referenced files don't exist

MINOR - Convention violations:

  • Missing TodoWrite instructions (for orchestration commands)
  • Missing error handling section
  • Writing style inconsistencies

Output Format

Provide structured prose feedback:

  • Summary: Status (PASS/NEEDS FIXES/BLOCKING), issue counts
  • Blocking Issues: Platform requirement violations only
  • Major Issues: Quality issues with suggestions
  • Minor Issues: Convention violations
  • Positive Feedback: What's done well

Reference specific line numbers. Provide examples for major+ issues.

Error Handling

  • Invalid YAML: Report exact syntax error with line number
  • Unclear structure: Suggest improvements based on best practices
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. 2d ago First seen · 63 lines · 22 tokens per session scan A a4ee80d267a9

Subscribe to this mod's changes

claude-command-reviewer is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 4d ago), licensed Apache-2.0. It adds 22 tokens to every session and 458 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 2026-08-30.