Skip to content
Agentmart
Submit a tool

review

Run an adversarial code review on staged changes or a specific file.

Skill by fullymiddleaged

IndexedMIT★ 5
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/fullymiddleaged-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Run an adversarial code review on staged changes or a specific file. Spawns the code-critic agent to find bugs, performance issues, and missed edge cases. Use before merging PRs or committing.

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/review

What's inside

Skill name
review
Description
Run an adversarial code review on staged changes or a specific file. Spawns the code-critic agent to find bugs, performance issues, and missed edge cases. Use before merging PRs or committing.
License
MIT
Instructions
31 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Adversarial Code Review

Run a thorough code review using the Clawness code-critic agent.

> **Before spawning the agent:** if you surfaced this proactively (the user
> mentioned reviewing/merging but didn't explicitly ask to run it), first ask:
> "Want me to run the adversarial code review now?" Proceed only once they
> confirm. If the user explicitly invoked `/clawness:review` or already
> said yes, skip the question.

## Steps

1. **Identify changes** — If $ARGUMENTS specifies files, review those.
   Otherwise, check for staged git changes (`git diff --cached`).
   If nothing is staged, review the most recently changed files
   (`git diff HEAD~1`).

2. **Delegate to code-critic** — Send the relevant code to the
   `code-critic` sub-agent for adversarial review focusing on:
   - Correctness bugs and logic errors
   - Performance issues (N+1, re-renders, memory leaks)
   - Missing edge cases (null, empty, concurrent, malicious)
   - Maintainability (naming, complexity, duplication)

3. **Report** — Present findings grouped by severity. For each finding,
   include the file, line, problem, and suggested fix.

4. **Offer to fix** — Ask the user if they want to apply any of the
   suggested fixes.

From fullymiddleaged/Clawness, MIT.

More from fullymiddleaged/Clawness

Signals

Stars
5
Forks
0
Open issues
0
Last commit (this folder)
Jun 26, 2026 (4 months ago)
Last release
Oct 4, 2026 (24 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from fullymiddleaged

Cite this page

review skill. Agent Mart. https://agentmart.dev/skills/fullymiddleaged-review (last updated 2026-10-24)