Skip to content
Agentmart
Submit a tool

critique

Council critique mode - agents find bugs and flaws in each other's answers

Skill by agentic-box

IndexedMIT★ 140
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/agentic-box-critique

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

Council critique mode - agents find bugs and flaws in each other's answers

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. 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/critique

What's inside

Skill name
critique
Description
Council critique mode - agents find bugs and flaws in each other's answers
License
MIT
Instructions
27 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • allowed-tools: must be a space-separated string

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Council Critique Mode

Start an owlex council in **critique mode** - agents actively find bugs, security issues, and flaws.

## Instructions

1. Take the user's question or code from: $ARGUMENTS
2. If no argument provided, ask what they want critiqued
3. Call `mcp__owlex__council_ask` with:
   - `prompt`: The user's question/code to critique
   - `working_directory`: Current working directory
   - `deliberate`: true
   - `critique`: true (enables adversarial mode)
4. Return immediately with the task_id
5. Tell the user:
   - "Critique started (task: <task_id>)"
   - "This typically takes 2-5 minutes"
   - "Check results with: `/council-result <task_id>`"

**Do NOT call wait_for_task. Return immediately.**

## Usage

- `/critique Review this auth for security holes`
- `/critique Find bugs in this payment code`

From agentic-box/owlex, MIT.

Signals

Stars
140
Forks
16
Open issues
0
Last commit (this folder)
Jan 10, 2026 (9 months ago)
Last release
Feb 18, 2026 (8 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from agentic-box

Cite this page

critique skill. Agent Mart. https://agentmart.dev/skills/agentic-box-critique (last updated 2026-10-24)