A command that asks other locally installed AI coding tools to review code or a technical decision, then combines their responses with its own review. An adversarial review looks specifically for bugs, security problems, design weaknesses, and simpler options.

Use it on a file, pull-request description, web page, or plain-text decision when you want a critical second opinion about implementation or design.

It gives you independent opinions instead of relying on one review, while showing which reviewers were available on the machine.

crit — Command for Claude Code by Achitokun14/claude-universal

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.

Clone the repo

git clone --depth 1 https://github.com/Achitokun14/claude-universal

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/achitokun14/claude-universal/crit/github.svg)](https://agentmods.dev/commands/achitokun14/claude-universal/crit)

Your own site

<a href="https://agentmods.dev/commands/achitokun14/claude-universal/crit"><img src="https://agentmods.dev/badge/commands/achitokun14/claude-universal/crit/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/achitokun14/claude-universal/crit"><img src="https://agentmods.dev/badge/commands/achitokun14/claude-universal/crit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 452 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.

Model	Per session	Once invoked
Fable 5.1	$0.00027	$0.00452
Opus 5.5	$0.00011	$0.00181
Sonnet 5.5	$0.00005	$0.00090
Haiku 4.5	$0.00003	$0.00045

Measured 2mo ago against content hash 63a712805649, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

crit 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 2mo 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.

user/commands/crit.md · 58 lines

What it actually says

Get second opinions from other AI coding tools installed on this machine.

Steps:

If $ARGUMENTS is empty, ask: "What should I crit? (file path, PR description, or plain-text decision)".

Prepare the review prompt:

Give a critical, adversarial review of the following. Call out bugs, security issues,
design flaws, and simpler alternatives. Do not be polite — be useful. Under 250 words.

<CONTENT>

If $ARGUMENTS is a file path, Read it and embed. If a URL, WebFetch it. Otherwise use it verbatim.

Check availability of external reviewers with Bash:
- command -v kimi → run kimi -p "<prompt>" in background via run_in_background
- command -v opencode → run opencode run "<prompt>"
- command -v codex → run codex exec "<prompt>"
- command -v aider → skip (interactive only) Dispatch all available in parallel. Skip silently if a tool is missing.
Also generate Claude's own review so there are always ≥2 opinions.

Synthesize into:

# Crit: <short title>

## Claude (self)
<review>

## Kimi
<review or "not installed">

## OpenCode
<review or "not installed">

## Codex
<review or "not installed">

## Consensus
- **All agree:** <shared concerns>
- **Claude unique:** <only Claude flagged>
- **Others unique:** <only external tools flagged>

## Recommendation
<what to act on first>

If any external tool returned nothing or errored, note it but don't fail the command.

Never pipe secrets or .env contents into external tools.

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.

2mo ago First seen · 58 lines · 27 tokens per session scan A 63a712805649

Subscribe to this mod's changes

crit is a command published in the GitHub repository Achitokun14/claude-universal (2 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 452 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.

Claude Code Code review ai-agents bash codex coding-agents gemini-cli

pi-code-review

Adversarial code review via Codex — break confidence in changes, not validate them.

tznthou/claude-prism · 17 tokens

pi-fact-check

Fact-check content via Gemini search + Claude verification — cross-provider claim validation.

tznthou/claude-prism · 14 tokens

pi-askall

Ask both Codex and Gemini the same question — get three perspectives with Claude synthesis.

tznthou/claude-prism · 16 tokens

pi-ask-gemini

Ask Gemini a question — get Google's perspective alongside Claude's.

tznthou/claude-prism · 11 tokens

audit

You are a Principal Engineer & Product Architect conducting a full adversarial audit of this codebase. Your job is not to be polite. Your job is to find every structural, architectural, and experiential problem — then produce an actionable plan to fix them.

openplanr/OpenPlanr · 0 tokens

review-pr

Command "review-pr" from saski/arnesto, covering review pr, what this command does, workflow steps, phase 0: initialize review and phase 1: analysis & summary.

saski/arnesto · 0 tokens