critical-review

critical-review is a skill for Claude Code, Codex from swDomass/AI_orchestrator. It costs 21 tokens per session (437 once invoked), scanned A, original, MIT.

A direct architectural review of a codebase, its design, working methods, and operation in the real world. It questions whether the project should exist, where it may fail, and what the minimum fixes are.

In plain words
What is it for?
Use it to challenge a project's basic premise, assess whether its complexity is justified, find design and code-quality problems, and identify risks that may appear in production.
Why use it?
It exposes assumptions, hidden complexity, weak tests, operational risks, and accumulating technical debt. The review is intended to surface uncomfortable problems rather than soften them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to challenge a project's basic premise, assess whether its complexity is justified, find design and code-quality problems, and identify risks that may appear in production.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/swdomass/ai_orchestrator/critical-review
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.

Any agent
npx skills add swDomass/AI_orchestrator --skill critical-review
Clone the repo
git clone --depth 1 https://github.com/swDomass/AI_orchestrator

Made for: Claude Code, Codex.

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 critical-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/swdomass/ai_orchestrator/critical-review/github.svg)](https://agentmods.dev/skills/swdomass/ai_orchestrator/critical-review)
Your own site
<a href="https://agentmods.dev/skills/swdomass/ai_orchestrator/critical-review"><img src="https://agentmods.dev/badge/skills/swdomass/ai_orchestrator/critical-review/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.

agentmods 80×15 button for critical-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/swdomass/ai_orchestrator/critical-review"><img src="https://agentmods.dev/badge/skills/swdomass/ai_orchestrator/critical-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 437 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 $0.00021 $0.00437
Opus 5 $0.00010 $0.00218
Sonnet 5 $0.00004 $0.00087
Haiku 4.5 $0.00002 $0.00044

Measured 11d ago against content hash 2d6863189208, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

critical-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 11d 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.

skills/critical-review/SKILL.md · 43 lines

What it actually says

System Prompt Addition

Perform a radical-honesty architectural review. You are a principal engineer who does not soften findings. Explore the entire codebase first, then write a structured report covering:

  • Concept & Fundamental Premise (most important): Should this thing exist at all? What is the core assumption that, if wrong, makes the project pointless? Who else solved this and why is this better? If you had to argue against building it, what would you say?
  • Problem–Solution Fit: Is the complexity justified? What assumption was never questioned?
  • Architecture & Design: Where does this break under real-world conditions?
  • Code Quality: Where is complexity hidden? What tests give false confidence?
  • Operational Reality: What happens at 2am when something breaks?
  • Methodology & Process: Where is tech debt accumulating faster than it's paid down?
  • Risk & Blind Spots: What does the author not know they don't know?

Output format (mandatory): 0. Concept Verdict (2–3 sentences: should this exist?)

  1. TL;DR (3–5 sentences, blunt verdict)
  2. Critical Findings (P0/P1) — problem + consequence + minimum fix
  3. Significant Concerns (P2)
  4. Methodology Critique
  5. What's Actually Good (specific, no padding)
  6. Recommended Action (one thing, not a list)

Rules: no sandwiching, no hedging, no vague statements. Name files, lines, patterns. This is a read-only analysis — do NOT modify any files. Output is saved to docs/critical-review-YYYYMMDD-HHMMSS.md in the CWD.

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. 11d ago First seen · 43 lines · 21 tokens per session scan A 2d6863189208

Subscribe to this mod's changes

critical-review is a skill published in the GitHub repository swDomass/AI_orchestrator (5 stars, last pushed 5d ago), licensed MIT. It adds 21 tokens to every session and 437 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 2026-08-31.

Related

Other skills, from other repositories

plugin-review

Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.

athola/claude-night-market · 23 tokens

code-review-expert

Expert-level code review focusing on quality, security, performance, and maintainability. Use this skill for conducting thorough code reviews, identifying issues, and providing constructive feedback.

personamanagmentlayer/pcl · 38 tokens

code-review-architecture

Architecture-focused code review covering hexagonal boundary violations, DDD anti-patterns, CQRS misuse, and microservices coupling issues. Applied in addition to the language-specific review skill when architecture markers are detected. Invoked when reviewing hexagonal architectures, DDD patterns, or microservices…

soulcodex/agentic · 63 tokens

code-review-php

Deep PHP-specific code review covering strict types, PHPStan compliance, PSR standards, domain modeling, and ORM boundary violations. Applied in addition to the generic code-review skill when PHP code is detected. Invoked when reviewing PHP PRs, Symfony/Laravel changes, or performing PHP-specific quality checks.

soulcodex/agentic · 66 tokens

code-review-python

Deep Python-specific code review covering type annotations, async pitfalls, mutable defaults, threading safety, and domain modeling. Applied in addition to the generic code-review skill when Python code is detected. Invoked when reviewing Python PRs, Py changes, or performing Python-specific quality checks.

soulcodex/agentic · 59 tokens

code-review-typescript

Deep TypeScript-specific code review covering type safety, ESM/CJS, async correctness, money precision, and domain modeling. Applied in addition to the generic code-review skill when TypeScript/JavaScript code is detected. Invoked when reviewing TS/JS PRs, TypeScript changes, or performing TypeScript-specific quality…

soulcodex/agentic · 71 tokens