chad-review

chad-review is a skill for Claude Code from psd401/psd-claude-plugins. It costs 267 tokens per session (2,387 once invoked), scanned C, original, MIT.

A review process that rewrites an artifact in plainer, more practical language after examining it from the viewpoint of a blunt intended reader. An artifact can be code, documentation, a prompt, a skill, or other written or visual work.

In plain words
What is it for?
Reviewing and simplifying code-related instructions, documentation, prompts, diagrams, landing pages, and other project materials.
Why use it?
It removes unnecessary clever wording and exposes parts that do not clearly help the reader complete their job.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: model in frontmatter; mentions subagents; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the psd-coding-system plugin — 9 skills, 5 hooks shipped together

Good fit Reviewing and simplifying code-related instructions, documentation, prompts, diagrams, landing pages, and other project materials.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add psd401/psd-claude-plugins
Claude Code
/plugin install psd-coding-system

Made for: Claude Code.

Or install psd-coding-system, the plugin that ships this one along with the rest of its 9 skills, 5 hooks.

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 chad-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/psd401/psd-claude-plugins/chad-review.svg)](https://agentmods.dev/skills/psd401/psd-claude-plugins/chad-review)
Your own site
<a href="https://agentmods.dev/skills/psd401/psd-claude-plugins/chad-review"><img src="https://agentmods.dev/badge/skills/psd401/psd-claude-plugins/chad-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 267 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,387 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00267 $0.02387
Opus 5 $0.00133 $0.01193
Sonnet 5 $0.00053 $0.00477
Haiku 4.5 $0.00027 $0.00239

Measured 8d ago against content hash 60c34e050c15, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

chad-review scanned grade C with 1 finding 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 8d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **The clone step runs `rm -rf`.** `workflows/chad-review.js` clones with `rm -rf "<path>-clone" && cp -R "<path>" "<path>-clone"` (or `cloneTo` if you supply it). Anything already sitting at that `-clone` path is destr
plugins/psd-coding-system/skills/chad-review/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chad Review — strip the showing-off, keep the job

Attribution. Vendored from the chad-review plugin by Nityesh Agarwal (upstream v0.5.0, vendored 2026-08-18). Upstream declared no license at the time of vendoring. The workflow script workflows/chad-review.js is an unmodified copy; this SKILL.md carries PSD-specific notes marked below.

SOTA AI models show off: they reach for the clever word, the metaphor, the caveat nobody needed, the little bit of self-narration — because they don't trust the material to be interesting on its own. Chad is the antidote. This skill runs him on a clone and hands you the plainer version, the full comment trail, and whatever the review couldn't settle.

The two mindsets

Chad is the artifact's intended audience wearing the meme personality: he meets it cold, with a job to do, and asks dumb questions out loud without a flicker of shame — because looking dumb costs nothing and getting to the point is everything. He gets exactly one piece of context, the crux — the job he came to get done. He reviews in depth, every part and piece, and leaves specific feedback comments; his last comment is always a bird's-eye view of the whole thing (too long? too busy? wrong shape? or does it land?). He doesn't rewrite; he comments.

The defender owns the artifact and ships it. Chad is an asset, not an opponent: a bullshit detector running before the real world does, and every comment is a free preview of where the artifact fails the person it's for. He addresses every comment — the bird's-eye included — either by fixing the artifact or by rejecting the comment with a reason written to Chad. The bird's-eye comment is about the shape of the whole and deserves a whole-shaped answer: reorganize, merge parts that do the same job, remove a part whose job the rest already does. Repetition is a structure smell — the fix for the same thing said in three places is one home for it, not three local edits.

Read the full file on GitHub · 113 lines

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. 8d ago First seen · 113 lines · 267 tokens per session scan C 60c34e050c15

Subscribe to this mod's changes

chad-review is a skill published in the GitHub repository psd401/psd-claude-plugins (2 stars, last pushed 7d ago), licensed MIT. It adds 267 tokens to every session and 2,387 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.