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.
/plugin marketplace add psd401/psd-claude-plugins/plugin install psd-coding-systemWrote 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.
[](https://agentmods.dev/skills/psd401/psd-claude-plugins/chad-review)<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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00267 | $0.02384 |
| Opus 5.5 | $0.00107 | $0.00954 |
| Sonnet 5.5 | $0.00053 | $0.00477 |
| Haiku 4.5 | $0.00027 | $0.00238 |
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 14d 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 How it starts
The opening of the file, as written. The whole thing — 112 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-reviewplugin by Nityesh Agarwal (upstream v0.5.0, vendored 2026-08-18). Upstream declared no license at the time of vendoring. The workflow scriptworkflows/chad-review.jsis 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.
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.
- 14d ago Changed · -1 lines 99e950e05a17
- 1mo ago Changed 2a1562091edc
- 2mo ago First seen · 113 lines · 267 tokens per session scan C 60c34e050c15
chad-review is a skill published in the GitHub repository psd401/psd-claude-plugins (2 stars, last pushed 9d ago), licensed MIT. It adds 267 tokens to every session and 2,384 once invoked, about $0.0011 per session on Opus 5.5. 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.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…