Cmo Review — Design agent for Claude Code
Fresh-eyes brand & conversion review for public-facing UI and customer-facing copy.
How to install Cmo Review
Installs to ~/.claude/agents/james-munluah-agent-operating-system-cmo-review.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/james-munluah/agent-operating-system/HEAD/agents/cmo-review.md -o ~/.claude/agents/james-munluah-agent-operating-system-cmo-review.md Restart Claude Code, or start a new session, for it to be picked up.
What Cmo Review does
name: cmo-review description: Fresh-eyes brand & conversion review for public-facing UI and customer-facing copy. Read-only. Dispatched by the review runner. tools: Read, Grep, Glob model: sonnet
You are a brand & conversion reviewer. Review the current change for brand and conversion ONLY. Do not fix, only report.
- Read
agents/lenses.mdand apply the CMO section. - Inspect the diff/files you are pointed at; check against
docs/BRAND.md. - Report findings as
file:lineitem
Alternatives in Design
- Codemod Runner — Writes and runs codemod scripts that replace hardcoded visual values with token references in ui/src/index.css 79.4k ★
- Design Producer — Agent visual & production — asset list, brief anh/carousel/video, brand guideline, design review, HTML email/l 554 ★
- Omd Designer Review — Visual + brand consistency reviewer 465 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Comptroller Review
Fresh-eyes accounting-treatment & control-design review for changes that compute, display, or decide a money f
Brand Reviewer
Reviews a finished piece of copy, design or messaging against the project's brand profile and the relevant rul
Kimi Review
Use this agent when Claude wants an independent second-pair-of-eyes review from Kimi over a working-tree diff
Architecture Adversary
Fresh-context, refute-framed DESIGN-quality review of a proposed fix (a §0 plan or a diff). Hunts BAND-AID / s
Qp Slop Reviewer
Read-only reviewer for the quality-pass slop & honesty dimension — fabricated stats, placeholder copy, fake UI
Agent Safety Reviewer
Read-only review of model-facing behaviour: tool risk classification, approval gating and its UX, prompt-injec
Related Skills
Double Check
Great, now I want you to carefully read over all of the new code you just wrote and other existing code you ju
Goalpost
Your agent says “All tests pass!” The hidden tests say 28/34. goalpost makes Claude Code's /goal prove it: fro
Auto Dev Merge
PHASE 2 of an auto-dev worker — land the already-ready PR via merge-pr, in a fresh context. Dispatched by the