What Breaks — Design agent for Claude Code
Opus 5 validator that pressure-tests a handed artifact — diff, PR, document, design, claim, or question — and returns an evidence-backed assessment of what fails.
How to install What Breaks
Installs to ~/.claude/agents/ryanthedev-what-skills-what-breaks.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ryanthedev/what-skills/HEAD/agents/what-breaks.md -o ~/.claude/agents/ryanthedev-what-skills-what-breaks.md Restart Claude Code, or start a new session, for it to be picked up.
What What Breaks does
name: what-breaks description: "Opus 5 validator that pressure-tests a handed artifact — diff, PR, document, design, claim, or question — and returns an evidence-backed assessment of what fails. Never edits." model: opus tools: Read, Grep, Glob, Skill
Validator brief
You are an independent validator: your job is to find what makes the artifact in front of you fail, and to say so plainly — including when the honest answer is that nothing does. Your assessment is relayed largely verbat
Alternatives in Design
- UI Visual Validator — You are an experienced UI visual validation expert specializing in comprehensive visual testing and 31.9k ★
- Chief — Head of the PO Council and eight-seat design bench 79 ★
- Web UI Route Reviewer — Use this agent for any change that adds, edits, or removes an Express route in server/index.mjs or server/lib/ 56 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Design Reviewer Facts
The evidence reviewer of the stage-2 design review round — every claim about an external tool or internal serv
Dnp Performance Analyst
⚡ .NET performance analysis — async hotspots, N+1 queries, missing caching opportunities, allocation pressure,
Codex Deep Reasoner
CLI-backed read-only deep-reasoning worker — the codex variant of deep-reasoner. Use for root-cause analysis,
Task Decomposer
Use this agent for Phase 4 (Task Decomposition) of the claude-forge. Breaks a design document into a numbered,
Pattern Conformance Reviewer
Reviews new/changed UI against the project style guide AND the implied patterns used across the codebase (e.g.
Statistician
Statistical rigor advisor: experimental design, signal-vs-noise, pressure-testing metric claims, sample-size a
Related Skills
Aegis Return Format
Sub-agent return format — every non-trivial claim must be tagged [VERIFIED: ] (backed by executed command) or
Agent Skill Builder
A skill that builds agent skills — and doesn't rot. Spec-current frontmatter plus a validator that fails on dr
Harness Engineer
Use when designing or auditing Claude Code harness infrastructure — hooks, rules, settings, constraint gaps, m