Wh Eval Designer — Design agent for Claude Code
Design-phase agent, tier 2 and above only.
How to install Wh Eval Designer
Installs to ~/.claude/agents/muhibm1-workhorse-snapshot-wh-eval-designer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/muhibm1/workhorse-snapshot/HEAD/agents/wh-eval-designer.md -o ~/.claude/agents/muhibm1-workhorse-snapshot-wh-eval-designer.md Restart Claude Code, or start a new session, for it to be picked up.
What Wh Eval Designer does
name: wh-eval-designer description: Design-phase agent, tier 2 and above only. Reviews and extends the evals.md the designer wrote: adds the edge, failure and adversarial cases whose failure would change a decision, cuts cases a machine cannot run, and appends the matching test step to the plan.md task that owns each added case, within the tier's case limit. Use after wh-designer, in parallel with the constraint auditor. tools: Read, Glob, Grep, Write, Edit model: sonnet effort: medium skill
Alternatives in Design
- Workflow Architect Agent — Workflow design specialist who maps complete workflow trees for every system, user journey, and agent interact 669 ★
- Omd A11y Auditor — Stage 0 deterministic gate of the eval pipeline 465 ★
- API Platform Reviewer — API platform / dev-API pre-implementation reviewer 83 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Agent Eval Engineer
Use to design and run regression evaluations for an agent, skill, tool, or prompt — happy-path, edge-case, adv
Game Critic
Adversarial validator for game-design proposals. Finds counter-examples, known failure cases, and post-mortem
Media Producer
Produces short-attention media - feature demo videos, social cuts, screenshots, generated images - built as co
Robo Reviewer
Adversarial design and code review for robotics. Hunts failure modes, runs FMEA, checks safety-path integrity,
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/
Statistician
Statistical rigor advisor: experimental design, signal-vs-noise, pressure-testing metric claims, sample-size a
Related Skills
Canary Test Pipeline
Run the full test intelligence pipeline — assess critical areas, discover edge cases, trace failure impact, ge
Adversarial Test
Post-build adversarial review — a fresh agent stress-tests recent changes for bugs, regressions, conflicts, an
Motion Reel
Agent skill for motion-designer-grade websites and code-rendered videos: kinetic type, full-bleed color cuts,