Component Benchmark Harvester — Design agent for Claude Code
Given a component name, harvests design-system excerpts from 18 sources (design-corpora.md) and emits raw, source-attributed output to .design/benchmarks/raw/ .md.
How to install Component Benchmark Harvester
Installs to ~/.claude/agents/hegemonart-ultimate-design-component-benchmark-harvester.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/hegemonart/ultimate-design/HEAD/agents/component-benchmark-harvester.md -o ~/.claude/agents/hegemonart-ultimate-design-component-benchmark-harvester.md Restart Claude Code, or start a new session, for it to be picked up.
What Component Benchmark Harvester does
name: component-benchmark-harvester description: Given a component name, harvests design-system excerpts from 18 sources (design-corpora.md) and emits raw, source-attributed output to .design/benchmarks/raw/.md. Spawned by /gdd:benchmark. tools: Read, Write, WebFetch, Bash, Grep, Glob color: yellow default-tier: sonnet tier-rationale: "Network fetch + multi-source synthesis is open-ended; Haiku misses cross-system nuance, Opus overkill for structured harvesting." parallel-safe: co
Alternatives in Design
- Part Of Claude Forge — Github.com/sangrokjung/claude-forge — name: architect description: Software architecture specialist for system design, scalability, and technica 584 ★
- Role Design Author — Generates multi-file role analysis for a brainstorm session — analysis.md index + per-feature files + optional 530 ★
- Gdd Auditor — Independent GDD reviewer 517 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Design Authority Watcher
Fetches a curated whitelist of design-authority feeds, diffs against .design/authority-snapshot.json, classifi
Token Modeller
Modelling agent that turns raw measured or inferred values into the semantic token set and emits tokens.ts, th
Design Generator
Use after design-architect locks the brief. Generates 3 implementation variants using 21st.dev Magic MCP (2 va
Cb Feeling
CoalBoard's show-me skeptic lens (sub3) — demands demonstrated evidence (show it runs, show the proof, show th
Design Learner
Harness component 07 · learning-loop. Given one or more critic verdicts (solo design-critic or multi-critic sp
Visual Exporter
Convert a structured deepthinking thought into diagram source code. Use when the user asks to visualize, rende
Related Skills
Gql Performance Benchmark
Run GraphQL performance benchmarks against the Alkemio API and compare against a stored baseline
Hatch3r Benchmark
Run and analyze performance benchmarks. Compare results against baselines, identify regressions, and produce p
Aeo Benchmark
Benchmarks AEO performance across multiple URLs or documentation sets. Compares scores, tracks improvements ov