Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/zanwei/harness-design/claude-mdgit clone --depth 1 https://github.com/zanwei/harness-designWrote 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/instructions/zanwei/harness-design/claude-md)<a href="https://agentmods.dev/instructions/zanwei/harness-design/claude-md"><img src="https://agentmods.dev/badge/instructions/zanwei/harness-design/claude-md.svg" alt="Measured on agentmods" 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 | $0.00696 | $0.00696 |
| Opus 5 | $0.00348 | $0.00348 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
harness-design CLAUDE.md scanned grade A with 0 findings 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 5d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Claude Code marketplace plugin for design-dna downstream QA. Bundles a single skill that scores generated HTML against both a Design DNA JSON spec and the original reference website using browser-based visual verification.
Root README files follow design-dna: README.md (English), README.zh-CN.md, README.ja.md, README.ko.md, README.es.md, README.zh-TW.md, with the same centered title and cross-linked language bar.
Architecture
| Path | Role |
|---|---|
.claude-plugin/marketplace.json |
Plugin metadata, version, and skill paths |
skills/harness-design/ |
SKILL.md + references/ (rubric, verification checklist, browser procedures) |
The skill uses browser MCP tools (navigate, screenshot, network_requests, console_messages, profiling) and optionally the web-shader-extractor Playwright scripts for resource collection.
Workflow
- design-dna Phase 2 → DNA JSON (from reference URL)
- design-dna Phase 3 → HTML output
- harness-design → 5-pass verification (resource audit + mechanical + visual comparison + perceptual + effects), weighted score, correction loop
The harness does not edit the DNA JSON; it only adjusts generated markup/CSS/JS to match the spec and reference.
5-Pass Verification
| Pass | Name | Tools Used |
|---|---|---|
| 0 | Resource Audit | fetch-rendered-dom.mjs (Playwright) or browser_network_requests + browser_console_messages |
| 1 | Mechanical Checks | browser_snapshot + getComputedStyle injection + DNA JSON matching |
| 2 | Visual Comparison | browser_take_screenshot + browser_scroll (section-by-section) |
| 3 | Perceptual Review | Screenshot-informed qualitative assessment |
| 4 | Effects Audit | Frame sampling + browser_profile_start/stop + auxiliary skills |
Auxiliary Skills
| Effect Type | Skill | Usage |
|---|---|---|
| WebGL / Shader / Canvas | web-shader-extractor |
fetch-rendered-dom.mjs for resource collection, scan-bundle.sh for framework ID, shader param extraction |
| ScrollTrigger / GSAP | gsap-scrolltrigger |
Scroll trigger position identification, pin/scrub verification |
| Three.js / 3D | 3d-web-experience |
3D engine analysis, rendering verification |
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.
- 5d ago First seen · 53 lines · 696 tokens per session scan A d8a60964f5e9
harness-design CLAUDE.md is an instructions file published in the GitHub repository zanwei/harness-design (4 stars, last pushed 4mo ago), licensed MIT. It adds 696 tokens to every session, about $0.0035 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
webdev-agent-kit AGENTS.md
Instructions for ytvee-dev/webdev-agent-kit, covering webdev agent kit runtime policy, purpose, precedence and approvals, context loading and workflow scale and skill discovery.
supergraph AGENTS.md
AGENTS.md instructions for datit309/supergraph, covering supergraph — mandatory workflows, skills, auto language detection, tiered workflow — pick the right tier first and full pipeline (tier 3).
MemoryCustodian GEMINI.md
Gemini CLI instructions for waittim/MemoryCustodian, covering agent instructions, memorycustodian and development.
mobile-ai-agents CLAUDE.md
Claude Code instructions for salmanashraf/mobile-ai-agents, covering claude.md — mobile ai agents, what this repo is, quick start, install everything and install by platform.
dining-places-skill AGENTS.md
AGENTS.md instructions for ddalgrande/dining-places-skill, covering agents.md, how to use it, by agent capability, the one command and ground rules.
idd-skill idd-review-fix.instructions.md
Instructions for kurone-kito/idd-skill, covering idd — review fix phase (e9–e15), e9 — fix accepted issues, e10 — validate fixes with critique pass, e11 — resolve conflicts with {development-branch} and e12 — lint, test, push.