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 skills add ericrisco/rsc-harness --skill designgit clone --depth 1 https://github.com/ericrisco/rsc-harnessWrote 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/skills/ericrisco/rsc-harness/design)<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/design"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/design"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/design.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00079 | $0.01559 |
| Opus 5.5 | $0.00032 | $0.00624 |
| Sonnet 5.5 | $0.00016 | $0.00312 |
| Haiku 4.5 | $0.00008 | $0.00156 |
Grade A, and why
design 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 today.
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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design
A model left to design picks the average of every page it has seen. This skill takes those decisions away from the model and makes it look at what it built.
- A script deals the direction. You choose among researched directions; you never invent one.
- The idea comes from the subject, not from the category.
- Real pictures and full content, never empty space dressed as restraint.
- A real browser measures the page at three widths. A
FAILmeans it is not done. - You look at the screenshots, fix the worst, and look again.
The engine is taste-skill (MIT), shipped unmodified in
engine/. The modes, the fresh review and the design record adapt
impeccable by Paul Bakaus (Apache-2.0). Credits and what
changed: THIRD_PARTY.md.
0. Name the surface and its mode
Decide before anything else. The mode is chosen from the surface, not from the product.
| Mode | The visitor… | Surfaces | Run |
|---|---|---|---|
| Persuade | decides and acts | landing, marketing, product site, pricing, event, local business | engine/RUN.md, the page run |
| Experience | is inside the work | portfolio, gallery, showcase | engine/RUN.md, the page run |
| Operate | completes a task | dashboard, admin, settings, inbox, editor | engine/references/app-screens.md |
| Read | understands something | docs, guide, article, changelog | the page run, under the Read rules |
What each mode allows and refuses: references/modes.md.
1. Brand first, when there is one
Look for an existing identity before dealing anything: 02-DOCS/wiki/brand/, a DESIGN.md in the
repo, or a coherent identity already in the code. If one exists, its colours and faces win: pass
--keep palette,type to the draw and take only the composition. If none exists, do not stop to
interview the user about brand; the draw is how a starting point is made.
2. Run the engine
What ships with it
44 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- engine/assets/app.css 16 KB
- engine/assets/base.css 6.4 KB
- engine/assets/base.js 2.1 KB runs code
- engine/assets/charts.js 57 KB runs code
- engine/assets/scenes/stage.css 1.1 KB
- engine/assets/scenes/stage.js 7.3 KB runs code
- engine/library/app.json 72 KB
- engine/library/directions.json 60 KB
- engine/library/heroes.json 106 KB
- engine/library/motions.json 8.8 KB
- engine/library/palettes.json 34 KB
- engine/library/photos.json 157 KB
- engine/library/sections.json 270 KB
- engine/library/sites.json 849 KB
- engine/library/type.json 80 KB
- engine/LICENSE 1.0 KB
- engine/references/app-screens.md 83 KB
- engine/references/colour.md 6.7 KB
- engine/references/copy.md 9.2 KB
- engine/references/critique.md 11 KB
- engine/references/imagery.md 50 KB
- engine/references/layout.md 18 KB
- engine/references/motion.md 54 KB
- engine/references/research.md 24 KB
- engine/references/scenes.md 9.6 KB
- engine/references/tells.md 7.2 KB
- engine/references/type.md 8.3 KB
- engine/RUN.md 37 KB
- engine/scripts/assets.mjs 63 KB runs code
- engine/scripts/draw.mjs 53 KB runs code
- engine/scripts/inspect.mjs 27 KB runs code
- engine/scripts/lib/app-draw.mjs 14 KB runs code
- engine/scripts/lib/cdp.mjs 12 KB runs code
- engine/scripts/lib/probe.mjs 79 KB runs code
- engine/scripts/lib/rules.mjs 36 KB runs code
- engine/scripts/lint.mjs 11 KB runs code
- engine/scripts/scenes.mjs 8.8 KB runs code
- engine/UPSTREAM.json 416 B
- evals/cases.yaml 2.9 KB
- IMPECCABLE-LICENSE.txt 11 KB
- references/design-md.md 1.9 KB
- references/finish-review.md 2.5 KB
- references/modes.md 2.7 KB
- THIRD_PARTY.md 1.7 KB
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.
- today Changed · -285 lines · -22 tokens per session scan C → A 1032cc8189a3
- 2d ago Changed · +36 lines · +1 tokens per session 0e8bb023a1ea
- 1mo ago First seen · 361 lines · 100 tokens per session scan C 3d1a80053489
design is a skill published in the GitHub repository ericrisco/rsc-harness (247 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 1,559 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
qa-design
UI/UX design audit and verification of web best practices, including responsive/mobile-first breakpoints. Trigger when the user wants to audit the design, verify the UI/UX, check responsive behaviour, or improve the user interface.
dev-frontend-design
Distinctive UI design with strong art direction. Trigger when the user wants to create an interface, a landing page, a visual component, or when frontend code creation is detected without a defined design direction.
dev-shadcn
Integration and customization of shadcn/ui (copy-paste React components, Radix + Tailwind). Trigger when the user wants to install shadcn, add components, customize the theme, or when shadcn/ui usage is detected in the project.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", or "vs best practices".
check-the-style
Analizza, progetta, implementa e verifica il visual design di interfacce web e mobile. Usa quando una UI esistente o in sviluppo appare debole, rumorosa, incoerente o poco rifinita, oppure quando occorre migliorare gerarchia, spaziatura, tipografia, colore, contrasto, profondità, immagini, stati, resa responsive e…
taste
Anti-slop frontend engineering directive and design taste system. Enforces brief inference, dynamic design dials, absolute prohibition of AI visual tells, and 100% full-output completion.