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 design-loopgit 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-loop)<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/design-loop"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/design-loop/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-loop"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/design-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.02134 |
| Opus 5.5 | $0.00032 | $0.00854 |
| Sonnet 5.5 | $0.00016 | $0.00427 |
| Haiku 4.5 | $0.00008 | $0.00213 |
Grade A, and why
design-loop 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 1mo 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Loop — the front door of the design area
A reference you can open, mechanisms you can check, and three judges who did not build the thing.
This is where a design request enters. It owns the method: the bar, the judges, the rounds. It
does not own the visual system — ../design/SKILL.md does, and this skill invokes it as the builder.
Why the method and not a rubric. A rubric scored by whoever built the piece measures intent, because the builder knows what they were going for and so they see it there. And scores drift upward every round: a 7 that becomes an 8 with nothing changed is how a loop declares itself finished early. Binary verdicts from someone who did not build it are the fix for both.
Four phases. Do not skip ahead, and do not start building during 1 to 3.
Phase 1 — Interview
Ask exactly these three, together, then stop and wait.
- What are you building, and how long or how big?
- Name something that already does this brilliantly — a site, a video, a doc, anything I can open. If nothing comes to mind, say skip.
- Any files I should work from? Design system, brand doc, script, existing draft.
A vague bar is the number one reason this method fails. If they name something vague ("Apple's website", "good SaaS design"), push once for the specific page or file: a critic with no concrete reference invents the comparison and approves everything on round one.
On skip, propose three candidate bars, one line each on why, and wait. No answer → take the
hardest one and say so. Where they come from: ../design/references/starting-point.md — run its
step 0 first, because a bar the project already owns outranks anything you would pick from outside,
and proposing from memory is how this promise used to resolve to the AI-template median.
Where to go looking. For a whole page to beat, and for the flows and single patterns behind it:
../design/references/inspiration-sources.md. For a component idea rather than a whole reference:
a gallery of real products. Browse for the technique, never to clone a
competitor's exact grid — and come back with a specific page you can open, because a gallery
is not a bar.
What ships with it
2 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.
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.
- 1mo ago First seen · 161 lines · 79 tokens per session scan A 22094c8e045e
design-loop is a skill published in the GitHub repository ericrisco/rsc-harness (237 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 2,134 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
demand-elegance
Challenges hacky fixes on non-trivial changes.
desktop-brand-builder
Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop.
dataviz
Design guidance for charts, graphs, dashboards, maps, and data visualizations, including a local palette validator.
sage-review
Deep, platform-neutral code review for PRs and CRs in ONE thorough single pass — design reasoning (Problem Worth Solving & Solution Fit) as one dimension alongside the 9 code-level dimensions, with chain-of-consequences, self-critique, and draft-only comments. The single app-owned source of truth.
ui-mockup
Create UI mockups at three fidelity levels — ASCII wireframes for quick iteration, standalone HTML mockups for delivery with requirements, and live prototypes for interaction testing.
atomic-visual-options
Planning-phase visual comparison aid. Renders 2-4 side-by-side variants per decision dimension as a single throwaway, self-contained HTML file and captures the user's pick as typed terminal codes (e.g. "A2 B3"). Auto-fires on phrases like "show me a few options", "mock up some variants", "let me see this side by…