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 bharat3645/The-Ideal-Harness --skill design-critiquegit clone --depth 1 https://github.com/bharat3645/The-Ideal-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/bharat3645/the-ideal-harness/design-critique)<a href="https://agentmods.dev/skills/bharat3645/the-ideal-harness/design-critique"><img src="https://agentmods.dev/badge/skills/bharat3645/the-ideal-harness/design-critique/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/bharat3645/the-ideal-harness/design-critique"><img src="https://agentmods.dev/badge/skills/bharat3645/the-ideal-harness/design-critique.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 | $0.00067 | $0.00722 |
| Opus 5 | $0.00034 | $0.00361 |
| Sonnet 5 | $0.00013 | $0.00144 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
design-critique 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 12d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design critique
A checklist run against your OWN output before you show it, not a linter run after the fact. This is the one home for several related ideas (hallmark's pre-emit self-critique, a slop-gate list, astryx-style token discipline) folded into a single skill rather than several overlapping ones or a whole new source module — the value here is procedural judgment, which is what a skill is for; building deterministic tooling around subjective taste would be false precision.
Slop gates — catch these before emitting
- Generic AI-visual-cliché markers: purple/blue gradient backgrounds with no reason, emoji used as section icons, everything centered regardless of content type, decorative rounded corners/shadows applied uniformly instead of purposefully, stock-phrase headers ("Unlock the power of...").
- Padding/spacing that wasn't decided, just defaulted. If every gap is the same "safe" value, that's the tell of not having actually looked at the layout.
- Copy that describes instead of communicates. "This section shows your recent activity" above a list literally showing recent activity is filler, not information.
Pre-emit self-critique (do this last, right before showing the work)
Look at what you are about to output and ask, plainly: would someone who does this for a living ship it, or does it read as generated? If the honest answer is "generated," name the specific reason (not "needs polish") and fix that one thing before emitting — vague dissatisfaction doesn't converge, a named defect does.
Taste dials — calibrate, don't default
State (even briefly, to yourself) where this piece sits on the axes that matter for its context: formal ↔ playful, dense ↔ spacious, bold ↔ restrained. A dashboard for financial data and a landing page for a kids' app should not default to the same visual voice.
Token-contract check
If the project already defines a design-token system (CSS custom properties, a Tailwind config, a
theme object), every color/spacing/type value in new work should reference a token, not a one-off
magic value — an unreferenced #3b82f6 next to a token file that defines --color-primary is a
drift bug, not a style choice. If no token system exists, this check doesn't apply — don't invent
one uninvited.
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.
- 12d ago First seen · 55 lines · 67 tokens per session scan A a7abad1814db
design-critique is a skill published in the GitHub repository bharat3645/The-Ideal-Harness (5 stars, last pushed 2d ago), licensed MIT. It adds 67 tokens to every session and 722 once invoked, about $0.0003 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 skills, from other repositories
pn-animation
Motion philosophy and governance for web interfaces. Covers the motion role taxonomy (Reveal/Orient/Confirm/Delight), library selection guide, motion budgets by page mode, prefers-reduced-motion compliance, and motion map output format. Use when designing a motion system, auditing animations, or choosing libraries.…
pn-color-system
Color system design and implementation: OKLCH color space, tinted neutrals, palette structure, contrast, dark mode architecture, and token hierarchy. Use when establishing color tokens, theming, dark mode, or reviewing color choices.
pn-design-system
Establishes or maintains a design system: tokens, CSS variables, spacing/type scales, theming, and consistency auditing. Use when defining tokens or auditing components. The pn-design-system rule enforces token usage when editing CSS/SCSS files.
pn-frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use when building web components, pages, or apps (React, Astro, Next.js, vanilla HTML/CSS). Avoid generic AI aesthetics.
pn-frontend-design-philosophy
Defines an authoritative, brand-agnostic frontend design rulebook. Use when designing or reviewing frontends, typography audit, layout audit, state architecture, performance budget, responsive/mobile/touch design, or when establishing design constraints for mixed visual/motion/media/form/conversion sites.
pn-figma-design-to-code
Implements designs from Figma with design-to-code workflow, token extraction, and component mapping. Use when implementing from Figma; ensures fidelity to design specs.