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 ivy00johns/Skill-Madness --skill design-token-guardgit clone --depth 1 https://github.com/ivy00johns/Skill-MadnessWrote 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/ivy00johns/skill-madness/design-token-guard)<a href="https://agentmods.dev/skills/ivy00johns/skill-madness/design-token-guard"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/design-token-guard/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/ivy00johns/skill-madness/design-token-guard"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/design-token-guard.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 | $0.00221 | $0.02360 |
| Opus 5 | $0.00111 | $0.01180 |
| Sonnet 5 | $0.00044 | $0.00472 |
| Haiku 4.5 | $0.00022 | $0.00236 |
Grade A, and why
design-token-guard 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 10d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design-token-guard
The problem this solves
A hardcoded color renders identically to the token it should have used.
style={{ background: "#07090c" }} and style={{ background: "var(--tl-tooltip)" }}
produce the same pixels. So every render-level gate — visual review, e2e,
screenshots, "console is clean" — passes a component that has silently bypassed
the design system. The violation only exists in source.
That is why inline styles and hardcoded CSS accumulate invisibly until someone eyeballs the code weeks later and burns hours on a token refactor. The fix is a source-level gate: a deterministic check that reads the diff for styling that bypasses the token system, run before the code is declared done, and wired into the repo so it can't regress.
This skill is that gate. It does two things:
- Audit — run the bundled checker (
scripts/check_design_tokens.py) to find every inline style and hardcoded color, each mapped to the exact token to use. - Enforce — scaffold the check into the repo (config + ESLint rule +
pre-commit hook +
lint:tokensscript) so the gate runs on every commit/CI, not just when an agent remembers to look.
It is dynamic: it auto-discovers whatever token system the project already uses and derives the rules from it. TruthLens and a vanilla Vue app are two configs of one skill, not two skills.
Step 1 — Audit
Run the checker from the project root. It needs no flags for a first pass:
python3 <skill-dir>/scripts/check_design_tokens.py --root .
What it does automatically:
- Discovers the token source — scans for CSS custom properties
(
--name: …), SCSS/Less vars ($name,@name), JS/TS theme objects, or design-token JSON. From those it builds acolor-value → tokenmap. - Scans the source tree (
.tsx/.ts/.jsx/.js/.vue/.svelte/.astro/.html), skippingnode_modules, build dirs, config files, and the token files themselves. - Reports each finding as
file:line:col, the offending snippet, and — when the literal matches a declared token — the exact fix:
What ships with it
8 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.
- 10d ago First seen · 172 lines · 221 tokens per session scan A 146d18894966
design-token-guard is a skill published in the GitHub repository ivy00johns/Skill-Madness (11 stars, last pushed 2d ago), licensed MIT. It adds 221 tokens to every session and 2,360 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.