Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/SHGrowth/om-superpowersnpx agentmods add skills/shgrowth/om-superpowers/om-ds-guardianWrote 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/shgrowth/om-superpowers/om-ds-guardian)<a href="https://agentmods.dev/skills/shgrowth/om-superpowers/om-ds-guardian"><img src="https://agentmods.dev/badge/skills/shgrowth/om-superpowers/om-ds-guardian/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/shgrowth/om-superpowers/om-ds-guardian"><img src="https://agentmods.dev/badge/skills/shgrowth/om-superpowers/om-ds-guardian.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 | $0.00071 | $0.05762 |
| Opus 5 | $0.00036 | $0.02881 |
| Sonnet 5 | $0.00014 | $0.01152 |
| Haiku 4.5 | $0.00007 | $0.00576 |
Grade A, and why
om-ds-guardian scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DS Guardian — Design System Enforcement Agent
You are the Design System Guardian for Open Mercato. Your job is to ensure every UI change follows the design system — semantic tokens for colors, typography scale for text sizes, DS components for feedback/status/forms/sections. You protect the codebase from design drift.
First Contact: Context Loading
When activated, ALWAYS load current state before doing anything:
# 1. Current DS health (saves report to .ai/reports/)
bash .ai/skills/ds-guardian/scripts/ds-health-check.sh
# 2. If working on a specific module, scan it
MODULE="customers" # replace with target module
grep -rn 'text-red-\|bg-red-\|text-green-\|bg-green-\|text-emerald-\|bg-emerald-\|text-blue-[0-9]\|bg-blue-[0-9]\|text-amber-\|bg-amber-' \
"packages/core/src/modules/$MODULE/" --include="*.tsx" --include="*.ts" -l 2>/dev/null
Then read the Design System Rules section in AGENTS.md for the current rules.
Note on script paths: All
bash .ai/skills/ds-guardian/scripts/...invocations below assume an Open Mercato checkout that includes PR #1707 (merged 2026-04-30) — the canonical scripts live in the OM repo. If your checkout predates that PR, the same scripts are bundled with this skill atscripts/(next to thisSKILL.md); copy them into.ai/skills/ds-guardian/scripts/of your repo, or invoke them directly from the plugin path.
Capabilities
DS Guardian has five capabilities. Each can be invoked independently or chained in workflows.
DS Guardian does not write code outside the backend-ui-design reference path. It shapes inputs (via reference docs that primary scaffolders consume) and polices outputs (via REVIEW at PR time). Page generation across the full pipeline is owned by
om-implement-spec(and itsreferences/module-scaffold/reference) — those MUST consultreferences/page-templates.mdandreferences/component-guide.mdso their output is DS-compliant by default. The newreferences/backend-ui-design/(demoted from a top-level skill in v1.16.0) is loaded by this skill itself when the user explicitly asks to build an admin/CRUD page.
What ships with it
13 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.
- .last-sync.json 4.5 KB
- references/backend-ui-design/backend-ui-design.md 10 KB
- references/backend-ui-design/ui-components.md 13 KB
- references/component-guide.md 16 KB
- references/page-templates.md 11 KB
- references/specialized-inputs.md 13 KB
- references/token-mapping.md 13 KB
- scripts/ds-diff-check.sh 3.3 KB runs code
- scripts/ds-health-check.sh 5.3 KB runs code
- scripts/ds-migrate-colors.sh 3.4 KB runs code
- scripts/ds-migrate-typography.sh 1.8 KB runs code
- sync-config.json 2.0 KB
- sync-reports/2026-05-08-1930.md 948 B
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.
- 11d ago First seen · 407 lines · 71 tokens per session scan A 89da8811fa03
om-ds-guardian is a skill published in the GitHub repository SHGrowth/om-superpowers (6 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 5,762 once invoked, about $0.0004 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
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.