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.
git clone --depth 1 https://github.com/igloude/ds-skillsWrote 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/plugins/igloude/ds-skills/ds-skills)<a href="https://agentmods.dev/plugins/igloude/ds-skills/ds-skills"><img src="https://agentmods.dev/badge/plugins/igloude/ds-skills/ds-skills/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/plugins/igloude/ds-skills/ds-skills"><img src="https://agentmods.dev/badge/plugins/igloude/ds-skills/ds-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ds-skills 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.
What it actually says
{
"name": "ds-skills",
"description": "Police large volumes of AI-generated frontend work for design-system conformance, and audit the design system itself so it can be policed. Report-only: verdicts, reviews, plans, and issues — it never edits your code.",
"version": "0.5.0",
"author": {
"name": "Ian Gloude",
"url": "https://github.com/igloude"
},
"homepage": "https://github.com/igloude/ds-skills",
"repository": "https://github.com/igloude/ds-skills",
"license": "MIT",
"keywords": ["design-system", "conformance", "audit", "code-review", "tokens", "agents"]
}
What it installs
The manifest is a name and a version. 4 skills travel with it, and installing the plugin installs all of them — 118 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json 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 · 14 lines scan A 932f64f68ad6
ds-skills is a plugin published in the GitHub repository igloude/ds-skills (9 stars, last pushed 25d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
design-system-ops
Staff-level design system auditing, governance, documentation, validation, and communication — 36 skills, 4 agents, and 13 knowledge notes for the full design system lifecycle.
frontend-craft
A shared add-on for frontend development teams, with frontend instructions, helper agents, automated hooks, and connections to design tools such as Figma and Sketch. It saves reports as Markdown files.
fig
Skills for a Figma file several people share: work out its conventions, stub the screens still missing, draw them inside those conventions, wire the flow arrows, audit a page before handoff, hand sections over pinned to a version, QA what shipped, and bring the canonical page current. Installed with pm, it reads pm's…
ce-design-flow
Design-first Compound Engineering. Adds a design leg to the CE loop: brainstorm -> wireframe -> pick -> hi-fi -> plan, driven by Open Design, with a live browser portal you can chat and mark up in and a clean handoff back to your terminal.
swiftui
SwiftUI patterns and critique for iOS, macOS, and visionOS apps.
han-research
Pre-planning knowledge-work skills for the Han suite: understanding a problem before anyone commits to a plan. Home of research (research an open-ended question and end at an adversarially-validated recommendation), gap-analysis (compare two artifacts and report what is missing, incomplete, or conflicting), and…