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 Eliyce/paqad-ai --skill design-system-syncgit clone --depth 1 https://github.com/Eliyce/paqad-aiWrote 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/eliyce/paqad-ai/design-system-sync)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/design-system-sync"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/design-system-sync/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/eliyce/paqad-ai/design-system-sync"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/design-system-sync.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 | $0.00030 | $0.00904 |
| Opus 5 | $0.00015 | $0.00452 |
| Sonnet 5 | $0.00006 | $0.00181 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
design-system-sync 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 9d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What It Does
When a token, component, or breakpoint is added to source (Tailwind theme entry, design-token export, new component file), this skill updates the matching contract clause in docs/instructions/design-system/* so the contract stays in step with reality. Mirror of canonical-doc-sync, scoped to the design system.
Use This When
Use this from the documentation_sync stage of feature-development.yaml whenever the diff touches:
src/design-tokens/**tailwind.config.*src/components/**(added/removed components)- A CSS-in-JS theme provider definition
Also runs during design-test Step 5 when a finding's resolution implies the contract should expand (e.g. a documentation-drift finding noting a token used in code but not declared).
Inputs
- Read the diff (
git diff --name-only HEAD). - Read the current
docs/instructions/design-system/*.mdfiles. - Read
references/sync-rules.md.
Procedure
Proposal generation is deterministic — the scripts produce unified-diff hunks ready for the Decision Pause Contract. The LLM never hand-writes the diff.
- Capture the current diff:
git diff HEAD > /tmp/sync.diff(or read from the workflow's staged diff). - Run
scripts/detect-token-additions.sh /tmp/sync.diff→<key>\t<value>rows for every added token-shaped entry (accepts identifier and quoted-numeric keys; only token-shaped values: hex/px/rem/em). - Pipe those rows into
scripts/propose-tokens-diff.sh→ a unified-diff hunk targetingdocs/instructions/design-system/tokens.md. Surface this hunk to the user via the Decision Pause Contract. - Run
scripts/detect-component-additions.sh /tmp/sync.diff→<Component>\t<source-file>rows for every newly-added component file (uppercase-named, undersrc/components/, not a test/spec/story/barrel/type decl). - Pipe those rows into
scripts/propose-components-diff.sh→ a unified-diff hunk forcomponents.mdwith the default skeleton (variants: TBD, states: default/hover/focus/disabled, composition: TBD). - Never auto-apply. Surface every proposal via the Decision Pause Contract; the user accepts, modifies, or rejects each.
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.
- agents/openai.yaml 160 B
- assets/output.template.md 497 B
- references/sync-rules.md 1.3 KB
- scripts/detect-component-additions.sh 2.0 KB runs code
- scripts/detect-token-additions.sh 2.1 KB runs code
- scripts/lint-findings.sh 1.7 KB runs code
- scripts/propose-components-diff.sh 1.2 KB runs code
- scripts/propose-tokens-diff.sh 1.2 KB runs code
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.
- 9d ago First seen · 77 lines · 30 tokens per session scan A 8c7cb0a91ba9
design-system-sync is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 904 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
double-diamond
A four-stage design method for understanding a problem, defining it clearly, exploring possible solutions, and choosing one to deliver.
make-interfaces-feel-better
Use when building or reviewing UI polish: typography, hit areas, nested radius, optical alignment, shadows, media outlines, micro-interactions, and animation performance.
frontend-skill
Use when the task asks for a visually strong landing page, website, app, prototype, demo, or game UI. This skill enforces restrained composition, image-led hierarchy, cohesive content structure, and tasteful motion while avoiding generic cards, weak branding, and UI clutter.
frontend-skill
Use when the task asks for a visually strong landing page, website, app, prototype, demo, or game UI. This skill enforces restrained composition, image-led hierarchy, cohesive content structure, and tasteful motion while avoiding generic cards, weak branding, and UI clutter.
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
infographics
Create professional infographics using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Integrates research-lookup and web search for accurate data. Supports 10 infographic types, 8 industry styles, and colorblind-safe palettes.