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 token-conformance-reviewgit 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/token-conformance-review)<a href="https://agentmods.dev/skills/eliyce/paqad-ai/token-conformance-review"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/token-conformance-review/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/token-conformance-review"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/token-conformance-review.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 | $0.00039 | $0.01398 |
| Opus 5 | $0.00019 | $0.00699 |
| Sonnet 5 | $0.00008 | $0.00280 |
| Haiku 4.5 | $0.00004 | $0.00140 |
Grade A, and why
token-conformance-review 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 8d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What It Does
Scans UI source for hard-coded design values that should resolve back to a declared token: hex literals, raw px/rem/em, unregistered color names, ad-hoc font stacks, magic shadow values. The presence of color.primary.500 in tokens.md while a component inlines #1a73e8 is a finding, not a stylistic preference.
token findings default to high severity — this is the load-bearing check for "is the design system actually being followed."
Use This When
Use this for every design-test run. It is one of the two primary "is the contract followed" skills, alongside component-conformance-review.
Inputs
- Read
docs/instructions/design-system/tokens.mdto know what's declared. - Read the contract-summary from
design-system-coverage(lists every declared token name). - Read
references/token-leak-checklist.mdbefore scanning. - Read
tailwind.config.*if present — Tailwind theme entries count as tokens too.
Procedure
The mechanics are deterministic — drive them with the scripts in scripts/
rather than re-deriving them on every finding. Reserve LLM reasoning for the
"is this leak resolvable to which token" judgment, not for parsing files.
- Run
scripts/parse-tokens.sh <tokens.md>once and persist the TSV (<name>\t<value>\t<namespace>). This is the declared truth. - Run
scripts/scan-tokens.shto grep the source roots for hard-coded value patterns. Each hit is an investigation candidate. - For each leak hit, run
scripts/match-leak-to-token.sh --leak <value> --tokens <parsed.tsv> [--namespace <ns>]. It usesscripts/normalize-color.shinternally so#1A73E8,#1a73e8, andrgb(26,115,232)all resolve to the same canonical form. The output is one of:match\t<token-name>→ emit atokenfinding, high severity.Required action:writes itself: replace<leak>at<file>:<line>with<token-name>fromtokens.md.ambiguous\t<n1>,<n2>...→ still a finding; pick the more specific token (most dotted segments) and explain the alternatives in the finding body.no-match→ emit a paralleldocumentation-driftfinding pointing at the gap in the contract; the token leak finding becomesmediumuntil the gap is filled.
- If the hit lands inside a known exemption path (
**/*.test.*,**/*.stories.*,**/__tests__/**,src/design-tokens/**,tailwind.config.*) the scanner already drops it — never re-check those manually.
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 182 B
- assets/output.template.md 839 B
- references/token-leak-checklist.md 2.4 KB
- scripts/lint-findings.sh 1.7 KB runs code
- scripts/match-leak-to-token.sh 2.9 KB runs code
- scripts/normalize-color.sh 2.4 KB runs code
- scripts/parse-tokens.sh 1.8 KB runs code
- scripts/scan-tokens.sh 2.4 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.
- 8d ago First seen · 89 lines · 39 tokens per session scan A d6c39c024d34
token-conformance-review is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 1,398 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
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-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Use whenever the task produces or modifies anything a user will see rendered — websites, landing pages, web apps, dashboards, React/HTML/Vue components, artifacts with visual output, style overhauls, or "make this…
frontend-design
Produce intentional, responsive, accessible UI work and perform visual QA instead of generic component assembly.
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
accessibility-a11y
Semantic HTML, keyboard navigation, focus states, ARIA labels, skip links, and WCAG contrast requirements. Use when ensuring accessibility compliance, implementing keyboard navigation, or adding screen reader support.