Borrowing it
Nothing to install: this file belongs to aziontech/webkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aziontech/webkit/main/.claude/skills/token-map/SKILL.mdgit clone --depth 1 https://github.com/aziontech/webkitWrote 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/aziontech/webkit/token-map)<a href="https://agentmods.dev/skills/aziontech/webkit/token-map"><img src="https://agentmods.dev/badge/skills/aziontech/webkit/token-map/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/aziontech/webkit/token-map"><img src="https://agentmods.dev/badge/skills/aziontech/webkit/token-map.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 | $0.00034 | $0.00993 |
| Opus 5.5 | $0.00014 | $0.00397 |
| Sonnet 5.5 | $0.00007 | $0.00199 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
token-map 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 2mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: token-map
Purpose
Transform the structured JSON from figma-discover into a deterministic mapping of figma_variable → DESIGN.md token rows. Flag any Figma variable that has no equivalent as a theme gap.
When to invoke
- Step 2 of
/component-create, immediately afterfigma-discover. - Step 1 of
/spec-createwhen populating the Tokens table of a draft spec.
Inputs
- The JSON blob from
figma-discover. - The canonical catalog in
.claude/docs/DESIGN.md(mirror of DESIGN.md). - The authoritative file
.claude/docs/DESIGN.md— load read-only and use it to verify any class/var the mirror does not list.
Workflow
- Parse input JSON. Reject if
variablesis absent. An emptyvariablesarray is valid (emit an empty mapping with a comment). - For each Figma variable, classify by kind:
color/...→ look for matching semantic var (--primary,--bg-surface,--text-default, …) in DESIGN.md's "Colors" catalog.text/...→ match a generated class (.text-heading-md,.text-button-lg, …).spacing/N→ matchvar(--spacing-N).radius/...→ matchvar(--shape-*).shadow/...→ matchvar(--shadow-*).container/...→ matchvar(--container-*)orvar(--container-max-width).
- No fuzzy matching. If the Figma name does not point at an exact DESIGN.md token, emit a row with
Theme gap: yesand the closest primitive (shadow-lg,gap-2, …). - Emit two artifacts to stdout:
### Token mapping | Figma variable | Resolved to | Source | |---|---|---|
| color/surface | var(--bg-surface) | DESIGN.md |
| text/heading-md | .text-heading-md | DESIGN.md |
Theme gaps
| Figma variable | Temporary primitive | Follow-up |
|---|---|---|
| color/overlay-shadow | shadow-lg |
TODO: tokenizar |
## Outputs
- The two Markdown tables above. Nothing else.
## Rules
- **Do not** invent a DESIGN.md token that does not exist. If unsure, flag a theme gap.
- **Do not** edit DESIGN.md, the spec, or any component file.
- **Do not** restate the DESIGN.md catalog beyond the mapping — the mirror in [`tokens.md`](../../docs/DESIGN.md) is enough.
- **Do not** suggest a HEX/RGB/HSL/Tailwind palette fallback. Always use a `var(--*)` primitive or a generated class.
- **Do not** carry a Figma zero over with its unit. A Figma value of `0px` / `0em` maps to `0` — a zero length takes no unit (see [`.claude/rules/styling.md`](../../rules/styling.md)). Units that mean something at zero (`0%`, `0s`, `0deg`) map as-is, and a zero that lands inside `calc()`/`min()`/`max()`/`clamp()` maps to `0rem` (CSS requires a unit there).
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.
- 2mo ago First seen · 78 lines · 34 tokens per session scan A fff635af2655
token-map is a skill published in the GitHub repository aziontech/webkit (3 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 993 once invoked, about $0.0001 per session on Opus 5.5. 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
design-component
Design a UI component spec to the house quality bar (anatomy, variants, sizes, the 8 states, token mapping, and accessibility). Use when the user wants to design or document a component (button, input, tabs, toast, combobox, date picker, modal, etc.) at the spec level before or alongside code. For generating framework…
design-doctrine
The house rules for ANY design or UI work - the verification protocol (run the gate, never claim a number), the absolute no-emoji rule, token by intent, one shared theme, the eight states, one thing leads, and output completeness. Load this FIRST whenever building, reviewing, or theming a screen, component, or token…
design-screen
Design or build a page, screen, landing page, website, app or UI from a request - the whole job, end to end. Use this for "design a landing page", "build a settings screen", "make me a website", "design the onboarding", "ออกแบบหน้าเว็บ", "ทำหน้า landing", "ออกแบบ UI", "ทำแอป". It runs the pipeline no single skill…
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.
grill-me
Interrogate the brief before a line is built. Ask only the questions whose answers change the work, and put every unasked decision on the record as a stated assumption.
scaffold-project
Scaffold a new design-product project that matches the recommended Claude Code layout (the reference structure). Use when starting a fresh product/app that will be built with this design system.