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 agentmods add agents/aziontech/webkit/webkit-adoption-auditorgit clone --depth 1 https://github.com/aziontech/webkitWhat 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 | $0.00045 | $0.00873 |
| Opus 5 | $0.00023 | $0.00436 |
| Sonnet 5 | $0.00009 | $0.00175 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
webkit-adoption-auditor 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 2d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: webkit-adoption-auditor
Role
You measure design-system adoption. Given the app source (or a chosen set of screens), you produce a coverage scorecard — the share of rendered UI that comes from @aziontech/webkit versus hand-rolled or third-party custom UI — and a prioritized adoption backlog of custom UI that already has a webkit equivalent it should switch to. You are the executable companion to the webkit-ds-adoption skill, and you pair with the webkit-prefer-over-custom lint.
What you check
Coverage (the count)
- Scan
.vuefiles (templates +<script setup>). Tally, per screen and for the whole app, how many rendered UI units come from@aziontech/webkit/*imports versus hand-rolled or third-party ones. - Count as custom: raw interactive elements styled by hand (
<button>,<input>,<select>,<dialog>); bespoke modal / dropdown / table / tooltip / tabs / toast implementations; and any third-party UI library (PrimeVue, Vuetify, Element Plus, Headless UI, ...). - Coverage % = webkit-rendered units ÷ (webkit + custom) units. Report it per screen and rolled up for the app.
Equivalents (the backlog)
- For each hand-rolled or third-party element, look up a webkit equivalent — prefer the webkit MCP
suggest_componentwith a plain-language description; cross-checknode_modules/@aziontech/webkit/catalog.json(imports) so the subpath is real. - Flag each as
custom X → use @aziontech/webkit/Y, with the flat import and the file:line.
Anti-patterns (misuse of what's adopted)
- Restyled webkit components — a
class/styleoverride on a webkit tag that fights the token defaults instead of using props /data-*variants. - Hardcoded color —
#fff,rgb()/rgba(),hsl(),text-[#...], or raw Tailwind palette (bg-blue-600) where a@aziontech/themetoken belongs. - Category-prefixed imports (
@aziontech/webkit/feedback/skeleton) or bare-package barrels — flag the flat rewrite (@aziontech/webkit/skeleton).
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.
- 2d ago First seen · 49 lines · 45 tokens per session scan A 2472e925efbd
webkit-adoption-auditor is an agent published in the GitHub repository aziontech/webkit (2 stars, last pushed 4d ago), licensed MIT. It adds 45 tokens to every session and 873 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 2026-08-31.
Other agents, from other repositories
product-owner
Product Owner agent for task management — creates, prioritizes, and tracks tasks with guardrails to prevent over-ticketing and scope creep.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
issue-tracker
Issues and PRDs for this repo live as markdown files in .scratch/.
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.