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 skills/aziontech/webkit/webkit-create-surfacenpx skills add aziontech/webkit --skill webkit-create-surfacegit 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 | $0.00169 | $0.02647 |
| Opus 5 | $0.00084 | $0.01324 |
| Sonnet 5 | $0.00034 | $0.00529 |
| Haiku 4.5 | $0.00017 | $0.00265 |
Grade A, and why
webkit-create-surface 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 yesterday.
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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: webkit-create-surface
Purpose
"Where does this form go?" gets asked once per module and answered differently every time. One team ships a create page, the next ships a modal for the same shape of task, a third puts an inline row in the table — and the product teaches the reader three habits for one action. The cost is not aesthetic: a modal cannot be linked or reloaded, a page thrown up over a list destroys the context the reader was working in, and a dialog that holds a nine-field form traps them in a box they cannot resize.
This skill removes the question. The surface is a property of what is being created, not a choice the module makes. Three rules decide it, and one anatomy is shared by all of them so a reader who has created one resource recognizes every other.
1. The surface rule
A first-level resource creates on a PAGE. Anything created inside a resource opens a DRAWER. Nothing creates in a dialog.
First level means a resource the primary navigation routes to directly — the things the sidebar
lists. Creating one is the whole task: the reader came to do it, nothing behind it needs to stay
visible, and the result is something they will link to, reload and share. So it gets its own URL
(/<module>/new), its own screen, no sidebar, and it survives a refresh and the back button.
Inside a resource means a thing that only exists in the context of another: a record in a zone, a rule in an application, a column in a table, a domain on a workload. Creating one is a step in work already underway. The list behind the drawer is the context, and it has to stay visible — the thing being added is judged against the things already there. A page here would throw that away and make the reader navigate back to it.
Dialogs never create. A dialog is for a short blocking decision with one answer — a confirmation, a destructive guard. The moment it holds a form, it is a drawer with worse ergonomics: no resize, no scroll room, and a stray Escape destroys typed work.
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.
- yesterday First seen · 192 lines · 169 tokens per session scan A d7b9ea92764f
webkit-create-surface is a skill published in the GitHub repository aziontech/webkit (2 stars, last pushed 4d ago), licensed MIT. It adds 169 tokens to every session and 2,647 once invoked, about $0.0008 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 skills, from other repositories
monorepo-management
Sets up or audits a monorepo workspace: tool selection, package naming, shared tooling, inter-package dependencies, selective CI, and versioning strategy. Invoked when the user asks to set up a monorepo, add a workspace, or manage multiple packages in a single repository.
bazel-monorepo-expert
Expert knowledge for managing large-scale Bazel monorepos with multiple services, shared libraries, and cross-cutting concerns. Use for workspace structure, visibility, and dependency management.
pnpm
Skill "pnpm" from pledgeandgrow/pledge-skills, covering pnpm documentation skill, key benefits, file index, quick start and install pnpm.
fast-typescript-check
Keep www-sacred's TypeScript fast to type-check and fast to run. Use when touching the ASCII/canvas animation components (the only real per-frame code here), tightening type-check wall-clock, or auditing a change for runtime or compiler regressions. Scoped to this repo — a React 19 / Next.js 16 component library plus…
port-sacred-terminal-ui-to-typescript-cli
Take a React Window.tsx (or any sacred component) and produce a terminal CLI screen written in TypeScript that uses Simulacrum — the sacred CLI framework in scripts/cli/lib/.
port-sacred-terminal-ui-to-react-using-same-conventions
Take a CLI screen written for Simulacrum — the sacred CLI framework (scripts/cli/templates/.ts or scripts/python/templates/.py) — and produce a React component that lives inside components/examples/ (or components/) using only sacred's existing primitives — Window, Card, SimpleTable, ActionButton, RowSpaceBetween…