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/structure-decidenpx skills add aziontech/webkit --skill structure-decidegit 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 | $0.00030 | $0.00635 |
| Opus 5 | $0.00015 | $0.00318 |
| Sonnet 5 | $0.00006 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
structure-decide 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: structure-decide
Purpose
Apply the shadcn-vue rule consistently:
Use Composition Pattern only when the consumer needs to reorder or omit parts the root exposes. Otherwise, monolithic with props + slots.
When in doubt, choose monolithic. Atoms (Button, IconButton, Tag, Badge, Spinner, Currency) are always monolithic.
When to invoke
- During
/spec-create, before writing thestructure:frontmatter. - Re-check during
/component-createwhen the spec isapproved(defense in depth).
Inputs
- The spec's Purpose, Props, Slots, and Sub-components sections (or the user's verbal description during
/spec-create). - The
figma-discoverJSON if available (for theregionsarray).
Workflow
- Apply the decision tree:
- If the spec lists Sub-components →
composition. - If the regions array includes a header + body + footer with optional reordering or omission →
composition. - If the component is an atom (no slots beyond
default, no sub-anatomy) →monolithic. - If the component has props + slots but fixed layout →
monolithic. - Otherwise →
monolithic(default when in doubt).
- If the spec lists Sub-components →
- Reference the canonicals to confirm:
- Composition: Dialog, Tabs, Accordion, composed Card, DropdownMenu, Sheet/Drawer, Form fields.
- Monolithic with slots:
card-pricing.vue(fixed layout, slot inversions). - Atomic:
button.vue,icon-button.vue.
- Emit a single line with the verdict and a one-sentence rationale:
orstructure: composition rationale: Consumer reorders/omits Header, Body, Footer.structure: monolithic rationale: Fixed layout with optional default + actions slots.
Outputs
- Two lines:
structure: <verdict>andrationale: <one sentence>.
Rules
- Do not choose Composition reflexively for "complex" components — the decision is about reordering, not about size.
- Do not restate the shadcn-vue criterion in the output — just the verdict and rationale.
- Do not edit the spec from this skill (the orchestrator writes the frontmatter).
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 · 72 lines · 30 tokens per session scan A 0656385d0b83
structure-decide is a skill published in the GitHub repository aziontech/webkit (2 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 635 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 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…