spec-validate

A checker for Markdown component specifications. It verifies the document's frontmatter, required sections, property tables, design-token references, and constraints against defined rules.

In plain words
What is it for?
Use it to validate files in .specs/, including during component creation or a manual component verification.
Why use it?
It catches incomplete or incorrectly structured specifications before they are used to generate code. A checksum and approval status are written only when the specification passes.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/aziontech/webkit/spec-validate
Any agent
npx skills add aziontech/webkit --skill spec-validate
Clone the repo
git clone --depth 1 https://github.com/aziontech/webkit

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,083 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00041 $0.01083
Opus 5 $0.00020 $0.00541
Sonnet 5 $0.00008 $0.00217
Haiku 4.5 $0.00004 $0.00108

Measured yesterday against content hash 3f52a2ebb262, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-validate 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.

.claude/skills/spec-validate/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: spec-validate

Purpose

Decide whether a spec is good enough to drive code generation. The spec-validator sub-agent runs this skill at Step 1 of /component-create. Validation must be deterministic — same spec, same verdict.

When to invoke

  • Step 1 of /component-create <name> (orchestrator passes the spec content).
  • /component-verify <name> (manual re-check).
  • Hook test suite (against .specs/__fixtures__/*).

Inputs

  • The full text of .specs/<name>.md (frontmatter + body).
  • .specs/_schema.json (frontmatter schema).
  • .claude/docs/DESIGN.md (to verify Token references).

Workflow

  1. Parse frontmatter. Run Ajv against _schema.json. Any violation → fail with the Ajv error path.
  2. Parse body sections. Use .claude/hooks/_lib/spec.mjs to extract the Props / Events / Slots / Sub-components / Tokens tables. Fail if any mandatory section is absent or contains only TBD.
  3. Check Props table. Each row must have all five cells filled. Boolean prop names must not start with is/has. Visual variant prop must be named kind. Size prop must be named size. JSDoc cell must not be empty. The Default cell must NOT be the string literal 'undefined' or 'null' (the quoted text, not the JS value undefined): for an optional text prop use '', for a genuinely absence-meaningful prop (open, modelValue, src) use unquoted undefined. Fail with FAIL: prop <name> Default is the string 'undefined'; use '' or unquoted undefined (helper: defaultCellIsStringUndefined in .claude/hooks/_lib/spec.mjs).
  4. Check Events table. Event names must be kebab-case OR update:<prop>. Payloads must be a TypeScript type (no any, no empty).
  5. Check Slots table. Slot names must be kebab-case. Scope must be or a typed object.
  6. Check Sub-components. If structure: composition, the Sub-components section must list at least the root + one sub-component. If structure: monolithic, the section must be absent.
  7. Check Tokens. Every "Token (DESIGN.md)" cell must match one of:
    • A generated class starting with .text- and present in DESIGN.md.
    • A var(--*) that exists in DESIGN.md. No HEX, no RGB, no Tailwind palette, no external color utility.
  8. Check Constraints block. The "## Constraints — DO NOT" section must be present and must contain at least the bullets from .specs/_template.md (verbatim text check on the canonical bullets).
  9. Write checksum. If all checks pass and the input had status: draft, compute sha256(body) (everything after the closing --- of the frontmatter), write it to the checksum field, and flip status: approved. Refresh last_updated.
  10. Emit verdict. Print OK or a list of failures (one per line, with the failing line number).

Read the full file on GitHub · 68 lines

Changes

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.

  1. yesterday First seen · 68 lines · 41 tokens per session scan A 3f52a2ebb262

Subscribe to this mod's changes

spec-validate is a skill published in the GitHub repository aziontech/webkit (2 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 1,083 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.

Related

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.

soulcodex/agentic · 63 tokens

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.

kinhluan/rules-quarkus-skills · 43 tokens

pnpm

Skill "pnpm" from pledgeandgrow/pledge-skills, covering pnpm documentation skill, key benefits, file index, quick start and install pnpm.

pledgeandgrow/pledge-skills · 31 tokens

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…

internet-development/www-sacred · 84 tokens

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/.

internet-development/www-sacred · 0 tokens

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…

internet-development/www-sacred · 0 tokens