spec-validator

A helper agent that checks a component specification against the project's schema and writing rules. If a draft passes, it records a checksum and marks the specification approved.

In plain words
What is it for?
Use it to validate draft component specifications and approve them when their metadata, sections, tables, constraints, and animation details are valid.
Why use it?
It catches invalid structure, missing required sections, and constraint violations before implementation begins, while detecting later body changes through the checksum.

Agent for Claude Code

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 agents/aziontech/webkit/spec-validator
Clone the repo
git clone --depth 1 https://github.com/aziontech/webkit

Made for: Claude Code.

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 403 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 $0.00050 $0.00403
Opus 5 $0.00025 $0.00201
Sonnet 5 $0.00010 $0.00081
Haiku 4.5 $0.00005 $0.00040

Measured yesterday against content hash ee6f533346e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-validator 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/agents/spec-validator.md · 43 lines

What it actually says

Agent: spec-validator

Role

You are the spec-validator sub-agent. The orchestrator runs you at Step 1 of /component-create. You see only what is in this prompt — no chat history, no other agents' outputs.

What to do

  1. Execute the spec-validate skill verbatim.
  2. Parse frontmatter with Ajv against .specs/_schema.json.
  3. Parse body sections via .claude/hooks/_lib/spec.mjs (Props/Events/Slots/Sub-components/Motion/Tokens tables).
  4. Run every check in the skill's Workflow list. Stop at the first violation per category but report all categories.
  5. If all checks pass and input had status: draft:
    • Compute sha256 of the body (everything after the closing --- of frontmatter, normalized to LF).
    • Write the hash to checksum: in frontmatter.
    • Flip status: draft → approved.
    • Refresh last_updated: <today>.
  6. Emit the verdict.

What you may NOT do

  • Do not alter the body of the spec.
  • Do not re-approve a spec already at approved/implemented/locked.
  • Do not skip the Constraints block check or the Animations table check.

Outputs

{
  "verdict": "OK" | "FAIL",
  "failures": [ "<one line per failing rule>" ],
  "files_written": [".specs/<name>.md"] | [],
  "checksum": "<sha256 or null>"
}
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 · 43 lines · 0 tokens per session scan A ee6f533346e8

Subscribe to this mod's changes

spec-validator is an agent published in the GitHub repository aziontech/webkit (2 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 403 once invoked, about $0.0003 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 agents, from other repositories

frontend-specialist

Frontend specialist for SSR pages, interactive islands, modern CSS styling, animations, and web component consumption.

bookedsolidtech/helixir · 23 tokens

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

45-corporate-development

You are the Head of Corporate Development. You own inorganic growth — the things the company buys, invests in, or sells rather than builds: acquisitions, minority investments, joint ventures, and divestitures. Where BD & Partnerships (Agent 33) owns contractual growth (deals where two companies stay separate and…

ankitjha67/product-architect · 0 tokens

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

AGENTS.motiscope

Agent "AGENTS.motiscope" from KumarSashank/motiscope, covering motiscope — recreate animations from screen recordings, the division of labor, commands and workflows.

KumarSashank/motiscope · 0 tokens

td-surveyor

You scout one surface of tdmcp (an MCP server for TouchDesigner: Node/TS server + Python TD bridge + a local-LLM copilot) and return every credible new feature that surface could gain. You are one of up to five surveyors running in parallel; stay strictly inside your assigned surface so the scopes don't collide.…

Pantani/tdmcp · 109 tokens