Borrowing it
Nothing to install: this file belongs to aziontech/webkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aziontech/webkit/main/.claude/commands/component-verify.mdgit clone --depth 1 https://github.com/aziontech/webkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/aziontech/webkit/component-verify)<a href="https://agentmods.dev/commands/aziontech/webkit/component-verify"><img src="https://agentmods.dev/badge/commands/aziontech/webkit/component-verify/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/aziontech/webkit/component-verify"><img src="https://agentmods.dev/badge/commands/aziontech/webkit/component-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00030 | $0.00392 |
| Opus 5.5 | $0.00012 | $0.00157 |
| Sonnet 5.5 | $0.00006 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
component-verify 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 2mo 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.
What it actually says
You are running /component-verify <name>. You do not write anything. You re-execute the read-only phases of /component-create against an existing component.
User input: $ARGUMENTS
What to do
- Resolve
.specs/<name>.md. If absent → exit with the path it expected. - Run
spec-validatoron the current spec content. Surface any failures. - Recompute
sha256(body)and compare to frontmatterchecksum. Mismatch → surface and exit. - Resolve the existing component dir at
packages/webkit/src/components/webkit/<category>/<name>/. Missing → exit. - Spawn
echo-reporteragainst the disk files. Surface its verdict (parity / mismatch / degraded). - Spawn
validate-component(pnpm webkit:lint, type-check, type-coverage, dts build, storybook build). - Print a one-table summary: spec status, hook verdict, echo verdict, validation pass/fail.
Rules
- Read-only. This command writes nothing — no specs, no
.vue, no logs (other than a one-line summary in.claude/logs/<run-id>.jsonl). - No retries on failure. Surface and exit. The user fixes the divergence (in the spec or in the
.vue) and re-runs. - No sub-agent spawned that writes. Forbidden:
scaffolder,storybook-writer,code-connect-writer,spec-author,spec-validator(which writes the checksum — exception: run it in dry-mode where it returns the verdict without flippingstatus).
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.
- 2mo ago First seen · 25 lines · 30 tokens per session scan A c4f5a93a14b7
component-verify is a command published in the GitHub repository aziontech/webkit (3 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 392 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
gate
Run every objective gate this project can prove and report the real N/N. Use before claiming any screen or component is done.
debug
Structured bug diagnosis and fixing workflow that reproduces, diagnoses root cause, applies a minimal fix, writes regression tests, and scans for similar patterns.
self-test
Run behavioral tests to validate stay-on-target prompts.
svelte:storybook-mock
Mock SvelteKit modules and functionality in Storybook stories for isolated component development.
test
Generate Vitest tests for Vue components or functions.
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.