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/agents/_README.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/agents/aziontech/webkit/_readme)<a href="https://agentmods.dev/agents/aziontech/webkit/_readme"><img src="https://agentmods.dev/badge/agents/aziontech/webkit/_readme/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/agents/aziontech/webkit/_readme"><img src="https://agentmods.dev/badge/agents/aziontech/webkit/_readme.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 | $0.00000 | $0.01394 |
| Opus 5.5 | $0.00000 | $0.00558 |
| Sonnet 5.5 | $0.00000 | $0.00279 |
| Haiku 4.5 | $0.00000 | $0.00139 |
Grade A, and why
_README 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
.claude/agents/ — isolated sub-agent prompts
Each file here defines the prompt for one isolated sub-agent. The orchestrator (/component-create) invokes them via the Task tool, one phase at a time. A sub-agent sees only the prompt the orchestrator hands it — no conversation history, no other sub-agent's output, no chat memory. This is the structural guarantee that "the agent never invents."
Universal prompt envelope
Every sub-agent is spawned with this envelope (filled in by the orchestrator):
=== SPEC (verbatim, do not modify) ===
<full content of .specs/<name>.md>
=== CONSTRAINTS (binding) ===
<verbatim copy of the spec's "Constraints — DO NOT" block>
=== RULES ===
<verbatim concatenation of the .claude/rules/*.md files this sub-agent needs>
=== SKILL ===
<verbatim content of .claude/skills/<skill>/SKILL.md>
=== TASK ===
<one paragraph from the orchestrator: precise, narrow, files-named>
=== OUTPUTS ===
Return JSON: { "files_written": [...], "decisions": {...}, "blocks": [] }.
If anything is ambiguous, emit a `BLOCKED: <reason>` line and write no files.
Catalog
| Sub-agent | Skill it executes | Reads (rules) | Writes |
|---|---|---|---|
spec-author.md |
spec-create |
tokens, naming, dependencies, migration, storybook | .specs/<name>.md (draft) |
spec-validator.md |
spec-validate |
tokens, naming | spec frontmatter only (status, checksum, last_updated) |
figma-extractor.md |
figma-discover |
migration | stdout JSON only |
token-mapper.md |
token-map |
tokens | stdout Markdown only |
reuse-auditor.md |
reuse-audit |
dependencies | stdout JSON only |
structure-decider.md |
structure-decide |
naming | stdout 2 lines only |
scaffolder.md |
component-scaffold |
no-invention, naming, component-structure, props, prop-vocabulary, v-model, emits, event-payloads, slots, composables, root-element, component-states, styling, tokens, accessibility, testid, dependencies, migration | <name>.vue, sub-components, injection-key.ts, root package.json#exports |
storybook-writer.md |
storybook-write |
naming, tokens, storybook, no-invention | apps/storybook/src/stories/components/<category>/<PascalName>.stories.js |
code-connect-writer.md |
code-connect-write |
naming, migration | <name>.figma.ts |
echo-reporter.md |
echo-report |
naming, tokens, storybook | stdout report only |
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 · 81 lines · 0 tokens per session scan A 4b6772318f9e
_README is an agent published in the GitHub repository aziontech/webkit (3 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,394 tokens. 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 agents, from other repositories
ci-fixer
Applies a CI checker's findings to test targets, hooks, and pipeline definitions after re-validating each one, and records what it fixed, disproved, and left for a person.
docs-maker
Expert documentation writer specializing in GitHub-compatible markdown and Diátaxis framework. Use when creating, editing, or organizing project documentation.
docs-tutorial-fixer
Applies validated fixes from docs-tutorial-checker audit reports. Re-validates pedagogical findings before applying changes. Use after reviewing docs-tutorial-checker output.
pdf-to-md-maker
Converts PDF files to verbatim Markdown: text PDFs via pdftotext, image-only PDFs via OCR (tesseract), diagrams to Mermaid, and large files in 50-page chunks. By default it writes the .md beside the PDF under the same name.
plan-execution-checker
Audits finished plan execution in fixed order and returns the terminal verdict that permits or blocks archival.
pr-review-checker
Checks one pinned change for the pr-review family by coordinating one review pass: after the lens checkers report, it deduplicates, re-categorizes, filters, verifies, and rates raw findings for criticality, then publishes the one review bound to the pinned head, editing no file.