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 agents/aziontech/webkit/_readmegit 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 | $0.00000 | $0.01394 |
| Opus 5 | $0.00000 | $0.00697 |
| Sonnet 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 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 — 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.
- yesterday First seen · 81 lines · 0 tokens per session scan A 4b6772318f9e
_README is an agent published in the GitHub repository aziontech/webkit (2 stars, last pushed 3d ago), 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
docs-curator
Use this agent when you need to review, improve, or curate documentation files in the /apps/docs/content directory. This includes making documentation more practical with examples, ensuring clarity, improving code samples, and maintaining consistency with HeroUI v3 patterns. Context: User wants to improve…
style-migrator
Use this agent when you need to migrate HeroUI components from TypeScript-based styles (.styles.ts files using tailwind-variants) to CSS-based styles (.css files) following the BEM naming convention. This includes converting tv() configurations to CSS classes, maintaining variant mappings, and ensuring all visual…
tailwind-v4-css-expert
Use this agent when you need to analyze, create, modify, or debug Tailwind CSS v4 component CSS files. This includes identifying issues with existing CSS files, suggesting improvements, migrating styles to v4 patterns, or helping other agents (like storybook-debugger and style-migrator) understand Tailwind v4 CSS…
storybook-debugger
Use this agent when you need to debug and fix issues in the HeroUI Storybook development environment, particularly CSS transformation errors, Tailwind CSS v4 compatibility issues, or component styling problems. This includes investigating build errors, runtime errors in the browser, and issues with the CSS-to-JS…
AGENTS
The primer now lives at the repo root: ../AGENTS.md — that's the file Codex, Cursor, and Copilot read by convention, so it's the single source of truth.
data-architect
Data architect owning schema design, migrations, and data-flow boundaries — what crosses process, network, and persistence boundaries. For rea, owns the audit-log shape, last-review.json schema, policy.yaml field evolution, and audit hash-chain semantics. Designs the model that backend-engineer builds against.