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 instructions/damiansire/web-worker-patterns/claude-mdgit clone --depth 1 https://github.com/damiansire/web-worker-patternsWrote 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/instructions/damiansire/web-worker-patterns/claude-md)<a href="https://agentmods.dev/instructions/damiansire/web-worker-patterns/claude-md"><img src="https://agentmods.dev/badge/instructions/damiansire/web-worker-patterns/claude-md.svg" alt="Measured on agentmods" 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 | $0.00848 | $0.00848 |
| Opus 5 | $0.00424 | $0.00424 |
| Sonnet 5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
web-worker-patterns CLAUDE.md 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 4d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Cómo trabajar en este repo: fases y convenciones de código. El diseño vive en
ARQUITECTURA-multi-theme.md; los gates, el
tooling y el loop de design-review viven en
docs/AI-PROCESS.md. Este archivo era referenciado por
AGENTS.md/docs/AI-PROCESS.md como fuente de verdad pero no existía —
creado por /fragua adoptar el 2026-07-10.
Fases
- Cambios chicos y acotados, que se lean como diff — no reescrituras masivas.
- Un ejemplo nuevo = un commit por paso lógico (worker + logic.ts con test →
registro en
examples.registry.ts→ i18n → wiring por theme), no todo junto. - Parar a mostrar al terminar un hito: gates verdes (
npm run format:check,npm run build,npm test,npm run lint:boundaries), sin warnings nuevos. - Tests antes que UI: la lógica pura (
*.logic.ts) se valida con un test unitario sinTestBedantes de cablear la pantalla que la consume. - Si tocás
core/domain/, dejá un test que lo cubra.
Convenciones de código
- Commits: Conventional Commits en español (
feat(scope): …,fix(scope): …,chore(scope): …). Sin atribución a IA niCo-Authored-By. - Angular moderno únicamente: standalone components, signals
(
signal/computed/effect/input/output),inject(),ChangeDetectionStrategy.OnPushen todo componente (la app es zoneless). Nada deNgModuleni inyección por constructor. - La regla de oro (ver
AGENTS.md):core/nunca importa dethemes/. La lógica de Web Workers vive encore/domain/workers/, nunca en un theme. - Nombres por dominio: un servicio/signal se nombra por lo que significa
para el ejemplo (
workerPoolStatus,threadLane), no por su mecanismo interno (state,data,handler). - No agregues abstracciones para un caso de uso único; no diseñes para requisitos hipotéticos.
Estándar nivel mundial
Piso transversal de /fragua (fellow-standard.md del corpus,
~/.claude/tools/_audit-tools/refs/), más lo que este repo ya cumple por
construcción (boundaries auto-verificados, CI multi-harness, gate de tests
con auto-verificación en guard-tests.mjs — ver el comentario ahí sobre el
falso-verde de dependency-cruiser 16, el mismo principio que motivó este
archivo):
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.
- 4d ago First seen · 57 lines · 848 tokens per session scan A 5dfa2bac0dcb
web-worker-patterns CLAUDE.md is an instructions file published in the GitHub repository damiansire/web-worker-patterns (175 stars, last pushed 18d ago), licensed MIT. It adds 848 tokens to every session, about $0.0042 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 2026-08-30.
Other instructions, from other repositories
angular AGENTS.md
Instructions for angular/angular, covering environment, key documentation, testing and pull requests.
heroes-angular AGENTS.md
AGENTS.md instructions for johnpapa/heroes-angular, covering heroes angular — agent guide, project overview, repository structure, tech stack and build & run.
heroes-angular copilot-instructions.md
Copilot instructions for johnpapa/heroes-angular, covering copilot instructions — heroes-angular, project type, code conventions, typescript and angular components.
joint CLAUDE.md
Claude Code instructions for clientIO/joint, covering claude.md, project overview, common commands, install dependencies and build distribution files (runs grunt).
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
Claw3D AGENTS.md
Instructions for iamlukethedev/Claw3D, covering agent instructions, cursor cloud specific instructions, service overview, running the app and lint, typecheck, and tests.