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 skills add cruzs85/opencode-multiagente-local-37-iterations --skill build-scaffoldinggit clone --depth 1 https://github.com/cruzs85/opencode-multiagente-local-37-iterationsWrote 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/skills/cruzs85/opencode-multiagente-local-37-iterations/build-scaffolding)<a href="https://agentmods.dev/skills/cruzs85/opencode-multiagente-local-37-iterations/build-scaffolding"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/build-scaffolding/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/skills/cruzs85/opencode-multiagente-local-37-iterations/build-scaffolding"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/build-scaffolding.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 | $0.00018 | $0.00622 |
| Opus 5 | $0.00009 | $0.00311 |
| Sonnet 5 | $0.00004 | $0.00124 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
build-scaffolding 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 11d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validacion Post-Scaffolding
Usar DESPUES de que code-writer ejecute ng new.
IMPORTANTE: ng new es la UNICA forma de crear el proyecto. Si falla, PREGUNTAR al usuario. NO crear archivos manualmente sin autorizacion.
Pasos
- build resuelve version de Angular CLI con Context7 y la pasa a code-writer.
- code-writer crea el proyecto con
ng newusando la version recibida de build. Todo en UNA SOLA LINEA bash. - Si
ng newFALLA: build PREGUNTA al usuario que hacer (reintentar, probar otra version, detener). - Esperar a que code-writer termine completamente (task se resuelva) antes de continuar.
- Delegar a qa-validator SOLO despues de que code-writer haya terminado: "Ejecuta npm run build"
- Si el build FALLA: delegar a explorer para diagnosticar el error exacto
- Si el error es de versiones (Node, TypeScript, etc.): delegar a code-writer para corregir, luego QA otra vez
- Si falla 2 VECES: PREGUNTAR al usuario que hacer. No decidir por el.
- Si el build PASA: continuar con la implementacion de componentes
Limites
- Maximo 2 intentos de build post-scaffolding
- Si el build falla 2 veces, PREGUNTAR al usuario. No reintentar sin autorizacion.
Verificacion de tests post-scaffolding
IMPORTANTE: NO configurar Vitest manualmente. El builder @angular/build:unit-test maneja todo:
- Genera
init-testbed.jsinternamente (no necesitatest-setup.ts) - Resuelve
templateUrl/styleUrlvia el compilador Angular - No necesita instalar
@angular/platform-browser-dynamic(causa conflictos de peer deps)
Despues de npm run build exitoso, code-writer debe:
- Ejecutar
ng test --watch=false(vianpm run test -- --watch=false). - Verificar que los tests del scaffold (
app.spec.ts) pasan. - Si falla, reportar el error exacto y NO continuar con implementacion.
Errores comunes
- Node version: Angular CLI 21.x requiere Node >= 22.22.3.
- Fallback Angular < 21: Si code-writer usa version anterior, detectar y PREGUNTAR al usuario.
- Proyecto manual: Si code-writer crea package.json/angular.json a mano, las configuraciones seran incorrectas. Detectar y PREGUNTAR.
- Tareas paralelas: NO ejecutar code-writer y qa-validator al mismo tiempo. Esperar que code-writer termine.
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.
- 11d ago First seen · 45 lines · 18 tokens per session scan A 7e93853f4e5c
build-scaffolding is a skill published in the GitHub repository cruzs85/opencode-multiagente-local-37-iterations (5 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 622 once invoked, about $0.0001 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.
Other skills, from other repositories
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…