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 5.5 | $0.00007 | $0.00249 |
| Sonnet 5.5 | $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 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 — 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.
- 2mo 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 3mo ago), licensed MIT. It adds 18 tokens to every session and 622 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.
build-scaffolding compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| build-scaffoldingcruzs85/opencode-multiagente-local-37-iterations | Skill | 5 | 3mo ago | MIT | A | 18 | OpenCode |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 3d ago | MIT | A | 200 | Claude Code, Codex |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 6d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |