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 agent-scope-limitsgit 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/agent-scope-limits)<a href="https://agentmods.dev/skills/cruzs85/opencode-multiagente-local-37-iterations/agent-scope-limits"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/agent-scope-limits/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/agent-scope-limits"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/agent-scope-limits.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 | $0.00691 |
| Opus 5 | $0.00000 | $0.00345 |
| Sonnet 5 | $0.00000 | $0.00138 |
| Haiku 4.5 | $0.00000 | $0.00069 |
Grade A, and why
agent-scope-limits 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 9d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: agent-scope-limits
Propósito
Evitar que agentes correctores (QA validator, code-writer en modo corrección) reescriban archivos más allá del cambio solicitado o introduzcan nuevas dependencias no autorizadas.
¿Cuándo usarla?
Siempre que un agente vaya a corregir errores en archivos existentes.
Reglas para QA Validator
Modo solo-reporte (OBLIGATORIO)
✅ PERMITIDO: Ejecutar npm run build y npm test
✅ PERMITIDO: Reportar errores con archivo, línea, código actual y código esperado
✅ PERMITIDO: Delegar la corrección a code-writer con instrucciones mínimas y precisas
✅ PERMITIDO: Indicar el tipo de error (Sintaxis, Arquitectura, Lógica)
❌ PROHIBIDO: Reescribir archivos completos usando bash + cat ❌ PROHIBIDO: Cambiar la estructura de datos del servicio (ej: mover señales dentro de un objeto) ❌ PROHIBIDO: Añadir dependencias nuevas no solicitadas (rxjs, BehaviorSubject, etc.) ❌ PROHIBIDO: Refactorizar métodos que no tienen errores de compilación ❌ PROHIBIDO: Cambiar la lógica de negocio para "mejorarla"
Si un error persiste tras 3 iteraciones
- NO reescribir el archivo
- Escalar al decomposer con el log completo de errores
- El decomposer determinará si se necesita un refactor estructural
Reglas para code-writer (en modo corrección)
Principio de mínimo cambio
✅ PERMITIDO: Crear nuevos archivos según especificación ✅ PERMITIDO: Modificar líneas específicas para corregir errores de compilación ✅ PERMITIDO: Cambiar types, firmas de métodos o imports rotos ❌ PROHIBIDO: Refactorizar código que funciona y no tiene errores ❌ PROHIBIDO: Añadir librerías no solicitadas ❌ PROHIBIDO: Cambiar la estructura de datos acordada en el plan original ❌ PROHIBIDO: Renombrar métodos o propiedades que ya funcionan
Excepción: refactor autorizado
Un refactor solo está permitido si:
- El decomposer lo autoriza explícitamente en el plan
- El cambio es necesario para corregir un error de compilación
- Se limita estrictamente al archivo y líneas con errores
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.
- 9d ago First seen · 61 lines · 0 tokens per session scan A 3def91d225af
agent-scope-limits is a skill published in the GitHub repository cruzs85/opencode-multiagente-local-37-iterations (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 691 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…