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 analyst-protocolgit 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/analyst-protocol)<a href="https://agentmods.dev/skills/cruzs85/opencode-multiagente-local-37-iterations/analyst-protocol"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/analyst-protocol.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 5.1 | $0.00039 | $0.00968 |
| Opus 5 | $0.00019 | $0.00484 |
| Sonnet 5 | $0.00008 | $0.00194 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
analyst-protocol 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 8d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Protocolo de Análisis Estructurado (para Analyst)
Objetivo
Este protocolo define cómo el agente Analyst debe realizar análisis profundos del código fuente, garantizando informes estructurados, trazables y libres de bucles.
Reglas Generales
- No modificar archivos durante el análisis
- Evitar bucles infinitos mediante fingerprint y límite de iteraciones
- Priorizar herramientas especializadas (grep, read, glob) sobre comandos bash
- Documentar hallazgos con estructura obligatoria
- Siempre incluir fingerprint al inicio y fin del reporte
Tipos de Análisis
📊 Análisis de Flujo
- Rastrear datos desde su origen hasta su consumo
- Identificar componentes, servicios, stores involucrados
- Mapear cadena de llamadas (método A → servicio B → store C)
🏗️ Análisis de Arquitectura
- Identificar estructura de directorios y módulos
- Detectar violaciones de patrones (NgModules, constructores, signals expuestos)
- Verificar cumplimiento de standalone components
🔗 Análisis de Dependencias
- Encontrar todos los imports y usos de una interfaz/clase
- Identificar dependencias circulares
- Mapear relaciones entre archivos
🐞 Auditoría de Bugs Potenciales
- Buscar patrones sospechosos: any, null checks faltantes, promesas sin catch
- Identificar efectos sin injector, afterNextRender faltante para APIs DOM
- Detectar variables no utilizadas
Pasos de Análisis
Paso 1: Identificación del objetivo
- Determinar qué se necesita analizar exactamente
- Listar archivos relevantes (usar glob/grep)
- Si es ambiguo, solicitar aclaración
Paso 2: Ejecución del análisis
- Usar grep para localizar patrones
- Usar read para examinar archivos clave
- Usar glob para encontrar archivos relacionados
- Para MySQL: cargar skill 'mysql' y usar ./.opencode/scripts/db-query.sh
- Para análisis multi-archivo: leer todos los archivos involucrados antes de concluir
- Máximo 5 toolcalls de lectura por análisis
Paso 3: Generación del informe
- Incluir fingerprint al inicio
- Estructura obligatoria:
ANALYST::<objetivo>::<archivos analizados>::<fecha/hora> RESUMEN: <2-3 líneas de resumen> HALLAZGOS: 1. [ruta:línea] Descripción del hallazgo 2. [ruta:línea] Descripción del hallazgo RELACIONES: - archivo A ↔ archivo B (tipo de relación) RECOMENDACIONES: - Acción recomendada 1 - Acción recomendada 2 CONCLUSIÓN: <conclusión final>
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.
- 8d ago First seen · 118 lines · 39 tokens per session scan A 094b3bdffe66
analyst-protocol is a skill published in the GitHub repository cruzs85/opencode-multiagente-local-37-iterations (5 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 968 once invoked, about $0.0002 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…