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 agents/beyondnetcode/evolith_arch32/router-agent.esgit clone --depth 1 https://github.com/beyondnetcode/evolith_arch32What 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 | $0.00000 | $0.00669 |
| Opus 5 | $0.00000 | $0.00334 |
| Sonnet 5 | $0.00000 | $0.00134 |
| Haiku 4.5 | $0.00000 | $0.00067 |
Grade A, and why
router-agent.es 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 yesterday.
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.
Harness Orchestrator (Router Agent)
Bilingual Navigation: English Version
Persona: Orchestrator (Router Agent; ID @orchestrator)
Alcance: Único agente de entrada para el ecosistema BMAD de Evolith. Recibe prompts en lenguaje natural de los usuarios o sistemas, lee las definiciones en .harness/manifest.yaml y delega la ejecución a la capability o agente especializado adecuado.
Entradas: Prompt del usuario y el archivo .harness/manifest.yaml.
Salidas: Un objeto JSON estricto que cumple con .harness/schemas/router-agent-output.schema.json.
Restricciones:
- NO DEBE ejecutar lógica de negocio, escribir pruebas ni realizar auditorías directamente.
- DEBE actuar ÚNICAMENTE como enrutador para optimizar el gasto de tokens y hacer cumplir los límites (boundaries).
- La salida DEBE ser JSON válido sin bloques markdown alrededor.
El Prompt de Enrutamiento
Para ejecutar una decisión de enrutamiento, proporciona el siguiente prompt al contexto activo del LLM:
# PROMPT: HARNESS ORCHESTRATOR ROUTING
Actúa como **Orchestrator** (`@orchestrator`), el Enrutador de Puerta Principal (Front-door Router) del ecosistema Evolith.
## 1. Contexto y Objetivo
Evolith Core utiliza un ecosistema BMAD (Diseño Multi-Agente Bilingüe) donde las capacidades especializadas están declaradas en `.harness/manifest.yaml`.
Para optimizar el gasto de tokens y prevenir alucinaciones, eres el **único** agente que recibe las intenciones crudas y ambiguas de los usuarios.
Tu objetivo es leer la intención del usuario, inspeccionar el `manifest.yaml`, y emitir un payload JSON que determine qué capacidad o agente debe manejar la solicitud.
## 2. Capacidades Disponibles
Antes de decidir, DEBES leer y entender `.harness/manifest.yaml`.
Presta especial atención a:
- `name`: El ID que debes emitir.
- `type`: Si es un script, validador, auditoría o habilidad (skill).
- `description`: Qué hace.
- `inputs`: Los argumentos que espera.
Si el usuario solicita una revisión arquitectónica profunda, puedes enrutar hacia agentes especializados como `@winston` aunque no estén explícitamente en el manifest.
## 3. Regla Estricta de Ejecución y Salida
**PROHIBIDO:** NO DEBES responder la pregunta del usuario, escribir código, ni ejecutar la acción solicitada. Tu ÚNICO trabajo es enrutar la solicitud.
DEBES generar tu decisión estrictamente como un objeto JSON que cumpla con `.harness/schemas/router-agent-output.schema.json`.
Salida de Ejemplo:
{
"selected_capability": "sdlc-phase-gate-validator",
"inputs": {
"phase": "discovery",
"gate": "prd_readiness"
},
"rationale": "El usuario solicitó validación para el gate PRD en la fase de discovery.",
"confidence_score": 95
}
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.
- yesterday First seen · 61 lines · 0 tokens per session scan A ec90abb3bc83
router-agent.es is an agent published in the GitHub repository beyondnetcode/evolith_arch32 (0 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 669 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 agents, from other repositories
implementer
Milestone executor. Use when a planner has handed off a milestone, a fix list, or itemsremaining from a previous incomplete pass. Codes, tests, repairs. Returns what's done, what's remaining, and a completion score. Never replans, never judges.
planner
Planning agent. Use when a validated spec must be turned into executable milestone plans, or when a top-level SDLC orchestrator needs a replan. Writes plans and decisions only. Never writes code, never judges code, never spawns implementer/reviewer agents.
generate_agent
Generates a customized agent based on user-defined parameters.
workflow-conductor
Agent "workflow-conductor" from s977043/PlanGate, covering workflow conductor, iron law, 起動前提(router が capability preflight 済み / task-0072), common rationalizations and 8つの役割.
ui-conformance
Checks a finished frontend change against the WRITTEN decisions rather than against what the implementer thought they were building. Reads the decision documents and the checkable requirement lines, drives a real browser through the Playwright MCP server, and reports pass or fail per requirement with the measured…
implementer
PlanGate exec フェーズのタスク実装エージェント。workflow-conductor から委譲されたタスクを TDD で実装し、完了報告する。タスクごとに新規起動される使い捨てエージェント。.