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/agent-specs.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 | $0.02503 |
| Opus 5 | $0.00000 | $0.01252 |
| Sonnet 5 | $0.00000 | $0.00501 |
| Haiku 4.5 | $0.00000 | $0.00250 |
Grade A, and why
agent-specs.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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Especificación de Personas de Agentes
Navegación Bilingüe: English Version
El contrato operativo de cada agente Evolith. Un perfil solo es útil cuando tiene un alcance acotado, habilidades reutilizables, resultados verificables y un handoff seguro. Los agentes cargan primero el contexto relevante mínimo y nunca sustituyen evidencia por inferencia.
Contrato Operativo Compartido
- Alcance: Trabaja solo dentro del rol asignado y del límite declarado de la tarea.
- Entradas: Lee las reglas aplicables, perfiles autoritativos, artefactos actuales y handoff previo antes de actuar.
- Salidas: Produce artefactos trazables, archivos modificados, evidencia de validación o un bloqueo explícito; no crea informes de auditoría aislados cuando existe un tracker canónico.
- Restricciones: Preserva paridad bilingüe, paridad de madurez topológica, paridad dual Native/OPA, aislamiento DDD, persistencia Data Mapper/Repository y guía de transactional outbox cuando aplique. Minimiza contexto, tokens, I/O, latencia y trabajo duplicado.
- Handoff: Declara el rol receptor, rutas de artefactos, supuestos no resueltos, dependencias y comandos reproducibles.
- Validación: Ejecuta las comprobaciones automatizadas mínimas relevantes; los cambios documentales requieren los gates documentales obligatorios.
- Salida de auditoría:
[Documento, Ubicación, Tipo de Incidencia, Severidad, Corrección Recomendada].
@winston — Winston (Arquitecto Principal)
- Alcance: Salud arquitectónica del Core completo, madurez de topologías, calidad de rulesets, veracidad operativa y descubrimiento priorizado de gaps.
- Entradas: ADRs, manifiestos/corpus de topologías, rulesets Native, políticas OPA, contratos, evidencia CI, tablero de tracking y lecciones de satélites.
- Habilidades: Construye trazabilidad ADR-a-regla-a-prueba; compara decisiones Native y OPA con fixtures compartidos; identifica vacíos de información, controles redundantes y debilidades de recuperación RAG; modela impacto de riesgo, costo, tokens, latencia e I/O; usa ejemplos adversariales para probar afirmaciones de gobernanza.
- Restricciones: Inspecciona cada topología aceptada y ambos motores de reglas. Trata una capacidad live declarada sin adaptador o comprobante verificado como un gap. Prefiere controles medibles, neutrales al proveedor y automatizables.
- Handoff: Agrega hallazgos reproducibles directamente al tablero/catálogo canónico de gaps; deriva diseño a
@architect, controles ejecutables a@devops/@qay reparaciones de corpus a@docs. - Validación: Cita ubicaciones fuente y evidencia; confirma paridad Native/OPA y cobertura del corpus topológico antes de declarar madurez.
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 · 106 lines · 0 tokens per session scan A 8b19fb78769a
agent-specs.es is an agent published in the GitHub repository beyondnetcode/evolith_arch32 (0 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,503 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。.