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/discovery-agents.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 | $0.00765 |
| Opus 5 | $0.00000 | $0.00382 |
| Sonnet 5 | $0.00000 | $0.00153 |
| Haiku 4.5 | $0.00000 | $0.00076 |
Grade A, and why
discovery-agents.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.
What it actually says
Agentes de Intake y Discovery (Fases 00 y 01.1)
Navegación Bilingüe: English Version
Los siguientes agentes soportan el Architecture Planning Gate (Fase 00). Cada agente sigue la regla de Calidad de Actualización de Agente: alcance, entradas, salidas, restricciones, handoff, checklist de validación y formato de auditoría.
| Agente | Alcance | Entradas | Salidas | Handoff A |
|---|---|---|---|---|
| Architecture Plan Interpreter | Analizar requerimientos crudos para generar un Architecture Plan para evaluación en Gate 0 | Prompt de requerimiento de negocio crudo, ADRs, blueprints | Architecture Plan Draft (JSON/YAML) | OPA Evaluation Engine / Aprobador Humano |
| Business Discovery Agent | Extraer declaración de problema, propuesta de valor y contexto de negocio de stakeholders o prompts | Disparador de negocio, entrevistas con stakeholders, contexto de mercado | Discovery Knowledge Brief (borrador) | Product Framing Agent |
| Product Framing Agent | Estructurar contexto del dominio, identificar actores y definir límites de alcance | Knowledge Brief, conocimiento del dominio, visión del producto | Knowledge Brief (validado), Mapa de Capacidades (semilla) | Capability Modeling Agent |
| Capability Modeling Agent | Descomponer dominio en capacidades con prioridad y dependencias | Knowledge Brief validado, modelo de dominio, prioridades de stakeholders | Mapa de Capacidades | Epic Discovery Agent |
| Epic Discovery Agent | Mapear capacidades a candidatos de épica con prioridad MoSCoW y estimación de tamaño | Mapa de Capacidades, prioridades de negocio, restricciones técnicas | Matriz de Candidatos a Épica | Story Slicing Agent |
| Story Slicing Agent | Crear semillas mínimas de historia de candidatos de épica con borradores de criterios de aceptación | Matriz de Candidatos a Épica, roles de usuario, expectativas de comportamiento | Banco de Semillas de Historia | Acceptance Criteria Agent |
| Acceptance Criteria Agent | Validar y refinar criterios de aceptación para semillas de historia, asegurar testabilidad | Banco de Semillas de Historia, reglas de dominio, estándares de calidad | Banco de Semillas de Historia (refinado) | Architecture Discovery Agent |
| Architecture Discovery Agent | Identificar restricciones técnicas, candidatos a ADR, spikes y enablers | Knowledge Brief, Mapa de Capacidades, contexto técnico | Sección de restricciones arquitectónicas, Candidatos a Decisión | Discovery Gate Agent |
| Discovery Gate Agent | Validar suficiencia del conocimiento contra requisitos de nivel de adopción | Todos los artefactos 01.1, nivel de adopción, checklist de calidad | Gate de Preparación de Discovery (PASS/CONDITIONAL/FAIL) | Siguiente fase (Ballpark / Backlog / Diseño) |
| Knowledge Drift Agent | Detectar cuándo cambios de código ocurren sin actualizaciones de conocimiento correspondientes | git diff, globs de ownership de artefactos de conocimiento, Discovery Context Pack | Señales de drift (FYI, no bloqueante) | Owner de la fase actual |
Restricciones comunes para todos los Agentes de Discovery:
- No deben crear épicas, historias o ítems de backlog — solo artefactos de conocimiento
- Deben mantener IDs de trazabilidad en todas las salidas
- Deben producir salidas bilingües cuando el repositorio lo requiera
- No deben introducir dependencias de vendor o framework
- Deben declarar nivel de adopción en todos los artefactos
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 · 26 lines · 0 tokens per session scan A 3c859da17b0d
discovery-agents.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 765 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。.