2025-12-28 17:40:51 +09:00
# AGENTS KNOWLEDGE BASE
## OVERVIEW
2026-02-01 19:26:57 +09:00
2026-02-10 14:53:39 +09:00
11 AI agents with factory functions, fallback chains, and model-specific prompt variants. Each agent has metadata (category, cost, triggers) and configurable tool restrictions.
2025-12-28 17:40:51 +09:00
## STRUCTURE
```
agents/
2026-02-16 15:26:53 +09:00
├── sisyphus.ts # Main orchestrator (559 lines)
├── hephaestus.ts # Autonomous deep worker (651 lines)
├── oracle.ts # Strategic advisor (171 lines)
├── librarian.ts # Multi-repo research (329 lines)
├── explore.ts # Fast codebase grep (125 lines)
├── multimodal-looker.ts # Media analyzer (59 lines)
2026-02-10 14:53:39 +09:00
├── metis.ts # Pre-planning analysis (347 lines)
├── momus.ts # Plan validator (244 lines)
2026-02-16 15:26:53 +09:00
├── atlas/ # Master orchestrator (agent.ts + default.ts + gpt.ts)
├── prometheus/ # Planning agent (8 files, plan-template 423 lines)
├── sisyphus-junior/ # Delegated task executor (agent.ts + default.ts + gpt.ts)
├── dynamic-agent-prompt-builder.ts # Dynamic prompt generation (433 lines)
├── builtin-agents/ # Agent registry + model resolution
├── agent-builder.ts # Agent construction with category merging (51 lines)
2026-02-09 14:29:53 +09:00
├── utils.ts # Agent creation, model fallback resolution (571 lines)
2026-02-16 15:26:53 +09:00
├── types.ts # AgentModelConfig, AgentPromptMetadata (106 lines)
2026-02-09 14:29:53 +09:00
└── index.ts # Exports
2025-12-28 17:40:51 +09:00
```
2026-01-17 22:01:56 +09:00
## AGENT MODELS
2026-02-10 14:53:39 +09:00
| Agent | Model | Temp | Fallback Chain | Cost |
|-------|-------|------|----------------|------|
| Sisyphus | claude-opus-4-6 | 0.1 | kimi-k2.5 → glm-4.7 → gpt-5.3-codex → gemini-3-pro | EXPENSIVE |
| Hephaestus | gpt-5.3-codex | 0.1 | NONE (required) | EXPENSIVE |
| Atlas | claude-sonnet-4-5 | 0.1 | kimi-k2.5 → gpt-5.2 | EXPENSIVE |
| Prometheus | claude-opus-4-6 | 0.1 | kimi-k2.5 → gpt-5.2 | EXPENSIVE |
| oracle | gpt-5.2 | 0.1 | claude-opus-4-6 | EXPENSIVE |
| librarian | glm-4.7 | 0.1 | glm-4.7-free | CHEAP |
| explore | grok-code-fast-1 | 0.1 | claude-haiku-4-5 → gpt-5-mini → gpt-5-nano | FREE |
| multimodal-looker | gemini-3-flash | 0.1 | NONE | CHEAP |
| Metis | claude-opus-4-6 | 0.3 | kimi-k2.5 → gpt-5.2 | EXPENSIVE |
| Momus | gpt-5.2 | 0.1 | claude-opus-4-6 | EXPENSIVE |
| Sisyphus-Junior | claude-sonnet-4-5 | 0.1 | (user-configurable) | EXPENSIVE |
2025-12-28 17:40:51 +09:00
2026-01-17 22:01:56 +09:00
## TOOL RESTRICTIONS
2026-02-10 14:53:39 +09:00
| Agent | Denied | Allowed |
|-------|--------|---------|
| oracle | write, edit, task, call_omo_agent | Read-only consultation |
| librarian | write, edit, task, call_omo_agent | Research tools only |
| explore | write, edit, task, call_omo_agent | Search tools only |
| multimodal-looker | ALL except `read` | Vision-only |
| Sisyphus-Junior | task | No delegation |
| Atlas | task, call_omo_agent | Orchestration only |
## THINKING / REASONING
| Agent | Claude | GPT |
|-------|--------|-----|
| Sisyphus | 32k budget tokens | reasoningEffort: "medium" |
| Hephaestus | — | reasoningEffort: "medium" |
| Oracle | 32k budget tokens | reasoningEffort: "medium" |
| Metis | 32k budget tokens | — |
| Momus | 32k budget tokens | reasoningEffort: "medium" |
| Sisyphus-Junior | 32k budget tokens | reasoningEffort: "medium" |
2026-02-16 15:26:53 +09:00
## KEY PROMPT PATTERNS
- **Sisyphus/Hephaestus**: Dynamic prompts via `dynamic-agent-prompt-builder.ts` injecting available tools/skills/categories
- **Atlas, Sisyphus-Junior**: Model-specific prompts (Claude vs GPT variants)
- **Prometheus**: 6-section modular prompt (identity → interview → plan-generation → high-accuracy → template → behavioral)
2026-02-10 14:53:39 +09:00
## HOW TO ADD
1. Create `src/agents/my-agent.ts` exporting factory + metadata
2. Add to `agentSources` in `src/agents/builtin-agents/`
3. Update `AgentNameSchema` in `src/config/schema/agent-names.ts`
4. Register in `src/plugin-handlers/agent-config-handler.ts`
2026-01-13 21:00:00 +09:00
## ANTI-PATTERNS
2026-02-10 14:53:39 +09:00
- **Trust agent self-reports**: NEVER — always verify outputs
- **High temperature**: Don't use >0.3 for code agents
2026-02-06 16:01:54 +09:00
- **Sequential calls**: Use `task` with `run_in_background` for exploration
2026-02-10 14:53:39 +09:00
- **Prometheus writing code**: Planner only — never implements