メニュー
Run agents that craft, compete, and evolve over generations — the user buys the best, winners reproduce. A compiler (a domain → a trained agent) and a research lab (selection discovers what works) in one engine. `crafter_sim()`.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Drive the whole cave-teams library from one function, as DATA — build/run any team from a spec in any sequence, save a team to your proven library, reuse a proven team anywhere, and discover teams across projects. Use when you want to serialize a team, run a team from JSON/dict, save+reuse a proven team across repos ("golden"), or have a higher system / global app drive cave-teams. NOT how you normally program (use the cave-teams DSL for that). Triggers: "cave()", "metacontrol", "run from a spec", "team as data", "golden team", "reuse a proven team", "scan for .cave", "global cave".
Build and run programmable agent teams with cave-teams — the provider-agnostic version of Claude Code Teams. Use when the user wants to wire multiple agents together, run agents in sequence or parallel, build a multi-agent pipeline/workflow, make a "team" of coding agents (Claude Code, Codex, MiniMax, or any), loop an agent until a check passes, run a contest between agents, or compose agents with the >> / | DSL. Triggers: "agent team", "multi-agent", "orchestrate agents", "wire these agents", "run agents in parallel", "cave-teams", "agent pipeline", "agent workflow".
Program WHEN each agent may be messaged — conditions on messages, the GUARDRAILS of a leader-driven team run. Use to gate agents on runtime state: after these two respond, only when a flag holds, any predicate over the message log. THIS is what makes cave-teams programmable where Claude Code Teams' flow is fixed.
N agents read and write a shared state over rounds, with a mutator that folds each contribution in and an optional adjudicator (stigmergy arena). Use for agents collaborating on a shared board, a market, a workspace they all see. `blackboard()`.
Run different agents depending on a condition (guarded choice / router). Use for 'if X do this else that', routing, triage, picking a path by the state. `choice()` / `router()`.
Run agents on a dependency graph — each fires when its inputs are ready (the general scheduler; sequential and parallel are its limits). Use for 'merge after frontend AND backend', diamond/fan-in dependencies, partial orders. `dag()`.
| name | cave-sim |
| description | Run agents that craft, compete, and evolve over generations — the user buys the best, winners reproduce. A compiler (a domain → a trained agent) and a research lab (selection discovers what works) in one engine. `crafter_sim()`. |
crafter_sim(population_dirs, spawn, judge, generations) runs the loop: each generation, spawn(dir) builds a crafter Link from an AIOS dir, the crafters compete, the judge (often the user's purchase) selects, and the winners evolve into the next generation. The async engine over cave-tournament + cave-evolve.
from pathlib import Path
from cave_teams import crafter_sim, AgentLink
result = await crafter_sim(
population_dirs=["seed1", "seed2"],
spawn=lambda d: AgentLink(Path(d).name, "craft the best X", backend="minimax"),
judge=user_purchase_judge,
generations=3)
Not a single cave() build-op — it's a composed simulation engine. Call crafter_sim() directly, or assemble the pieces with cave-tournament + cave-evolve + cave-world.
cave-tournament · cave-evolve · cave-world
Part of the cave-teams plugin — the language + full DSL is the cave-teams skill; drive any pattern from data with the cave skill.