Menu
Multi-agent primitives for Claude Code: consensus, debate, fanout research, skill building, and measured optimization.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
TRIGGER when user explicitly invokes optimization with a numeric automatable metric — "optimize the lighthouse score", "shrink the bundle", "reduce build time", "cut p99 latency", "hill climb the eval accuracy", "/autoresearch", "make X faster" where X is measurable. Drops a working hill-climb harness into the project, generates project-specific mutations by reading the codebase, runs the loop. SKIP when there's no numeric metric, when changes need design/UX/copy judgment, or for one-off manual tuning. SKIP requests like "make this cleaner/better/smaller" that have no measurement command.
Fan-out/fan-in research. Spawns N researchers (Sonnet) in parallel to explore a question from different angles, then synthesizes findings with Opus.
Spawn Claude instances into a shared conversation room where they debate, disagree, and converge. Round-robin turns with parallel execution within each round.
Build flawless Claude Code skills. Studies existing skills as reference, ensures correct format, and pushes for genuine intelligence — skills that exploit something specific about how Claude works. SKIP for one-off scripts, prompts, or task helpers.
Stochastic multi-agent consensus. Spawns N agents with identical prompts to independently analyze a problem. Aggregates by consensus (mode), divergences (splits), and outliers (unique ideas).
| name | founder-os |
| description | Multi-agent primitives for Claude Code: consensus, debate, fanout research, skill building, and measured optimization. |
Use founder-os when one Claude Code pass is not enough and you want to compare multiple agent runs, surface disagreement, or synthesize parallel research.
/stochastic: poll N agents with the same prompt and aggregate consensus, divergences, and outliers./model-chat: run a multi-agent debate room and synthesize the strongest position./fanout: send researchers down parallel paths, then merge findings./skillbuilder: build higher-quality Claude Code skills by identifying what the skill exploits./autoresearch: run measured optimization loops against a numeric metric.Install:
claude plugin install rhinehart514/founder-os