founder-os

Étoiles3

Forks0

Mis à jour25 mai 2026 à 16:43

Multi-agent primitives for Claude Code: consensus, debate, fanout research, skill building, and measured optimization.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

rhinehart514

rhinehart514/founder-os

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

name	founder-os
description	Multi-agent primitives for Claude Code: consensus, debate, fanout research, skill building, and measured optimization.

founder-os

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.

Included primitives

/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

Plus depuis ce dépôt

même dépôt

autoresearch

rhinehart514/founder-os

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.

2026-05-113

fanout

rhinehart514/founder-os

Fan-out/fan-in research. Spawns N researchers (Sonnet) in parallel to explore a question from different angles, then synthesizes findings with Opus.

2026-05-113

model-chat

rhinehart514/founder-os

Spawn Claude instances into a shared conversation room where they debate, disagree, and converge. Round-robin turns with parallel execution within each round.

2026-05-113

skillbuilder

rhinehart514/founder-os

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.

2026-05-113

stochastic

rhinehart514/founder-os

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).

2026-05-113

Exécutez n'importe quel Skill en un clic