← Browse
winning
mishafyi ★ 0
winning is an evolutionary parallel strategy orchestrator that deploys 3 agents per round on different strategies, compares results against verification tests, records learnings, and redeploys until the goal is achieved with no cycle or round limits. It maintains a persistent history of learnings across rounds to inform subsequent deployment strategies.
Install
> /plugin marketplace add mishafyi/claudus-maximus/tree/HEAD/plugins/winning
> /plugin install winning
Source: https://github.com/mishafyi/claudus-maximus/tree/HEAD/plugins/winning
What it's made of
4 commands · 2 agents · 2 skills · 1 hook
- Commands
- 4
- Agents
- 2
- Skills
- 2
- MCP servers
- 0
- Hooks
- 1 · Stop
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
stop-hook.sh- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (mishafyi).