← Browse
speed-run
2389-research ★ 3
Speed-Run is a token-efficient code generation pipeline that uses Cerebras-hosted LLMs for fast first-pass code creation while Claude handles architecture decisions and surgical fixes. It offers three modes—turbo for direct generation, showdown for parallel competitive implementations, and any-percent for exploring different architectural approaches—all designed to reduce token costs by 60-70% compared to Claude-only code generation.
Install
> /plugin marketplace add 2389-research/speed-run
> /plugin install speed-run
What it's made of
5 skills · 1 MCP server · 1 hook
- Commands
- 0
- Agents
- 0
- Skills
- 5
- MCP servers
- 1
- Hooks
- 1 · SessionStart
What it needs & plugs into
- API keys
CEREBRAS_API_KEY- Paid services
- Cerebras
- External tools
bashnode- 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 (2389-research).