claude

speed-run

Token-efficient code generation pipeline - parallel implementation with hosted LLM (Cerebras) for ~60% token savings. Includes MCP server.

102 on GitHubv1.1.1MITupdated 2 days agodevelopment
/

Plugin speed-run from marketplace 2389-research in 2389-research/claude-plugins. Commands read from the repo's manifest — yesterday.

This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (5)

  • any-percent

    Runs 2-5 parallel agents in isolated git worktrees, each implementing a distinct architectural approach via Cerebras hosted LLM, then judges all survivors to select the winner (~60% token savings vs Claude direct). Use when the best architecture is unclear and you want real competing implementations

  • judge

    Scores parallel implementations with a 5-criteria worksheet (fitness, justified complexity, readability, robustness, maintainability; 25 points max), hard gates on score=1 or Fitness delta>=2, and Speed-Run efficiency tiebreakers. Invoked automatically by speed-run:showdown and speed-run:any-percent

  • showdown

    Runs 2-5 parallel runners against a shared design doc in isolated git worktrees, each independently planning and generating code via Cerebras hosted LLM, then invokes speed-run:judge to score all implementations and pick the winner (~60% token savings vs Claude direct). Use when you have a finalized

  • speed-run

    Token-efficient code generation pipeline via Cerebras hosted LLM; requires CEREBRAS_API_KEY. Checks API key then routes to speed-run:turbo (direct codegen), speed-run:showdown (parallel competition), or speed-run:any-percent (parallel exploration). Use when the user says \"speed-run\", \"fast build\

  • turbo

    Generates code via Cerebras hosted LLM from a structured contract prompt, writes files directly to disk, then applies surgical Claude fixes for test failures (~60% token savings vs Claude direct). Use when you have a single task — algorithmic code, boilerplate, data transformations, or multi-file sc

MCP servers (1)

  • speed-run

    runs: node ${CLAUDE_PLUGIN_ROOT}/mcp/dist/index.js

Hooks (1)

  • SessionStart

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/check-api-key.sh

View source on GitHub 2389.ai

More from 2389-research/claude-plugins

All 31 plugins →

binary-re

claude

Agentic binary reverse engineering for ELF binaries on ARM64, ARMv7, x86_64 - hypothesis-driven analysis with radare2, Ghidra, GDB, QEMU

6 skills

102

simmer

claude

Iterative artifact refinement with investigation-first judge board - constructs problem-specific judges that read the code, understand the problem, and propose evidence-based improvements

6 skills

102

thrifty

claude

Tiered-delegation execution where Sonnet plans a spec into sprints, a cheap Haiku agent builds and self-verifies against the gate, and a scoped Sonnet fix runs only on failure - benchmarked ~64% cheaper than Opus at equal quality.

6 skills

102

Firebase project workflows including setup, features, debugging, and validation

5 skills

102

Digital drugs that modify AI behavior through prompt injection

3 commands · 1 MCP server

102

CSS development workflows with Tailwind composition, semantic naming, and dark mode by default

4 skills

102

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain speed-run?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins31 plugins