~ / leaderboard / skill / eval-runner
Skill · #4413
eval-runner
Run the Foundry-only 4-phase eval pipeline (deterministic gate → smoke 10-row → expanded 40-80 → nightly 80-150) using grok-4-1-fast-reasoning-2-eval primary + DeepSeek-V3.2 audit. Cost-bounded (≤1500
4rigs use it
0%of all rigs
14.1kavg rig context tax
Get it
$ npx degit haabe/mycelium/plugins/mycelium/skills/eval-runner .claude/skills/eval-runner From the most-starred rig that ships it: haabe/mycelium. Same-named skills in different rigs may differ — review before use.
Often used together with
brainstorming · 2grill-me · 2review · 2agent-team · 2tdd · 2improve-codebase-architecture · 2frontend-design · 2qa · 2create-verification-skill · 2ponytail · 2
Rigs using eval-runner (4)
haabe/mycelium
Prevent wasting time building the wrong thing. A plugin that keeps you and your AI coding agent focused, from first idea to market.
Skill Collector 22.3k tok · · Q34
heldernoid/agentic-build-templates
Build Templates for AI Agents
Skill Collector 5.7k tok · · Q0
Zion-sewers/claude-setup
A personal agent OS you can inspect: skills, verification harness, and deployment for Claude-based agents
Skill Collector 14.0k tok · · Q8
Zion-sewers/night-rick
A personal agent OS you can inspect: skills, verification harness, and deployment for Claude-based agents
Skill Collector 14.1k tok · · Q8