claude

crucible

Benchmark Claude model and effort configurations on your own real tasks.

0 on GitHubby Jaxson Mansouriv0.1.0MITupdated 1 month ago
/

Plugin crucible from marketplace crucible in Jaxsonman/Crucible. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (5)

  • create-task

    Turn a spec, ticket or PR into a Crucible benchmark task (.crucible/tasks/<id>/ with task.md, check.sh and hidden tests) that points at a real repo. Use when the user wants to create, import or write a benchmark task, or says "make a task from this ticket/spec".

  • init

    Create the .crucible/ home for Crucible benchmarks in the current git repo. Run once per repo before creating tasks.

  • mine

    Mine the repo's merged PRs (or local commits) into verified Crucible benchmark tasks. The CLI lists, verifies, scaffolds and proves; this skill only writes each task's prose and picks its kind. Spends usage, so it confirms first.

  • report

    Show and explain Crucible benchmark results for one task or across tasks, with the recommended model configuration. Use when the user asks which model or effort to use, or how a benchmark went.

  • run

    Run a Crucible benchmark for a task against a matrix of model configurations, in the background, then summarise the results. Spends usage, so it confirms first.

View source on GitHub

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.

1 skill

headroomlabs-ai/headroom 79,508

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

Cloud architecture design for AWS/Azure/GCP/OCI, Kubernetes cluster configuration, Terraform infrastructure-as-code, hybrid cloud networking, and multi-cloud cost optimization

8 skills · 7 agents

wshobson/agents 42,461

Claude Code native multi-agent orchestration with intelligent model routing across agents and skills. Zero learning curve. Maximum power.

85 skills · 20 commands · 19 agents · 1 MCP server · hooks

Yeachan-Heo/oh-my-claudecode 40,800

Maintain crucible?

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 pluginslisted