Updated 2mo ago
by Bambushu
crucible
Codebase-level adversarial review by a panel of frontier models. A Claude Code skill that runs every file through DeepSeek + Gemini + Kimi + MiniMax in sequence, then has Claude verify the findings against the actual source.
25 GitHub stars (25)
Steady at 25 stars — no new stars in the 13 days since Sep 30.
- 1 skill (1 skills found in its SKILL.md files)
- 2 forks (2 forks)
- 2mo ago last update (Last updated 2mo ago)
Install
Skills CLI
npx skills add Bambushu/crucible
Asks which agents to install it for. Add -g to install it for every project.
Claude Code
git clone https://github.com/Bambushu/cruciblecp -r "crucible" ~/.claude/skills/crucible
Copies the crucible skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project).
Plugin
/plugin marketplace add Bambushu/crucible
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
crucible
Crucible — codebase-level deep adversarial review using SOTA paid frontier models. Walks code piece-by-piece, dispatches a panel of top current OpenRouter paid models (DeepSeek V4-Pro, Gemini 3.1 Pro, Kimi K3, MiniMax M3 by default, plus Qwen3 and GLM-5 fallbacks) per file with auto family-diversity. Models team up sequentially or in parallel-blind, findings deduplicated and severity-ranked. Cost…
skill.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.