Crucible
A Claude Code slash-command skill that performs adversarial codebase review using a panel of frontier models to find bugs and issues.
Bambushu · AI review on file
Installation
Read the source and dependencies before running a command. Copying does not install or execute anything.
npx skills add Bambushu/crucibleAbout this skill
Crucible
Codebase-level adversarial review by a panel of frontier models.
A Claude Code skill that walks your code piece-by-piece and puts every file under simultaneous pressure from a panel of structurally different models, then aggregates the findings into a single severity-ranked report that Claude itself verifies before you see it.
Install · How it works · Cost · Modes · Sample report
What it is
/crucible is a Claude Code slash-command skill. You drop the folder into ~/.claude/skills/, set one env var, and from inside any project you can run:
/crucible # review the current branch's diff
/crucible --all # review the whole repo
/crucible --paths "src/api/**/*.ts" # review a glob
/crucible --diff main...HEAD # review a specific range
/crucible --verify # also EXECUTE a repro for runtime-flagged findings
Behind the scenes, Claude:
- Resolves the file list and prints a pre-flight (files, models, est. cost).
- Loads a panel of four current SOTA paid models from OpenRouter, each from a different vendor family (e.g. DeepSeek, Google, Moonshot, MiniMax).
- Reviews every in-scope file through the panel: pass 1 finds, pass 2 validates, pass 3 consolidates with severity ranks.
- Runs one cross-file architectural meta-pass to catch repeated anti-patterns, missing layers, and coupling smells.
- (opt-in
--verify) Executes a repro for the runtime bugs. Some bugs only exist when the code runs — a retry the surrounding rate-limit always rejects, a2>/dev/nullthat hides a device error. For each finding the panel tags runtime-checkable, a model writes a minimal repro harness, Crucible runs it in a locked sandbox, and findings that actually reproduce are promote