crucible

OtherGitHubActivePython

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.

Description provenance: Original source

Open canonical source

Measured: Oct 13, 2026 · 61 observations

Domains & Uses

Domains: Agents, skills and MCP
Uses: Code assistants

Check at the source

Compatibility and prerequisites must be checked in the official documentation.

https://github.com/Bambushu/crucible

Classifications

Nature: Tool

Measurement history

Comparable readings are grouped by signal and unit.

Stars

25stars · Oct 13, 2026

-2 (-7.4 %)since Sep 13, 2026

Exact values · 30 readings

Measured	stars	Change
Oct 13, 2026	25	0
Oct 12, 2026	25	0
Oct 11, 2026	25	0
Oct 10, 2026	25	0
Oct 9, 2026	25	0
Oct 8, 2026	25	0
Oct 7, 2026	25	0
Oct 6, 2026	25	0
Oct 5, 2026	25	0
Oct 4, 2026	25	0
Oct 3, 2026	25	0
Oct 2, 2026	25	0
Oct 1, 2026	25	0
Sep 30, 2026	25	0
Sep 29, 2026	25	0
Sep 28, 2026	25	0
Sep 27, 2026	25	0
Sep 26, 2026	25	0
Sep 25, 2026	25	0
Sep 24, 2026	25	0
Sep 23, 2026	25	0
Sep 22, 2026	25	0
Sep 20, 2026	25	0
Sep 19, 2026	25	-2
Sep 18, 2026	27	0
Sep 17, 2026	27	0
Sep 16, 2026	27	0
Sep 15, 2026	27	0
Sep 14, 2026	27	0
Sep 13, 2026	27	·