claudex-loop

claudex-loop is a Multi-stage workflow orchestration skill for AI agents, published by chaseai-yt in the claudex-loop repository on GitHub. Skillspace rates claudex-loop D (60/100) and it passed the safety scan; the rating is based on static analysis only.

Four-phase plan hardening (renamed from /crucible 2026-08-16; old triggers still work) — supersedes /grill-me-codex and /grill-with-docs-codex. PHASE 0 RECON — Claude scouts first (codebase + docs on brownfield; prior art, stack, and pitfalls research on greenfield) and drafts an assumptions ledger. PHASE 1 INTERROGATE — confirm the ledger in one batch, then question only the load-bearing decisions one at a time (each with why-it-matters, a recommendation, and what-breaks-if-we-guess-wrong), cosmetic ones batched, with a visible decision map and an accept-all-recommendations escape hatch. PHASE 2 REVIEW — the locked plan goes to PLAN.md and OpenAI Codex adversarially reviews it in a read-only sandbox (VERDICT: APPROVED/REVISE); Claude revises and re-submits to the SAME Codex session until APPROVED or MAX_ROUNDS, then you sign off before any code. PHASE 3 BUILD (optional) — you pick the builder and the models swap jobs: Codex builds via codex-build and Claude reads the full diff + runs…

Grade
D
Quality
60 / 100
Safety
Passed
GitHub stars
1,607

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubchaseai-yt/claudex-loop

Our review

Architecture
92 / 100
Maturity
Basic: a single SKILL.md
Security scan
Low-risk patterns
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • mentions secrets in text

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Multi-stage workflow orchestration

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.