Updated 1d ago
by chaseai-yt
claudex-loop
Claude Code skill: four-phase plan hardening (recon, interrogate, Codex adversarial review, cross-model build & inspection) — two AI models harden your plan before a line of code exists, then swap jobs to build it. Whoever built it never grades it.
3k GitHub stars (3,026)
+360 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | +5 |
| Oct 2 | +19 |
| Oct 3 | +10 |
| Oct 4 | +19 |
| Oct 5 | +15 |
| Oct 6 | +11 |
| Oct 7 | +14 |
| Oct 8 | +24 |
| Oct 9 | +16 |
| Oct 10 | +12 |
| Oct 11 | +59 |
| Oct 12 | +59 |
| Oct 13 | +18 |
| Oct 14 | +37 |
| Oct 15 | +22 |
| Oct 16 | +20 |
- 6 skills (6 skills found in its SKILL.md files)
- 327 forks (327 forks)
- 1d ago last update (Last updated 1d ago)
Install
Skills CLI
npx skills add chaseai-yt/claudex-loop
Asks which skills and agents to install. Just one: npx skills add chaseai-yt/claudex-loop --skill grill-me-codex — add -g for every project.
Claude Code
git clone https://github.com/chaseai-yt/claudex-loopcp -r "claudex-loop/legacy/grill-me-codex" ~/.claude/skills/
Copies the grill-me-codex skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add chaseai-yt/claudex-loop
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.
-
grill-me-codex
SUPERSEDED by /claudex-loop (formerly /crucible; adds a Phase 0 research/recon pass + rebuilt interview) — prefer that skill unless you explicitly want this one. Two-act plan hardening. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan or design, one question at a time, recommending an answer for each and exploring the codebase when it can answer itself, until every branch of…
legacy/grill-me-codex/SKILL.md on GitHub (opens in a new tab) -
grill-with-docs-codex
SUPERSEDED by /claudex-loop (formerly /crucible; its docs-aware mode covers this variant) — prefer that skill unless you explicitly want this one. Two-act plan hardening with living documentation. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan, one question at a time, challenging it against your project's existing domain model and glossary (CONTEXT.md), sharpening fuzzy te…
legacy/grill-with-docs-codex/SKILL.md on GitHub (opens in a new tab) -
claudex-loop
Harden a plan with independent Claude/Codex review, then optionally build and cross-inspect it. Start in either Claude Code or Codex: the host plans and the other provider reviews. Use for claudex this plan, claudex-loop, or the legacy crucible trigger; not for trivial edits.
skills/claudex-loop/SKILL.md on GitHub (opens in a new tab) -
claudex-route
Recommend a model and a scoped handoff for a task in Claude Code or Codex. Use when choosing who should handle a task, seeking a second opinion, getting unstuck, or delegating focused work; execute one handoff when requested.
skills/claudex-route/SKILL.md on GitHub (opens in a new tab) -
codex-build
Have Codex implement a concrete work order and have Claude independently inspect the final changes. Preserves the explicit Codex builder choice; use claudex-loop for host-based planning and automatic reviewer selection.
skills/codex-build/SKILL.md on GitHub (opens in a new tab) -
codex-review
Have Codex independently review an existing implementation plan while Claude coordinates a bounded revision loop. For automatic reviewer selection from either host, use claudex-loop with mode=review.
skills/codex-review/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.