Grill With Docs Codex
SUPERSEDED by /claudex-loop (formerly /crucible; its docs-aware mode covers this...
Install
npx skills add chaseai-yt/claudex-loop --skill grill-with-docs-codex -g -a claude-code -y- Repository
- chaseai-yt/claudex-loop3.3k
- Category
- Testing
- Updated
- 21d ago
- License
- See repository
- Context cost
- Mediumabout 2,402 tokens
- Runs scripts
- No, instructions only
What it does
SUPERSEDED by /claudex-loop (formerly /crucible; its docs-aware mode covers this variant), prefer that skill unless you explicitly want this one.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 terms, stress-testing with concrete scenarios, cross-referencing code, and updating CONTEXT.md + ADRs inline as decisions crystallise. ACT 2 (Claude ↔ Codex), Claude writes the locked plan 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 a MAX_ROUNDS cap, then you sign off before any code. Use when the user says "/grill-with-docs-codex", "grill me against the docs then have codex review", "stress-test this against our domain model then get a second model on it", or is about to build something high-stakes in a project with established terminology/ADRs and wants alignment, documentation, AND a cross-model sanity check. Builds on Matt Pocock's grill-with-docs (MIT). NOT for reviewing already-written code (use /codex:review) and NOT for trivial changes.
Grill-with-Docs-Codex, Grill Against Your Domain, Then Get Reviewed
Two acts. Act 1 aligns intent and keeps your living docs honest; Act 2 has a different model attack the result.
- Act 1 is Matt Pocock's
grill-with-docs, used under MIT (seeTHIRD-PARTY-NOTICES.md). It interrogates you, challenges your plan againstCONTEXT.md/ADRs, and updates them inline. - Act 2 is the original Codex adversarial review loop, cross-model, read-only, bounded.
You enter at two points: answering the grill, and signing off the converged plan.
ACT 1, GRILL WITH DOCS (you ↔ Claude)
<what-to-do>Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
Ask the questions one at a time, waiting for feedback on each question before continuing.
If a question can be answered by exploring the codebase, explore the codebase instead.
</what-to-do> <supporting-info>Domain awareness
During codebase exploration, also look for existing documentation:
File structure
Most repos have a single context:
/
├── CONTEXT.md
├── docs/
│ └── adr/
│ ├── 0001-event-sourced-orders.md
│ └── 0002-postgres-for-write-model.md
└── src/
If a CONTEXT-MAP.md exists at the root, the repo has multiple contexts. The map points to where each one lives:
/
├── CONTEXT-MAP.md
├── docs/
│ └── adr/ ← system-wide decisions
├── src/
│ ├── ordering/
│ │ ├── CONTEXT.md
│ │ └── docs/adr/ ← context-specific decisions
│ └── billing/
│ ├── CONTEXT.md
│ └── docs/adr/
Create files lazily, only when you have something to write. If no CONTEXT.md exists, create one when the first term is resolved. If no docs/adr/ exists, create it when the first ADR is needed.
