Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/peer-review-loop
Peer Review Ralph Loop — combines Cavekit kits with a Ralph Loop and true cross-model peer review using Codex (OpenAI). Claude builds from specs; Codex reviews adversarially. Primary path: Codex CLI delegation via codex-review.sh (fast, no MCP overhead). Legacy fallback: Codex as MCP server when CLI delegation is unavailable. Covers setup, iteration patterns, convergence detection, and completion criteria. Triggers: "peer review loop", "ralph loop with codex", "cavekit ralph", "peer review build
Passed 17 of 19 test cases with the skill, and 7 of 19 without it.
and 14 more in the full report
12 fixed8 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
Before running `/ck:peer-review-loop`, what npm package must be installed globally, and what plugin must be active for stop hook support?
| Checked | Without skill | With skill |
|---|---|---|
| Requires npm package `@openai/codex` installed globally | Missed | Passed |
| Requires active ralph-loop plugin for stop hook functionality | Missed | Passed |
The instructions your model reads when the skill loads.
Run a Cavekit cavekit through a Ralph Loop where Claude builds and Codex adversarially reviews. This is the most rigorous automated quality process available: every few iterations, a completely different model (different training data, different biases, different blind spots) challenges your implementation.
| Factor | Single-Model Loop | Peer Review Loop |
|---|---|---|
| Blind spots | Same model, same blind spots every iteration | Two models catch different classes of issues |
| Cavekit drift | Builder may silently deviate from cavekit | Peer reviewer checks cavekit compliance explicitly |
| Quality floor | Converges to "good enough for one model" | Converges to "survives cross-examination" |
| Dead ends | May retry failed approaches | Peer reviewer flags repeated patterns |
┌─────────────────────────────────────────────────────┐
│ Ralph Loop │
│ (Stop hook feeds same prompt each iteration) │
│ │
│ ┌──────────┐ ┌──────────────┐ ┌────────────┐ │
│ │ Claude │───▶│ Build from │───▶│ Commit │ │
│ │ (Build) │ │ cavekit + │ │ changes │ │
│ └──────────┘ └──────────────┘ └──────┬─────┘ │
│ ▲ │ │
│ │ ▼ │
│ ┌──────────┐ ┌──────────────┐ ┌────────────┐ │
│ │ Fix │◀──│ Parse │◀──│ Codex CLI │ │
│ │ findings │ │ findings │ │ (Review) │ │
│ └──────────┘ └──────────────┘ └────────────┘ │
│ │
│ Completion: all cavekit requirements met + │
│ no CRITICAL/HIGH findings │
test cases passed, vs 7 / 19 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.