Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/peer-review
Patterns for using a second AI agent or model to challenge the primary builder agent's work. Covers six review modes (Diff Critique, Design Challenge, Threaded Debate, Delegated Scrutiny, Deciding Vote, Coverage Audit), how to set up peer review with any model via MCP server, peer review iteration loops that alternate builder and reviewer prompts, the Codex Loop Mode (Cavekit + Ralph Loop + Codex as reviewer via CLI or MCP fallback), and prompt templates for each strategy. The peer reviewer's jo
Passed 23 of 23 test cases with the skill, and 14 of 23 without it.
and 6 more in the full report
9 fixed14 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are running the `/ck:make` command to start a cavekit build loop. What CLI flag enables Codex Loop Mode for adversarial peer review?
| Checked | Without skill | With skill |
|---|---|---|
| Specify the flag --peer-review. | Missed | Passed |
The instructions your model reads when the skill loads.
Use a second AI agent to review and challenge the first agent's work. The peer reviewer exists to find what the builder missed -- not to agree, not to be polite, and not to rubber-stamp. This is the single most effective quality gate you can add beyond automated tests.
The peer reviewer's job is to find what the builder missed, not to agree.
A review that says "looks good" is a wasted review. The peer review model should be given explicit instructions to be critical, to challenge assumptions, and to look for what is not there rather than what is.
LLMs have blind spots. Every model has patterns it over-relies on, edge cases it misses, and architectural assumptions it makes implicitly. A second model -- or the same model with a different prompt and role -- catches a different set of issues.
The analogy: In traditional engineering, code review exists because the author has cognitive blind spots about their own work. The same principle applies to AI agents, but the blind spots are different: they are systematic patterns in training data, context window limitations, and prompt interpretation biases.
What peer review catches that automated tests miss:
test cases passed, vs 14 / 23 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.