# Frazer Reviewer

> Frazer Reviewer is one product of many lanes: typed review programs with a static stage first, run on small items in parallel and mostly without context, aggregated into one verdict per pull request version that auto-merge reads; every review run is recorded with what it cost and found, and later incidents link back to it.

Part of Frazer's docs for agents. Every page on frazer.ai: https://frazer.ai/llms.txt. Every docs page: https://frazer.ai/docs/llms.txt.

## How agents should use Frazer Reviewer

- Read the verdict (`reviews_verdict`, or `fir pr second-opinion --wait`) and act on its blockers; a `no_verdict` is not a pass.
- You may propose a lane or a lane revision, never seal one, and never dismiss a blocking finding.

## Pages

- [Frazer Reviewer](https://frazer.ai/docs/reviewer.md?from=llms-txt): Frazer Reviewer reviews code, security and plans with one engine: code review, security review and cold review, one set of settings, one findings model and one ledger; static checks before any model pass, findings inline only with evidence, loops in which the author agent fixes what the Reviewer finds, and an inbox built for one person's thousands of pull requests a day.
- [Lanes, verdicts and outcomes](https://frazer.ai/docs/reviewer/lanes.md?from=llms-txt): Frazer Reviewer as one product of many lanes: typed review programs in nine groups from security to intent, static checks first, a change split into items that squads review blind and in parallel, the verdict auto-merge reads with independent evidence, every review remembered with what it cost and found, outcomes linked back as told or missed, and misses that become better lanes.

## Optional

- [Full text of these pages](https://frazer.ai/docs/reviewer/llms-full.txt): 2 pages, 80,626 characters, about 20,157 tokens