Run the code review benchmark pipeline — create PRs, extract results from MongoDB, judge with Sonnet against 136 golden comments (50 PRs across Sentry, Grafana, Cal.com, Discourse, Keycloak), and compute precision/recall/F1 scores.
Use when the user wants to validate the Kodus SSO flow end-to-end (cookie-domain regression for self-hosted, Bug 1 force-dynamic, SAML round-trip via Keycloak), confirm the SSO test still passes after changes, or regression-check before merging code that touches auth.controller.ts, derive-sso-cookie-domain.ts…
End-to-end front→back performance debugging for the Kodus web app. Use when a screen is slow, blank, looping, or you need to trace a UI perf problem down to the API query. Drives Playwright/Chrome MCP to open + measure the screen, then reads the API use-case/repository and the DB (Postgres/Mongo indexes, explain) to…
Interacts with live Hunk diff review sessions via CLI. Inspects review focus, navigates files and hunks, reloads session contents, and adds inline review comments. Use when the user has a Hunk session running or wants to review diffs interactively.
Use when the user wants Kodus to validate local diff changes against task requirements, acceptance criteria, or business rules via kodus pr business-validation, especially for implementation-vs-task or merge readiness checks.
Use when the user wants to fetch, triage, or implement Kodus suggestions for an existing remote pull request via kodus pr suggestions, --pr-url, or --pr-number.
Use when the user wants Kodus to review local changes through a local CLI build or non-production API such as node dist/index.js, localhost, or QA, including local --prompt-only flows.
Use when the user wants Kodus to review local changes, run kodus review or --prompt-only, fix Kodus review findings, or check commit, push, or merge readiness.
Use when about to edit files in an area you have not touched yet, or when the user asks why code is the way it is. Reads the decisions already recorded for those paths via kodus trace , so deliberate tradeoffs are not undone and settled questions are not re-litigated.