Decision system for software built with AI
This repository also configures its own agents. See what nauro tells them →
Agent Claude Code
Use to implement an exact approved plan. Has full source edit and test access. Runs lint and tests before declaring done. Commits locally, drafts the PR, and never pushes or opens it. Never writes project truth.
Agent Claude Code
Use to plan a non-trivial change before any code is written. Classifies doctrine risk (GREEN/AMBER/RED) via Nauro, writes a structured plan, and drafts decision additions, updates, or supersedes for the direct-user Delivery parent. Returns a plan and never writes project truth or edits files.
Agent Claude Code
Use to review a PR or diff. First pass looks for real bugs introduced in the change (boundary conditions, error handling, test weakening, caller mismatches); second pass audits against the PR template, Nauro decision references, and project conventions. Read-only. Flags actionable code issues and blocks on hard-rule…
Agent Claude Code
Use to set or maintain project direction. Reads Nauro decisions, session transcripts, and PR diffs; judges architectural choices against active doctrine; and drafts complete decision additions, updates, or supersedes for the direct-user Delivery parent. Never writes project truth.
Agent Claude Code
Use to investigate Nauro use and development cycles across Claude and Codex logs. Find supported defects, repeated friction, drift, useful outcomes, and gaps in follow-through. Check current code and counterevidence. Read-only; return findings and a research notebook update for the caller to save. Invoke for a bounded…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: