arcs

Use when the user provides a GitHub PR link with a "deep review" trigger inside a locally cloned repo, to perform a thorough multi-dimensional code review grounded in ARCS DAG context, AGENTS.md conventions, and optional codegraph coupling analysis, then post findings as inline GitHub review comments under explicit user gate

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when initializing a new ARCS project — bootstrapping a repo into the DAG with metadata, docs, and structural knowledge entries. Covers gather → present summary → init → codegraph ingestion → fan-out analysis across typed sub-agents.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when implementing any feature or bugfix, before writing implementation code

Use when you have a spec or requirements for a multi-step task, before touching code

Use when capturing a knowledge entry, before writing its body — to author a substantive per-kind body, not a summary-only stub

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Challenges user intent, stress-tests requirements, and forces precision before design.

Use when the task is mostly clear (50-90%) with one or two open decisions that can likely be resolved by inspecting the repo — not fully bounded, not a blank-slate design problem

Use when the task is fully bounded with no open decisions — rename, refactor, extract, multi-var/multi-file change, API shape already known, config nudge, copy update, trivial targeted bugfix

Use before writing code as a constructive minimalism reflex — triggers: 'minimal solution', 'simplest thing that works', 'do less', 'shortest path', 'reach for stdlib first', 'before writing code'. Auto-layers onto quick-dev / code-agent to build the smallest thing that works before reaching for new code or dependencies.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when creating or updating a Mermaid diagram for a ARCS plan — selecting dialect, encoding task status via classDef, managing the standalone .mmd file, and detecting or resolving diagram/metadata drift.

Use when `arcs project init` or `arcs codegraph-sync` returns `pending_enrichment: true` — drives the per-proposal verdict loop (keep/drop/merge) and produces agent-authored knowledge entries from raw codegraph proposals.

Use when writing git commit messages, especially when ARCS Caveman mode is active. Produces Conventional Commits with terse, intent-preserving prose. Subject ≤50 chars; body only when the "why" isn't obvious from the diff.