start

Comprehensive Code Review

Run a multi-agent code review with partitioned deep review, deterministic hygiene checks, model routing, and validated findings. Supports two modes:

• Local mode (default): Reviews changes and presents findings in the terminal
• GitHub mode (--github): Reviews a PR, posts inline comments, and writes a summary file

Usage

/start                              # Review open PR diff for current branch, or the diff since the branch forked from the default branch if no PR
/start staged                       # Review only staged changes
/start file1 file2                  # Review specific files
/start 123                          # Review PR #123 diff locally (no posting)
/start --github                     # GitHub CI: auto-detect PR from branch, post inline comments
/start --github 123                 # GitHub CI: review PR #123, post inline comments
/start --hygiene-only               # Fast hygiene-only check (zero LLM tokens)
/start --base develop               # Diff against a specific base branch
/start --since-last-review          # Review only changes since last successful review
/start --full-review                # Force full diff (disable auto-incremental)
/start --depth shallow              # Built-ins only (no critic-gates); see Depth Tiers below
/start --depth deep                 # Standard + future heavy reviewers (Impact Analyzer slot)

Depth Tiers (PLN-807)

The --depth flag selects which reviewer fleet runs. Default standard. Bare /start invocations preserve historical behavior.

• shallow — hygiene + BHA (partitioned at >5000 LOC) + BHB + unified_auditor + verifier. Skips signal extraction, coverage planning/critic, and all critic-gates.json entries. Static spawn spec; no routing/critic decisions. Hygiene emits a tier_mismatch_nudge MEDIUM finding (category Coverage) when the PR's diff size, schema/migration paths, or public API surface suggest standard would catch more.
• standard — current behavior. Full fleet with signal-driven routing, coverage critic, repo-specific critic activation via critic-gates.json. Budget arithmetic reserves BHA partitions FIRST (Phase 4) and caps total domain critics across both required and best-effort buckets at the tier-uniform DOMAIN_CRITIC_CAP = 3 (standard and deep alike). Required critics dropped by the cap emit coverage-gap findings.
• deep — standard plus two deep-only conditional core reviewers. The always-on Design Critic runs on every deep review (no trigger): a software-design craftsmanship reviewer covering module depth/information hiding, SOLID, dependency direction and layer boundaries, and project structure (drawing on A Philosophy of Software Design, SOLID, and Clean Architecture); it is source: "core" so it is exempt from DOMAIN_CRITIC_CAP, runs on Sonnet, is graph-aware (queries the codebase-memory-mcp knowledge graph via get_architecture/query_graph when the repo is indexed, else grep), and emits category: "Code Quality" findings scoped to design flaws this change introduces or worsens. The signal-gated Impact Analyzer (FEA-1401), a cross-file blast-radius reviewer, runs when signal extraction detects exported_symbol_change or symbol_deletion. The analyzer identifies changed exported symbols, finds external usages outside the diff (via the codebase-memory-mcp knowledge graph when the repo is indexed, else grep), and emits findings with external_impact[] listing every callsite that breaks under the new signature. Cost-capped at 30 symbols × 50 callsites with a 5-minute wall budget; deferred symbols surface in the Coverage Plan footer. Impact findings carry category: "ImpactAnalysis" and are verifier-audited per-entry (cited callsites read, snippet content-matched, grep replayed). ≥2 verified BLOCKING/HIGH Impact findings escalate the verdict to NEEDS_ATTENTION (Rule 6). Deep's extra breadth comes from these two reviewers rather than a wider domain-critic cap.