/review

name: review
description: 'Multi-agent code review of local Python files, directories, or the current git diff covering architecture, tests, performance, docs, lint, security, and API design. Scope: Python source files in local working tree. Python-file-free targets (pure JS/TS/Go/Rust projects) are out of scope. TRIGGER when: user asks to review local Python files, a directory, or the current git diff/working-tree changes, with no GitHub PR number involved; phrases: "review this", "review my changes", "code review this diff", "review src/foo.py". SKIP when: input is a bare GitHub PR/issue number (use `/oss:review <PR#>`, requires oss plugin); user wants the Codex-native tiered `$code-review` workflow (codex-rig plugin, JSON artifact + specialist fan-out) — different toolchain; implementation work (use `/develop:fix` or `/develop:feature`); non-Python-only projects.'
argument-hint: '[python-file|dir] [--no-challenge] [--challenge] [--codemap] [--no-codemap] [--semble] [--worktree] [--full] [--keep "<items>"]'
allowed-tools: Read, Write, Edit, Bash, Grep, Glob, Agent, Skill, TaskList, TaskCreate, TaskUpdate, AskUserQuestion, EnterWorktree, ExitWorktree
disable-model-invocation: true
effort: high

<objective>

Comprehensive code review of local files or working-tree diff. Spawns specialized sub-agents in parallel, consolidates findings into structured feedback with severity levels.

NOT for: GitHub PR review (use `/oss:review <PR#>` (requires oss plugin)); GitHub thread analysis or PR reply drafting (use `/oss:analyse <PR#>` (requires oss plugin)); implementation (use `/develop:feature` or `/develop:fix`); `.claude/` config changes (use `/foundry:manage` (requires foundry plugin) or `/foundry:audit` (requires foundry plugin)); non-Python-only projects (zero Python source files — pure JS/TS/Go/Rust) — review toolchain assumes Python/pytest; Python test-only targets where diff contains only test files (no `src/` or top-level `.py` source outside `tests/`) — review will be uninformative; for polyglot projects with Python source, reviews Python files only.

</objective>

<inputs>

• **$ARGUMENTS**: optional file path or directory to review.
• Path given: review those files
• Omitted: review current git diff (`git diff HEAD` — staged + unstaged vs HEAD)
• **Scope**: Python source only. Non-Python file (YAML, JSON, shell script, etc.) → state out of scope, suggest appropriate tool. No findings.
• `--no-challenge`: skip adversarial review (challenger runs by default)
• `--challenge`: force challenger (Agent 7) even on small diff that small-diff auto-skip would otherwise skip
• `--full`: run **every** dimension the classification preselected, instead of only the `FANOUT_MAX` most relevant of them. Never widens the preselection — a dimension the FIX/CHORE/small-diff rules ruled out stays out. **Not free**: each extra agent costs ~120,851 tok of fixed overhead however little work it does. Default stays capped; pass this when depth matters more than cost.
• `--codemap`: strict mode — stop and report if codemap not installed (on by default when installed; use `--no-codemap` to opt out)
• `--semble`: enable semble semantic search companion (off by default)

**PR#/filename disambiguation gate** (execute BEFORE Step 1): tighten classification — valid PR# is positive integer with no extension and no existing file at that path. Filenames that look like numbers (e.g. `42.py`) must NOT trigger PR mode.

TOKEN="$ARGUMENTS"
if [[ "$TOKEN" =~ ^[0-9]+$ ]] && [ ! -e "$TOKEN" ]; then
    echo "PR number detected — checking oss plugin availability"
    [ -f "$(ls -td ~/.claude/plugins/cache/borda-ai-rig/oss/*/skills/review/SKILL.md 2>/dev/null | head -1)" ] && OSS_AVAILABLE=true || OSS_AVAILABLE=false  # timeout: 5000
elif [ -f "$TOKEN" ]; then
    OSS_AVAILABLE=skip
elif [[ "$TOKEN" =~ ^#[0-9]+$ ]] && [ ! -e "$TOKEN" ]; then
    echo "PR number detected — checking oss plugin availability"
    [ -f "$(ls -td ~/.claude/plugins/cache/borda-ai-rig/oss/*/skills/review/SKILL.md 2>/dev/null | head -1)" ] && OSS_AVAILABLE=true || OSS_AVAILABLE=false  # timeout: 5000
else
    OSS_AVAILABLE=skip
fi

If `$OSS_AVAILABLE` is `skip`: proceed to Step 1 normally (path / diff / dir mode).

If `$OSS_AVAILABLE` is `true`: call `AskUserQuestion` ONCE with BOTH questions in the same call (a second sequential window costs another human-idle round trip) — Q1: "Looks like you passed a PR/issue number. Did you mean to run `/oss:review $ARGUMENTS` (requires oss plugin) to review that PR?" Options: (a) "Yes — launch `/oss:review $ARGUMENTS`" · (b) "No — review local code". Q2: "If reviewing local code: provide the file path or directory (free text; skip if Q1 = Yes)". On (a): call `Skill(skill="oss:review", args="$ARGUMENTS")`, ignore Q2. On (b): use the Q2 response as `$REVIEW_ARGS` and proceed to Step 1 (Q2 empty → ask once more for the path).

If `$OSS_AVAILABLE` is `false`: call `AskUserQuestion` ONCE with BOTH questions — Q1: "Looks like you passed a PR/issue number, but oss plugin not installed — `/oss:review` unavailable. Review local code instead?" Options: (a) "Yes — review local code" · (b) "I need oss plugin". Q2: "If reviewing local code: provide the file path or directory (free text; skip if Q1 = b)". On (a): use the Q2 response as `$REVIEW_ARGS` and proceed to Step 1 (Q2 empty → ask once more). On (b): inform user: install with `claude plugin install oss@borda-ai-rig`.

</inputs>

<constants>

FANOUT_MAX=3            # default: top-N spawn UNITS among classification-preselected dimensions
                        # cap counts dimension spawn units only; real default lineup = up to 3
                        # dimension units + challenger + bridge co-review + consolidator
                        # (+ up to 3 cross-validation verifiers when criticals exist)
                        # --full runs ALL preselected units instead — no numeric cap
AGENT_CALL_BUDGET=55    # target tool-calls per