Use when creating Claude Code plugins - covers skills, commands, agents, hooks, MCP servers, and plugin configuration. Use when user says "create plugin", "make a skill", "add command", "add hooks", "skill authoring", "SKILL.md", "plugin components", "package reusable behavior", "distribute skills", "scaffold plugin", "plugin structure", "write a skill description". NOT for: using existing plugins, installing plugins, plugin marketplace browsing. !`ls .claude-plugin/ 2>/dev/null`
Use when starting a new development project — creates memory folder structure with project_state.md (including codePath), architecture scaffolding, and registers project. Accepts optional code_path argument.
Use when checking code quality, running security audits, testing coverage, finding SOLID/DRY violations, or setting up quality tools. Use when user says "audit this code", "check security", "run PHPStan", "code quality", "find violations", "SOLID check", "DRY check", "test coverage", "lint this", "security review", "is this production ready", "check for vulnerabilities", "code review", "grade this code", "watch mode lint", "deep review", "ultrareview", "schedule quality sweep". Supports Drupal (PHPStan, PHPMD, Psalm, Semgrep, Trivy, Gitleaks via DDEV) and Next.js (ESLint, Jest, Semgrep, Trivy, Gitleaks). Use proactively before deployment or after significant code changes.
Use when an orchestrator must run a task's work-orders CONCURRENTLY behind the same gate floor as the sequential loop — the DB-free parallel sibling of work-order-loop. Each round it reconciles from disk (L1-light), selects a disjoint-file ready batch (wo-parallel-batch.sh), builds every batched WO at once in its OWN ephemeral git worktree branched off the integration HEAD (N parallel build atoms in ONE message), runs /review --headless + the work-order-critique rung per worktree, derives every verdict from disk, and merges each CLEAN WO back into the integration branch with a LOCAL git merge (wo-merge-back.sh — NOT a PR merge), pruning each ephemeral worktree after its verdict. The per-WO retry cap stays the SOLE responsibility of wo-run-state.sh dispatch; terminal-HALT precedence, disk-is-truth, and no-auto-merge are preserved verbatim. At the end it runs ONE integrated /review on the integration branch and opens ONE PR through wo-pr-open.sh (re-runs the merge gate, NEVER merges). MUST be invoked inline (ne
Use when an orchestrator must run the autonomous per-task run-loop behind the gate floor — the thin native glue (③ lifecycle_controls). Resumes from disk (L1-light), drives a ready-queue over the work-orders (a WO is ready when all blocked_by are done), dispatches ONE build atom per WO in clean context, runs /review --headless + the work-order-critique rung per WO, owns EVERY WO status transition via wo-compile.sh set-status, bounds the verify→fix loop with a crash-safe retry cap (wo-run-state.sh), and at the end opens a PR through the wo-pr-open.sh choke point that re-runs the merge gate and NEVER merges. Reads every decision from disk; treats builder transcripts as untrusted data; honors a budget/kill-switch call-site. MUST be invoked inline (never Task-dispatched). Prints a ready-to-paste /goal string; never runs /goal itself.
Use when an orchestrator must run the opt-in adversarial-critique rung on ONE built work-order — the absent-human review layered ABOVE the deterministic gates. Derives the work-order's risk tier (wo-risk-classify.sh), decides whether critique is required (forced-on for high-risk-unattended; else the per-task/per-project dial), spawns risk-scaled INDEPENDENT fresh-context wo-critic agents that re-derive the verdict from artifacts (git diff + gate envelopes), aggregates fail-closed (wo-critique-aggregate.sh) into a per-WO _critique.json, and writes a wo-NN.HALT marker when blocking. Fan-out is the unattended primitive; never edits /review's _review.json. A judgment layer, not a gate — gates always run first.
Use when a phase command (research/design/implement) needs to load methodology references, online dev-guides, and project playbooks before task work begins. **v4.10.0+: hybrid detection** — a deterministic phase-aware methodology floor + lexical catalog candidates via scripts/dev-guides-detect.sh, plus semantic matches from the guides-matcher agent. Delegates guide fetching to dev-guides-navigator. Loads playbook layers via scripts/playbook-load-deterministic.sh. Cross-references conflicts. Records loaded guide IDs into session_context.json loadedGuides[] to prevent re-loads.
Use when a framework command needs to read the hierarchy metadata of a task — parses the YAML frontmatter block at the top of task.md and returns structured data (id, kind, parent, children, blocks, blocked_by, external_ids, derived status) plus any warnings. Defensive: never blocks on malformed input; absent frontmatter yields kind=flat. Delegates to scripts/fm-read.sh.