super-compound

Use when following the Super Compound BRD -> PRD -> FSD -> GOAL -> IMPLEMENTATION -> VERIFICATION delivery path, artifact traceability, FSD authority, optional ADR handling, zero context bloat issue slicing, or OPEN-* stop conditions.

Use when an approved FSD goal or lightweight issue pointer is ready for implementation.

Use when multi-component work needs cross-component verification of API contracts, data flow, events, auth, config, UI, background jobs, or tests.

Use when /sc-plan needs FSD GOAL-* packets turned into lightweight issue pointers, local Markdown Kanban boards, blocker DAGs, or multi-agent task contracts.

Use when a plan or issue board has 2+ independent execution streams whose time saving exceeds coordination overhead. Dispatches agents in isolated git worktrees only after required delivery gates pass.

Use when an FSD and goal issue board need requirement coverage, goal quality, dependency DAG, sizing, and verification validated before execution.

Use when an approved BRD must be translated into observable product requirements before FSD planning.

Use when executing FSD goals with independent work packages. Dispatches a fresh subagent per goal with file-backed handoff and bounded review.

Use when /sc-plan or /sc-status needs to classify incoming issues, local Markdown issues, external PRs, feature requests, bug reports, stale tickets, ready-for-agent work, or wontfix decisions.

Use when an approved PRD needs an implementation-authoritative FSD before code is written.

Use when file placement, dependency direction, framework conventions, or project architecture presets must be verified before writing code.

Use when creative product, feature, UI, or behavior work needs intent, requirements, constraints, or design explored before implementation.

Use when introducing dependencies or auditing runtime support, peer conflicts, deprecations, vulnerability posture, and rollback risk.

Use when work needs shared domain language, CONTEXT.md updates, conditional ADR decisions, glossary cleanup, or terminology checks during BRD, PRD, FSD, triage, architecture, or goal shaping.

Use when building, redesigning, or reviewing frontend UI: pages, components, dashboards, landing pages, mobile screens, charts, and interaction states.

Use when auditing code for security vulnerabilities, reviewing auth flows, checking OWASP Top 10 risks, validating secrets handling, or assessing dependency and agent-surface security.

Use when implementing a feature, behavior change, or bugfix that requires production code.

Super Compound /sc-* .agent workflows.

Use when human information, judgment, approval, testing, credentials, review, or external action is genuinely required before proceeding.

Use when reviewing code changes for specification compliance, correctness, quality, security, and maintainability.

Use when you need up-to-date library/API documentation, code examples, version-specific guides, or framework conventions. Wraps the Context7 MCP tools with a clear usage pattern and fallback strategy.

Use when processing personal data (PII), implementing consent mechanisms, or handling data subject requests. Covers GDPR, UU PDP Indonesia, and privacy-by-design principles.

Use when non-trivial or AI-assisted behavior needs measurable success criteria and repeatable reliability evidence.

Use when verification, review, or manual testing identifies concrete gaps in otherwise planned or completed work.

Use when starting Git work, preparing commits, pushing branches, opening Pull Requests, or coordinating optional git worktrees.

Use when a non-trivial problem is solved or substantial work should make future sessions easier.

Use when implementing input validation, cryptography, data encryption, or secure data handling. Covers allowlist validation, context encoding, password hashing, encryption at rest/transit, and JWT security.

Use when creating, editing, or verifying a skill before deployment.

Use when non-trivial work needs durable, bounded project memory across checkpoints or sessions.

Use when encountering a bug, test failure, unexpected behavior, intermittent result, or error.

Use when designing features that handle sensitive data, authentication, or external integrations and need STRIDE, attack-tree, or trust-boundary analysis.

Use when ideas or tasks surface during work and must be captured, tracked, and routed without losing current-task focus.

Use when about to claim work complete, fixed, passing, or ready, including before moving to the next planned task.

Use when designing or improving module interfaces, test seams, deep modules, adapter boundaries, architecture options, codebase health, or AI-navigable refactors.

Use when managing AI context budget, selective file loading, history digests, and fresh-session handoffs.

Use when /sc-explore needs throwaway runnable evidence for uncertain state models, business logic, architecture options, UI directions, interaction design, or decisions that are cheaper to test than debate.