dc-setup
25Command
Install devco-agent-skills into the current project. Interactive wizard — always asks user preferences before configuring.
Command
Install devco-agent-skills into the current project. Interactive wizard — always asks user preferences before configuring.
Command
Show full plugin state: detected project type, Summer Framework status, loaded skills, loaded rules, context usage estimate, hook profile, installation status, and git info.
Command
Generate and run end-to-end API tests with Testcontainers for Spring Boot (MVC and WebFlux) applications.
Command
Umbrella for learning, evolution, ADR generation, and architecture review. Subcommands cover the Learn layer of the workflow (Layer 5) plus on-demand maintenance gates.
Command
Run OWASP Top 10 security scan on Spring Boot project with automated scripts. Requires explicit authorization.
Command
Decompose chosen solution into vertical slices with dependency graph. Reads Align + Brainstorm artifacts. Blocks for high-stakes lane without brainstorm artifact. WAIT for user CONFIRM before any code.
Command
Generate behavioral spec from approved plan -- define observable contracts before implementation. Gate between PLAN and BUILD phases.
Command
Generate threat model for Spring Boot application using STRIDE methodology.
Command
Classify task scope, route to workflow lane (trivial / standard / high-stakes). Use to override auto-triage from SessionStart.
Command
Run build, test, lint, security, and static analysis pipeline. Modes -- quick, pre-commit, full, gate.
Skill Claude CodeCodex
Production-ready gRPC patterns for Java 17+ / Spring Boot 3.x.
Hook
Runs when a session starts, executing session-init.sh via bash. From taipt1504/agent-skills.
Hook
Runs when a subagent starts, executing subagent-init.sh via bash. From taipt1504/agent-skills.
Hook
Runs before the agent uses a tool for Bash, Edit, Write, MultiEdit, Edit, Write, MultiEdit and Bash tool calls, executing preflight-discovery.sh, preflight-gate.sh, workflow-gate.sh, skill-router.sh, compact-advisor.sh and git-guard.sh via bash (6 commands). From taipt1504/agent-skills.
Hook
Runs after a tool call finishes for Edit, Write, MultiEdit, Edit, Write, MultiEdit, Bash, Bash and Bash tool calls, executing quality-gate.sh, build-checkpoint.sh, docs-index.sh, workflow-phase-lock.sh, workflow-tracker.sh and verify-fix-loop.sh via bash (6 commands). From taipt1504/agent-skills.
Hook
Runs before the context is compacted, executing pre-compact.sh via bash. From taipt1504/agent-skills.
Hook
Runs after the context is compacted, executing post-compact.sh via bash. From taipt1504/agent-skills.
Hook
Runs when the agent finishes a response, executing session-save.sh, auto-adr.sh and evolution-check.sh via bash (3 commands). From taipt1504/agent-skills.
Skill Claude CodeCodex
Surface ambiguity, missing requirements, hidden assumptions BEFORE planning. Fires after triage for standard (vague request) or high-stakes (always). Updates CONTEXT.md vocabulary. Produces agreed-requirements artifact feeding Plan gate.
Skill Claude CodeCodex
REST API design patterns for Spring Boot — HTTP methods, status codes, URL conventions, RFC 7807 ProblemDetail errors, pagination, versioning, validation, and OpenAPI documentation. Use when designing REST endpoints, choosing HTTP status codes, implementing error responses, adding pagination to list APIs, versioning…
Skill Claude CodeCodex
Hexagonal architecture, DDD, CQRS, and event sourcing for Java Spring applications. Use when designing package structure, creating Aggregate Roots or Value Objects, implementing ports and adapters, setting up CQRS command/query separation, wiring domain events, writing ArchUnit tests, or creating solution architecture…
Skill Claude CodeCodex
Foundation skill — auto-loads at SessionStart. Teaches 5-layer adaptive workflow, 1% pre-flight discovery rule, triage routing, skill announcement contract, project detection. All other skills depend on this. Do NOT manually load.
Skill Claude CodeCodex
Tournament-style iterative solution exploration. Generates 2-5 candidates via adversarial challenges, compares multi-dimensionally, recommends with explicit trade-offs. Mandatory high-stakes (≥3), conditional standard. Output feeds Plan + ADR for high-stakes.
Skill Claude CodeCodex
Unified Java code review + coding standards skill (alias "code-review"). Enforces ALL six rule sets — CORE-, MVC-, RX-, WFL-, XCT-, JKS- — across BUILD (REFACTOR self-check) and REVIEW (Stage 2 findings). Every finding cites [ ][ ]. Also encodes Java 17+ patterns (records, sealed, pattern matching), naming, Lombok…