autonomous-sdlc

Quickly understand a codebase before starting work - reads structure, key docs, and summarizes understanding

Cancel an active SDLC workflow and clean up resources

Check the status of an active SDLC workflow

Start an adaptive autonomous SDLC workflow — chooses coordination mode (agent teams, subagents, or solo) based on task complexity

Strategic architect that explores codebases, creates plan documents, and decomposes work into tasks with dependencies

Focused execution agent that implements ONE task at a time with PostToolUse validation hooks for automatic quality enforcement

Documentation sync agent that updates README, docstrings, and API docs to match code changes after implementation is validated

Merges task branches into feature branch, resolves conflicts, and verifies combined code passes all checks. Optional — lead uses when dedicated merge attention is needed.

Creates pull/merge requests with rich descriptions generated from plan documents, supporting both GitHub and GitLab

Read-only verification agent that validates builder work without modifying code. Provides direct feedback to builders in team mode.

Reference pattern for worktree isolation and wave management. Not a spawnable agent — the lead orchestrator consults this guide when using worktrees for parallel isolation. Claude Code handles worktree lifecycle natively via isolation: "worktree" on the Task tool.

Use AFTER bdd-spec has produced acceptance criteria, or when the user has existing Given/When/Then scenarios that need pytest-bdd scaffolding. MUST NOT run without existing acceptance criteria — invoke bdd-spec first if none exist. Trigger: "generate feature files", "scaffold BDD tests", "wire up pytest-bdd", "make these criteria runnable", "create step definitions". This is mechanical code generation, not spec writing.

Use INSTEAD OF superpowers:brainstorming when the user wants structured acceptance criteria in Given/When/Then format. This is the right choice when requirements need to be testable — not just designed. Trigger: "spec this out", "acceptance criteria", "BDD", "behavior driven", "what should happen when", "edge cases", "define requirements", or any pre-implementation requirements discussion where the output should be runnable scenarios, not just a design doc. Produces Gherkin-ready acceptance criteria. Not for generating test code — use bdd-generate after this.

MUST use when creating, updating, or closing Beads issues via `bd` commands. Use proactively when starting work (bd update --status=in_progress) and completing work (bd close). Trigger: any mention of "issue", "task tracking", "what should I work on", "bd create/ready/close", or when the session hook indicates beads is active. Provides full bd CLI reference and workflow patterns.

Save SDLC workflow feedback proactively. MUST trigger when the user corrects SDLC behavior ("don't generate tests like that", "always use this pattern", "that's not how I want specs written") or confirms a non-obvious approach worked ("yes exactly", "perfect"). Also trigger on explicit requests: "save this feedback", "show my feedback", "clear feedback", "workflow preferences", "sdlc settings", "consolidate feedback", "bake in my preferences". Feedback persists across sessions and is loaded by BDD, TDD, beads, and verification skills.

Python-specific TDD wrapper. Use INSTEAD OF superpowers:test-driven-development when the project uses uv + pytest. Adds: feedback loading from autonomous-sdlc, uv run pytest commands, test directory organization (unit/integration/e2e). Delegates core TDD discipline to superpowers:test-driven-development. Trigger: "TDD", "test first", "red green refactor", "write a failing test" in any Python/pytest project.

Python verification pipeline: ruff + pytest + type checking in sequence. Use INSTEAD OF superpowers:verification-before-completion when the project uses Python tooling. MUST run before any commit, merge, or PR claim in a Python project. Trigger: "run all checks", "verify the code", "is the build green", "run ruff and pytest", or proactively before claiming work is done.

3 hooks across 3 events