corticalstack

Research requirements, technology choices, and constraints for a feature or project and write findings under flow/research/. Explicit workflow command; run only when invoked via /research-requirements or explicitly asked.

Bootstrap a new project with the Flow workflow - creates AGENTS.md from the template, creates .claude/tracker.json from the example, and optionally sets up cross-vendor review profiles. Run once per project after installing the Flow plugin. Explicit-only; do not auto-fire.

Research the codebase and author a phased implementation plan under flow/plans/ from an issue / work item or task. Explicit workflow command; run only when invoked via /create-plan or explicitly asked, never autonomously.

Generate a PR description from the repo template, save it under flow/prs/, and update the live PR. Explicit-only; run only when invoked via /describe-pr or the user asks to describe a PR.

Fetch PR review feedback, implement the requested changes, commit, push, and re-request review. Explicit-only; run only when invoked via /handle-pr-feedback or explicitly asked.

Execute an implementation plan from flow/plans/ phase by phase, pausing for verification between phases. Explicit workflow command; run only when invoked via /implement-plan or explicitly asked, never autonomously.

Document the codebase as-is via parallel read-only sub-agents and write findings under flow/research/. Explicit workflow command; run only when invoked via /research-codebase or explicitly asked.

Validate an implementation against its plan, run verification commands, and report issues before commit. Explicit workflow command; run only when invoked via /validate-plan or explicitly asked.

Use when building FastAPI applications, async Python REST APIs, Pydantic V2 schemas, SQLAlchemy async database operations, JWT/OAuth2 authentication, async pytest testing, RFC 9457 error handling, cursor pagination, or API versioning strategies.

Use when building, debugging, or extending MCP servers or clients that connect AI systems with external tools and data sources. Invoke to implement tool handlers, configure resource providers, set up stdio/Streamable HTTP transport, validate schemas with Zod or Pydantic, debug protocol compliance issues, or scaffold complete MCP server/client projects using TypeScript or Python SDKs.

Use when building Python applications requiring type safety, async programming, or robust error handling. Invoke for type hints, PEP 695 generics, async/await with TaskGroup, dataclasses, Pydantic v2, uv packaging, and structured error handling.

Use when implementing infrastructure as code with Terraform on Azure. Invoke for module development (create reusable modules, manage module versioning), state management (Azure Blob backend, import existing resources, resolve state conflicts), provider configuration, multi-environment workflows, and infrastructure testing.

Analyse Microsoft 365 license export CSVs - profile the data, compute per-SKU and per-department aggregates, identify reclaimable licenses, and return clean markdown tables.