martinffx

Execute implementation tasks from an approved plan.json. Use when spec-plan has produced approved tasks and the human is ready to start coding. Tracks progress via beads (preferred) or harness-native todos, enforces TDD, reports between batches. Trigger when the user says "implement", "go", "start", "do it", or after spec-plan completes task creation. Do NOT use without an approved plan — invoke s

DDD and hexagonal architecture with functional core pattern. Use when designing features, modeling domains, breaking down tasks, or understanding component responsibilities.

Security architecture and threat modeling knowledge. Auto-invokes when designing features that handle untrusted data, authentication, authorization, external integrations, file uploads, or sensitive data. Provides risk assessment frameworks, trust boundary analysis, and security design principles — not implementation code.

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Multi-agent code review with parallel specialized reviewers, architecture validation, and challenge validation. Use `rq` to request a review of diffs (defaults to main branch), `rs` to respond to review findings. Triggers on "review this", "review my code", "code review", "check for bugs", "audit this", when examining PRs, pull requests, branches, or diffs. Always asks user before applying fixes.

DynamoDB single-table design using dynamodb-toolbox v2. Use when creating entities, defining key patterns, designing GSIs, writing queries, implementing pagination, or working with any DynamoDB data layer in TypeScript projects.

Socratic interrogation of plans against the project's domain model and documented decisions. Use when the user wants to stress-test a plan, clarify terminology, or validate assumptions against existing domain language. Updates CONTEXT.md and ADRs inline as decisions crystallise.

Adversarial review of non-trivial decisions using fresh-context scrutiny. Use when correctness matters more than speed, when stakes are high (production, security-sensitive logic, irreversible operations), or before committing significant architectural or implementation choices.

TypeScript project tooling with Bun, tsgo, Vitest, Biome, and Turborepo. Use when setting up package.json scripts, running builds, typechecking, configuring tests, linting, formatting, or orchestrating monorepo development.

Python application architecture with functional core, effectful shell, DDD, and data modeling. Use when designing application layers, separating pure business logic from IO, defining domain models, implementing validation, or structuring bounded contexts.