engineering

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

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.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Compact the current conversation into a handoff document for another agent to pick up.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.

Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.

Use when adopting an agent in a new or existing repo, when agents re-explore the codebase every session, when project state (done/doing/abandoned) is scattered or stale, when switching issue trackers (local ledger, GitHub, Linear, custom), when wiring an orchestrator to dispatch agent work autonomously (acceptance gates, failure states, dependency unblocking), when a long-horizon roadmap or milestone sequence needs a durable home agents pick up every session, when workflow skills (to-issues, to-prd, triage) need tracker/label/artifact/domain-doc/quality-gate config, or when an existing harness needs refresh or a drift check.

Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

Use when writing, reviewing, debugging, or refactoring Swift 6.2, SwiftUI, or SwiftData code for iOS 26 and later in an Xcode project.

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Break a plan, spec, or PRD into independently-grabbable work artifacts through the repo harness using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

Turn the current conversation context into a PRD and publish it through the repo harness. Use when user wants to create a PRD from the current context.

Triage tracker items through a state machine driven by harness-mapped triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare work for an AFK agent, or manage issue workflow.

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.