tswift

Autonomous developer iteration loop driven by a thin orchestrator that dispatches coder/reviewer/diagnoser subagents. Pick a mode — fix (make tests green), feature (implement one or more features), optimize (push a metric), debug (root-cause a failure), ab-test (race candidate implementations), or prototype (explore design variants) — define a verification signal, confirm the plan with the user, then loop implement → verify → review → commit with all state kept in loop-log.md. Use when the user states a concrete engineering goal or says "keep iterating", "loop on this", "autoloop", or "iterate until fixed".

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.

Turn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.

Keeps the tswift project website in sync with runtime implementation changes — coverage numbers, feature tables, WASM binary, and content. Use when features are implemented, coverage changes, the runtime is updated, or the user asks to update/sync/refresh the website.

Spawn a pi subagent to handle a specific task in a separate process. Use when the user asks to delegate work to a subagent, run a task in parallel, or says "spawn a subagent", "use a subagent", or "run this with pi".

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

When user or agent need to construct a swift AST, see how the Rust frontend parses a construct — kind, text, line, resolved type, and decoded modifiers.

Understand how much of a Swift framework runtime implements, by framework and type. Use when the user asks about Foundation/SwiftUI/stdlib coverage, what APIs are implemented/missing/verified, or which framework APIs to build next.

Understand how much of the Swift standard library the runtime implements, by section and by member. Use when the user asks about stdlib coverage, what's implemented/missing/verified, which APIs to build next, or when planning stdlib work.

Implement Swift compiler features.

Create a pull request in the warp repository for the current branch. Use when the user mentions opening a PR, creating a pull request, submitting changes for review, or preparing code for merge.

Analyzes codebase implementation details. Use when you need to find detailed information about how specific components work — trace data flow, understand key functions, identify architectural patterns, and document technical workings with precise file and line references. Does not suggest improvements or critique the code; purely documents what exists.

Locates files, directories, and components relevant to a feature or task. Use when you need to find WHERE code lives — essentially a "Super Grep/Glob/LS" — especially when you'd otherwise reach for those tools more than once. Returns structured file locations grouped by purpose without reading or analyzing content.

Finds similar implementations, usage examples, and existing patterns that can be modeled after. Use when you need concrete code examples — like how networking is done, how a view model is structured, how tests are written, etc. Similar to codebase-locator but goes further by reading files and extracting actual code snippets alongside their locations.

Conduct comprehensive research across the codebase to answer questions about how it works, where things live, and what patterns exist. Synthesizes findings from locating files, analyzing implementations, and extracting patterns — then saves a structured research document to docs/research/. Use when you need a thorough, documented answer about any aspect of the codebase.