agentjsx

Authoring and diagnosing code in the agentjsx codebase (npm package `@flamecast/agentjsx`, locally at `/Users/arjun/Documents/github/effectctx`). The library lets you define an agent as a JSX tree — capability components install tools, block components emit prompt content, shaper components transform via `renderChildren`. Use whenever the user is writing new components (capability, content, or shaper), adding a new extension, debugging the render walk or tool reconciler, asking how a piece of agentjsx works internally, or referencing JSX patterns like `useRenderContext`, `runEffect`, `emitTool`, `emitFragment`, `renderChildren`. Also trigger on filenames in `src/jsx/`, `src/core/`, `src/platforms/`, `src/extensions/`, or any task touching `@flamecast/agentjsx` imports. Use proactively when you see `createAgentRuntime`, `<Workspace>`, `<Compact>`, `<McpServer>`, `<Skills>`, `<Todo>`, or any other agentjsx component in code — that's the strong signal you should consult this skill before authoring more.

Diagnose and improve Effect-TS code against canonical patterns. Use whenever the user is writing, reviewing, refactoring, or debugging code that imports from `effect`, `@effect/*`, or a project built on Effect (like effectctx). Covers Layer composition, Service/Context.Tag, error channels with Data.TaggedError, Scope and resource management, Stream/Queue/PubSub, Schema decoding at boundaries, fiber management, tracing with withSpan, and the anti-patterns that experienced Effect users keep flagging (missing `yield*`, unbounded concurrency, providing Layers twice, accessor R-leakage, etc.). Trigger on phrases like "review my Effect code", "is this idiomatic Effect", "audit the Layer composition", "why is this fiber not interrupting", "what's the right error type here", "convert this Promise code to Effect", or any task that involves writing non-trivial Effect-TS code where idiom matters.