extra

Guard the project's architecture invariants. Use to evaluate any change affecting layers, boundaries, lifecycles, or contracts, and to decide whether an ADR is required.

Senior-level code review for the agent platform — architecture and boundaries first, then correctness, security, testability, and simplicity. Outputs a structured review.

Keep the repository's documentation accurate, honest, and synchronized with the code. Use when editing docs, README, AGENTS.md, or ADRs.

Work safely with Git — keep changes scoped and reviewable, never overwrite the user's work, and produce clear history. Use before editing, branching, staging, or committing.

Working on Python plugin tools, MCP server connections, tool invocation, or tool tracing. Primary task is tasks/0007-mcp-tools-and-permissions.md.

Foundational rules and layout for the declarative agent platform. Read this before any change, regardless of area; it anchors every other skill.

Working on prompt templates, template loading/caching, or per-request rendering. Primary task is tasks/0005-prompt-rendering.md.

Change the shape of code without changing behavior — safely, in small steps, preserving the project's layers and public contracts.

Working on RuntimeEngine, ExecutionContext, agent execution, or the request lifecycle. Primary tasks are tasks/0003-compiled-agent-graph.md and tasks/0004-runtime-engine.md.

The standard for writing Python here — small, typed, explicit, testable modules with side effects pushed to the edges. Use when implementing or designing any Python code.

Working on resolver plugins, the fixed access plugin contract, mapping resolver outputs into ExecutionContext, or protected-node filtering. Primary task is tasks/0006-sidecar-auth-context.md.

How to create or restructure a skill so the .ai/skills/ system stays consistent, operational, and trustworthy. A skill is a short, repeatable playbook — not an essay.

How to write and run fast, deterministic, behavior-focused pytest tests that never touch real external systems. Use whenever adding or changing behavior, or fixing a bug.

Loading agent.yml, defining schema models, and validating the specification (definitions, hierarchy, security). Primary task is tasks/0002-yaml-schema-and-validation.md.