meerkat

Internal architecture guide for the Meerkat agent platform. This skill should be used when understanding crate ownership, trait contracts, the agent construction pipeline, session service lifecycle, runtime control plane, mob orchestration internals, machine authority, comms wiring, or making cross-cutting architectural changes. Oriented toward AI agents and developers working on meerkat internals, not end users.

Build on the Meerkat agent platform. Covers every shipping surface (CLI, REST, JSON-RPC stdio/TCP, MCP, Python/TypeScript/Web/Rust SDKs), realm-scoped sessions, streaming, skills, hooks, memory, multimodal content, mob orchestration (spawn/fork/helpers/flows/profiles), durable scheduling, and provider auth via `auth_binding` + AuthMachine (env keys, OAuth, cloud IAM). Use when integrating with Meerkat, picking a surface, wiring auth, building agents, scheduling automated runs, deploying mobpacks, or asking how a feature exposes through a particular SDK.

Exact rkat CLI command contract for Meerkat help answers. Use this as the authority for command names, flags, aliases, and negative CLI facts.

Developer guide for the Meerkat WASM embedded runtime (meerkat-web-runtime) and the `@rkat/web` browser SDK. Covers wasm32 compilation, building/deploying WASM bundles, writing/auditing wasm_bindgen exports (sessions, mobs, comms, JS tool callbacks, external auth resolver, subscription handles), the auth_binding + registerExternalAuthResolver auth model, tokio_with_wasm aliasing, cfg-gating patterns, mobpack bootstrap, and common wasm32 gotchas. Use when touching meerkat-web-runtime, sdks/web, browser auth flows, or making a meerkat crate wasm32-compatible.

Ruthless Meerkat dogma inquisition for architecture, code, PRs, plans, tickets, ledgers, and designs. Use when Codex must find semantic-authority violations, shadow truth, provider leakage, surface-owned meaning, projection/mirror abuse, typed-truth failures, terminality lies, generation theater, or meta-level repeated dogma failure patterns; use for brutally honest reviews that cite concrete evidence and group symptoms by root dogma failure.

How to communicate with peers in a collaborative mob

How semantic memory works with compaction and the MemoryStore trait

Setting up keep-alive, peer trust, send vs request/response patterns

Writing hooks for the 8 hook points, execution modes, and decision semantics

How to configure MCP servers in .rkat/mcp.toml

How to author and inspect durable schedules from agent tools

Session persistence, resume patterns, event store replay, compaction tuning

How to use Meerkat built-in utility tools safely and productively

Background job patterns with shell and job management tools

How to browse, load, and use Meerkat skills during a session

How to use builtin task tools for private lightweight work tracking

How to use WorkGraph for durable commitments, dependencies, claims, and evidence

Set up a professional Rust CI/CD pipeline with pre-commit hooks, automated linting, testing, changelog management, and version control. This skill should be used when creating a new Rust project that needs CI/CD, when adding CI/CD to an existing project, or when troubleshooting pipeline issues. The pipeline follows the "Makefile as single source of truth" pattern and works without GitHub Actions for enterprise environments.

RCT (Representation Contract Tests) methodology for AI-assisted development. This skill should be used when creating implementation checklists from specifications, planning phased implementations, or when the user mentions "RCT", "representation contracts", "Gate 0", or asks for an "agent-ready checklist". It transforms specifications into executable, phased checklists with reviewer gates that an AI agent can autonomously execute.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.