Multi-stack coding standards and verification. Smart router auto-detects the active surface and loads matching code patterns.

Stack-agnostic code-review baseline: findings-first severity, mandatory security/correctness minimums, sk-code evidence.

MCP orchestration via TypeScript execution. Use Code Mode for ALL external MCP tool calls; ~98% context reduction, type-safe.

Routes ClickUp between cupt CLI (daily ops) and official MCP (docs, goals, bulk). Embedded install and agent safety invariants.

Chrome DevTools orchestrator: routes between bdg CLI (fast, token-efficient) and Code Mode MCP (multi-tool integration).

Autonomous iterative code-review loop with externalized state, convergence detection, P0/P1/P2 findings, fresh context per pass.

Autonomous deep-research loop: iterative investigation, externalized state, convergence detection, fresh context per pass.

Shared deep-loop runtime: executor + prompt-pack + validation + atomic state + coverage-graph + Bayesian scoring + fallback routing.

Evaluator-first bounded agent improvement: 5-dim scoring, dynamic profiling, packet-local candidates, guarded promotion.

AI Council: multi-seat planning, artifact persistence, convergence checks, packet-local ai-council outputs.

OpenCode CLI orchestrator: external dispatch, in-OpenCode parallel sessions, cross-AI handback with full runtime context.

Gemini CLI executor for Google Search-backed research, architecture sweeps, large-context analysis, and validation.

Devin CLI orchestrator: dispatch Cognition AI's 'Devin for Terminal' for autonomous coding work with optional local-to-cloud handoff.

Codex CLI executor for OpenAI-backed coding, repo analysis, PR review, web research, and cross-model validation.

Claude Code CLI executor for Anthropic-backed reasoning, edits, reviews, and structured cross-AI handoff.

Create or update OpenCode skills via one unified command with operation routing. :auto/:confirm.

Guide users through the MUXI platform -- infrastructure for AI agents. Covers installation (CLI and server), server setup and configuration, CLI commands and workflows, secrets management, writing formations (Agent Formation Schema), deploying formations, registry operations, and using both the Server API and Formation API. Use when the user asks about MUXI setup, CLI commands, formation authoring, secrets, deployment, the registry, server configuration, agents, MCP tools, overlord, memory, or any "how do I..." question about MUXI.

Use when creating or updating skills, testing skill behavior with subagents, repairing unclear triggers or observed misbehavior, designing pressure tests, closing loopholes, addressing rationalizations, or validating skill folders before deployment.

Use when creating pull requests, updating pull request branches, pushing or publishing work for review, editing pull request metadata, or submitting stacked branches. Load and follow the git-spice skill for the workflow.

Mandatory for Git repository operations involving commits, amendments, fixups, branch creation or movement, stacked branches, pushes, pull request creation, pull request updates, review submission, publishing, or recovery from raw Git usage. Use git-spice for supported operations; do not bypass git-spice for commits, branches, stack movement, pushes, or pull request submission.

Use when committing work, amending commits, creating fixup commits, creating branches as part of committing work, stacking work, inserting prerequisite work below the current branch, or recovering after raw Git commands. Load and follow the git-spice skill for the workflow.

Use when deciding whether a repository change needs a changelog entry, creating or updating Changie unreleased entries, choosing the correct changelog kind, or writing user-facing changelog body text in repositories that use `.changie.yaml`.

Run Motif to generate your vibe report, launch the live dashboard, or personalize your CLAUDE.md and skills. Use when the user says "motif", "run motif", "vibe report", "generate my report", "motif live", "start the dashboard", "analyze my coding patterns", "personalize my AI", "generate rules for me", or "motif analyze".

Handles end-of-session housekeeping: committing code, pushing to remote, deploying, and summarizing progress. Prevents forgotten commits and undocumented progress. [GENERATED BY MOTIF — review and customize]