udecode

Structured code review when explicitly requested, preferring OpenAI/Codex before Claude.

Transcribe a supplied local or linked video with Gemini Files API when its contents are needed as evidence.

Autonomously close the current Plate work tree through source sync, proof, review, checks, GitHub delivery, and final audit without expanding product scope.

Work a task end-to-end with lean context gathering, implementation, and verification

Create, verify, repair, and close durable Codex goals with measurable outcomes, evidence gates, plan templates, blocker handling, completion audits, and goal-backed workflow repair.

Pre-commit/ship code review: Codex default; optional Claude, Pi, Droid, Copilot, or OpenCode.

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Work heavyweight framework or library tasks with planning-first research, selective deep analysis, and rigorous handoff

Use for Convex/kitcn setup and feature work: cRPC, ORM, auth, React.

Autonomously close the current kitcn work tree through source sync, proof, review, checks, GitHub delivery, and final audit without expanding product scope.

Skill: 4-ultracite

Work a task end-to-end with lean context gathering, implementation, and verification

Skill: concave-parity

Autonomous kitcn supervisor for sweep, clean, full, design, milestone, PRD, timed, and review-until work. Compiles a run profile, keeps evidence-backed state, decomposes local task packets, repairs its workflow, and closes through GitHub delivery.

Create, verify, repair, and close durable Codex goals with measurable outcomes, evidence gates, plan templates, blocker handling, completion audits, and goal-backed workflow repair.

Pre-commit/ship code review: Codex default; optional Claude, Pi, or Kimi.

Show every Claude Code and Codex session on the iPhone lock screen through ActivitySmith and in the Mac menubar, with each plan page's pipeline, and buzz when a session needs you, ships or fails.

Set up the pstack plugin in a project through an interview, and keep every pstack project on one pinned tag and one shared AGENTS.md overrides block. Use to set up or install pstack in a repo, sync, bump or update pstack everywhere, list which projects use…

Write, check, repair and publish a plan page: a project's plans and subject files under its plans directory, rendered by .agents/pstack/plan-page.mjs and rendered as one local HTML page per subject with a local index of every subject, and published to…

Redo a prior pstack run at the current session's higher effort or stronger model, treating its plan as a draft: rerun only the plan, design, subagent and seat lanes, code and review judgments that ran below the current level, and reuse the rest. Use for "redo…

Turn Remote Control on for every non-archived Claude Code session in the Claude desktop app.

Present final screenshots or rendered artifacts as an annotated walkthrough when visual evidence is requested.

Audit existing tests for low-value, duplicated or implementation-coupled cases and the test-only code they keep alive, then remove or rewrite them on evidence. Use for test-audit, /test-audit <scope>, a test sweep, or pruning tests. Not for writing a new…

Manage native Codex goals under a direct or standing user request, with durable acceptance and completion evidence.

Structured code review when explicitly requested, preferring OpenAI/Codex before Claude.

Transcribe a supplied local or linked video with Gemini Files API when its contents are needed as evidence.

Create and manage Google Forms programmatically via MCP. Use when: (1) creating survey forms, (2) adding questions/sections to forms, (3) getting form responses, (4) converting AskUserQuestion to shareable forms. Covers setup, all tools, item ordering, and…