Antigravity Cli
>-
Check Model Usage
Checks quota/usage and session + weekly pacing across all 5 AI coding harnesses in one command -- Claude Code, Codex CLI, Antigravity (agy), GLM/Z.ai, and Kimi/Moonshot -- using only the CodexBar CLI (no TUI probes, no direct provider API calls). Use this whenever the user asks "how much quota do I have left", "am I going to run out before the weekly reset", "check my usage/limits across tools",…
Add To Changelog
Add a new entry to the project's CHANGELOG.md following the Keep a Changelog format and Semantic Versioning. Use when the user asks to "add a changelog entry", "update the changelog", "log this change", or runs /add-to-changelog with a version, change type, and message. Creates CHANGELOG.md if missing, adds the entry under the right version + change-type section, and keeps formatting consistent.
Model Classifier
>-
Interview
Interview the user in depth (via the AskUserQuestion tool) to turn a rough idea, plan file, or feature request into a concrete spec — then capture the result one of three ways. Use when the user runs /interview, or asks you to "interview me about this plan/feature", "grill me on the details", "flesh this out into a spec", or "turn this into Linear issues". Not for casual clarifying questions — th…
Peek
>-
Remotion Explainer Video
>-
Update Docs
Analyze changes since the last git commit and update README.md, docs in /docs/, and CLAUDE.md/AGENTS.md to reflect new features, config, commands, and architectural changes. Use when the user asks to "update the docs", "sync the README", "document what changed", or runs /update-docs. No arguments — it detects changes automatically.
Issue Breakdown
Break a feature or initiative into a Linear epic (project) plus small, review-ready issues that meet a strict quality bar: every issue is a user story ('as a role, I want an action, so a result') with explicit acceptance criteria, a Fibonacci estimate of 3 points or less (anything larger is split), a parent epic/project, blocker and dependency links, and labels; design issues also carry a screens…
Finch
>-
Skill Maker
Toolkit for authoring and iterating on Claude Code skills end to end. Create a new skill, edit or improve an existing skill, run skill evals, benchmark skill performance with baseline comparison and variance analysis, and optimize a skill's description for reliable triggering. Use whenever the user wants to create a skill, edit or improve a skill, test or benchmark a skill, set up skill evals, or…
Coderabbit Request
Use after completing file changes - strongest for source code (AST-aware linting, security, tests), lighter support for markdown/config. Dispatches CodeRabbit reviewer subagent via the gob background runner. ALWAYS request review before considering work complete.
Cmux Agent Orchestrator
>-
Convex Domain Folder
>-
Cmux Pr Qc Agent
>-