Guards

Implement an agreed plan with an enforced adversarial review loop: every phase commit is gated on an external review.

Keeps a brief of the session above the prompt: what it is for and where it stands; /brief adds what was done and decided, what waits on you, and what comes next

Autonomous optimize-measure-keep/discard loop: skill, run/log/stats tools, and a live experiment dashboard

Autonomous experiment loop for Claude Code: run, measure, keep or discard. A port of pi-autoresearch.

Replaces a secret with a format-preserving fake before the model reads it, and restores the real credential on the way into a tool call. The map survives a resume or a reload; set persist off to keep it in memory only.

btop-style live dashboard for Claude Code internals: /cctop opens it in a side pane, cctop-insights lets the session answer questions from its numbers

A status line under the prompt: context, cache hit rate, cache TTL countdown, today's spend for this project, and why a turn missed the cache. /usage prints the project ledger.

Hook-enforced development discipline for Claude Code. Skills teach methodology; hooks enforce compliance mechanically (git gates, planning mode, step budgets, quiet mode, pre-flight checks, self-diagnosis, autonomy metrics); store + tracing survive compaction.

Arcade games above the Claude Code prompt (a dodge race, Breakout, a dino runner and a side-scrolling shooter) that pause when Claude finishes a turn and react to the edits, tests and commits Claude makes. Needs function hooks (early access) and an interactive terminal.

Play Word Exchange Plaza's levels as a text game beside Claude while it works

Fighting-game combo meter for Claude Code: every clean tool call is a hit, every error breaks the chain. Ranks D to SSS, special moves, and an all-time high score.

/explain: get answers as ASD-STE100 prose, a diagram, an HTML page, or a 3b1b-style video

Claude Clubhouse: a toolbar above the prompt, rooms for usage, agents, commands, tool rules and colors, and whole-window themes on macOS

Turns xcodebuild and swift build output into a live pane of errors grouped by file, and hands Claude the diagnostics instead of the raw log.

A pixel-art crab in a side pane that grows while you work with Claude Code, and teaches you Claude Code

A pixel-art monster in a side pane that eats tokens and shows context, limits and activity at a glance

Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page report, specialist agents, and an optional live progress pane (early access).

Painel ao lado da conversa com agentes, diffs como no VS Code, contexto, turnos com os comandos, árvore de arquivos ao vivo e inventário de plugins, e uma linha de resumo colorida acima do prompt. Só observa.

Status band above the prompt: context weather, usage limits, and the Ponytail and Caveman levels

An orange cat above the prompt that reacts to your commits, tests and builds

/live: full-duplex voice (Kyutai streaming STT with semantic end of turn, or Silero and Whisper; Kokoro TTS) through a sidecar; /vibe: director mode that delegates all work to subagents; /livevibe: talk with a fast voice front that hands the work to Claude as director.

A desktop mascot overlay that reacts to turns, tool calls and subagents

EXPERIMENTAL. Answers a WebSearch from the local Claude Code doc mirror, context7, Brave or Exa, and adds a detached deep-research rung behind a handle.

EXPERIMENTAL. Deliver frontmatter-triggered rules at matching prompts and tool calls.