Commands

A live /agents-tree pane showing the session's subagents as a tree — status, how long each has run, its tool calls and steps, the tool it is on now and the output tokens it used

Experimental Claude Code mods for GraphOS Agent Services. GraphOS Inspector explains each execute call in a docked pane before you approve it, shows what came back with clickable records, and can auto-approve the reads you write trust rules for.

Your Pokémon party journeys through a pixel world above the Claude Code prompt: it runs while Claude works, cheers when tests pass, faints when they fail, levels up and evolves.

A debugger for Claude Code tool calls: breakpoints, pause/continue/reject/step, a timeline, an inspector, Error Lens failure diagnosis, a Permissions view of who refused each call and why, and sanitized trace exports.

Run your socials from Claude Code: the Creator OS connector, skills, and a live pane for accounts, scheduled posts and your inbox.

A /usagemeter pane with cost, tokens and plan limits across Claude Code, Codex, OpenCode and Antigravity, read from local history and a CLIProxyAPI hub.

A pane showing each QRSPI task in thoughts/: which phase it is in, what blocks it, and the /qrspi:next command to run

/daiban side pane listing the in-progress and wrap-up items of a Markdown to-do log (NOTCH_TODO_LOG); writes ~/.claude/notch/todo.json.

/banben side pane of preview servers started by headless claude -p runs (port, effort level, done or running), using local lsof/ps; blocks opening more than 3 at once; writes ~/.claude/notch/versions.json.

Park an idea while Claude works, without interrupting it: /idea , or the shelf's own box. Ideas are kept per project across sessions, and Send puts one in the prompt box when you are ready. Starts off: /idea-shelf on turns it on

Hides secrets in tool results before Claude reads them: the secret values of every .env and .env.* from your session's folder up to the drive root, and anything that looks like a secret (KEY=VALUE under a secret name, passwords in URLs, private keys, JWTs, AWS keys, Kubernetes Secrets); tells Claude how to use them without printing them

See which files Claude has listed, read, partially read, edited, created or deleted, as a tree and an activity map in a pane.

A toolbox pane for Claude Code: run, stop and watch the project's build tasks, scripts, Claude commands and prompts from one list

A workspace pane for Claude Code: agents and worktrees, checkpoints, notes, changes and memory files in one tabbed pane

Status line score 0-100 for how good a moment it is to /compact now, with reasons; offers a ready /compact that keeps goal, decisions, leftovers and paths, and adds that template to every compaction. Never compacts by itself.

Looks up every new package before it installs: holds made-up names, typosquats, days-old releases and curl-into-shell for your answer, and lets the rest through.

Your Claude plan usage inside Claude Code: session (5h) and weekly limits with reset countdowns in the status line, a /tally pane with bars, and warnings at 75% and 90%.

A council of independent code reviewers (Codex, Pi, Devin, OpenCodeReview) runs over your working diff in parallel; one summary of agreements, disagreements and unique findings. /council, plus an auto-review that only notifies.

Shows the meny.no basket and the planned dinners in a pane, in the matlevering repo

A separate agent conversation in Claude Code's right-hand pane, forked from the current context.

A side pane listing the repository's GitHub issues, with one click to have Claude work on one

A To do / Doing / Done board in a side pane, filled by Claude's to-do list, approved plans and a board tool, plus your own cards

A side pane (and a band above the prompt) tracking channel messages waiting for a reply, running and recently ended tool calls and subagents, rate-limit quota, external dispatches, custom cards from your own commands, and the session itself; cards can be reordered, moved to the band or hidden without commands.

Docker Compose status band above the Claude Code prompt: service health, ports, crash and stale-config alerts, one-press actions