Commands

Every subagent Claude starts waits for your approval: approve, refuse, approve all for the turn, change its model (suggested by the task's complexity) or add a note to its task. A pane lists the agents waiting, the full task and recent decisions, the same in the terminal and the desktop app.

A control panel tucked into the corner above the Claude Code prompt, in five modules you turn on or off: where your tokens go (files, chat, MCP, shell, skills and plugins, subagents and more), model and effort pickers in three styles, prompt-cache countdown with a 2-minute keep-warm alert, handoff buttons, and next steps (follow-up prompts after each reply, one key to put in the prompt box).

Ather Automata: what needs you and what is next in every S2 session and web app repository (Plan, Build, Prove, Ship), a newcomer tour, autonomy windows, and guards that catch false build passes and lost merge edits.

Ather Board: the team's intents as a project board. /board shows what is stuck, every intent by owner, area or stage, the open acceptance items and each person's and area's load; /board open writes the full page with a kanban and the weekly pulse; /board publish shares it. Read-only.

Pane for the per-repo aq prompt queue: pick items, batch them into the prompt box, queue drafts, and let Claude queue follow-ups

Runs each repo's dev servers as named services on fixed ports, with a pane, filtered log reads and start/stop tools for the model

A pane showing the milestone and task tree of spec/*/tasks.md and implementation_plan.md files; press a task to tick it

Keeps AI coding agents inside your project's rules, from idea to merged code: spec design, lanes, layer rules, protected paths with an approval log, spec-check and design gates, proof-before-finish checks, dispatch, review, build status and CI verification, configured per project from its docs

A menu for the tool mods in this repo and for your own commands: a button in the footer under the prompt box opens a menu pane, docked on the right, with a Prompt Upgrade switch, one-press shortcuts to /better and /report, and USER and PROJECT sections listing your own skills and commands, each of which you can turn off. A remote control, so every row runs a command that already exists.

Context window details like the Desktop app's panel: /ctx opens a pane that docks beside the transcript, and a 📊 button above the prompt toggles it.

Turns a rough prompt into a great one before it is sent: /better opens a pane that asks up to three quick questions, rewrites the prompt and shows both side by side. Nothing runs until you press Run.

Progress bar above the prompt plus an agents panel (/agents-info) for any subagent work: running, finished and planned subagents with model, task progress, context, cost and time, each drawn as a crab whose costume follows its model and effort. Fork of johnnyvizz/claude-kit savvy-progress 1.2.0.

A route for /goal and any multi-step work, built from Claude's own task plan: the plan drawn as a line of nodes and legs above the prompt, an ETA at the goal's own pace, a pane that opens by itself with the whole task trail, and every chat's goal in /waypoints. Follows Agent-Pulse's palette and animation. Claude is asked to plan by the mod itself. Fork of Nate Herk's goal-meter 1.0.0.

A pane that shows what Claude has done for you: tasks finished, an estimate of the hours that saved you, and what that time is worth. Tabs for Today, Week, Month and Year. /report opens it.

Keeps secrets that tools print (keys, tokens, passwords, private keys) out of what the model reads and the next request sends

侧边面板查看 A股/港股/美股指数与自选股行情

Pane that shows each code change Claude makes as a diff with a beginner-friendly explanation of why

Masks secrets (API keys, tokens, passwords, .env values) in tool output and prompts before Claude reads them

Nexika mizan: keeps your Claude Code session in balance. A band above the prompt shows the branch and who started it, open PRs or MRs per person, the branch's CI (passed, failed with the job, running), RAM and disk with warnings, the context level (fresh, mid, full), the running agent and its task, the current task step and the session cost; /mizan opens the details. At full context it saves a...

/board opens a live pane of this repo's PRs, today's merges, the herdr agents working on it, and what needs you, with no model call

📸 Shows you the pictures: a thumbnail the moment you paste one, and /gallery of every image you and Claude passed around this session.

Linear Watch + PR Watch: your Linear tickets and their PRs above the prompt, hourly. /tickets and /prs panes, compact and expanded modes, toasts on real changes.

Shows pasted images as framed thumbnails under the prompt; click to expand, open in a pane, or /image

A pane beside the transcript: the questions you asked (jump to where each was asked and answered) and the steps the model set itself, with completion rings