Guards

Mission control for subagents and agent teams: who is running, what each is doing, who spawned whom, who is talking to whom, and how they overlap

Click a .md path in the Claude Code conversation to read it rendered as markdown beside the session, pictures included, and point at any block to have Claude edit it.

Replay Theater: step through the file edits Claude made in the last turn, one diff at a time.

把想清楚的开发任务派给本机 ZCode（GLM）执行，隔离在 worktree 里跑，红线加模型审批把关，用 git diff 和测试验收

DOPA MODE (DOPA is short for dopamine) for Claude Code: fireworks for everything you do and every milestone Claude reaches (finished turns, commits, pushes, pull requests, passing tests), context and plan-limit meters with warnings, trophies, a daily command card and a focus timer.

A desk for the Claude Code prompt: context weather, Gmail, calendar, tasks across sessions, notes, a music deck and a billable-hours timer

Audible alerts for Claude Code: Claude sounds normal/yellow/red alerts on your server's speakers, with an LCARS status band and alert animations.

Claude Code mod: context/token band, escalation signals and per-turn effort log.

A plush Clawd above the prompt that reacts to what Claude is doing: works, celebrates, wobbles, blushes, naps, and can be patted and dragged.

Adds Exa's results to WebSearch, and saves each WebFetch page to disk with the lines that answer the prompt

Every Claude Code session as a pixel character in a shared office you can click and talk to

Flightdeck: a live agent dashboard for Claude Code. Main model vitals, an on-call architect, every permission check, subagent cards and swimlanes, a turn receipt and a session log, all from real session events

Bullswarm as a Claude Mod: live subscription meters for every installed coding-agent CLI above the prompt, quota-aware routing of Claude's own subagents to whichever pool has surplus, a verdict note on every bullswarm command the model runs, a /bullswarm command, and $.bullswarm for other plugins.

Time left on the working turn, on the spinner line: from the task list's pace, else from how long your turns run. No model calls, no tokens. /eta turns it on or off.

Keeps a per-turn tally of edits, runs, curls and destructive commands and shows it on the turn footer; any non-read-only Bash counts as a run, a claim (English or Japanese) with no run flags the spinner, a destructive Bash unfolds its tool group, and an edit-without-run turn suggests running the tests.

ASD-STE100 (Simplified Technical English) and 80% Karpathy Mode plugin, mod, and skill for Claude Code. Enforces clean, unambiguous technical explanations.

A Winamp-style player for Claude Code: live spectrum visualizer, scrolling marquee, playlist of tool calls and transport controls.

Play snake while Claude works. Every tool call Claude makes drops food into the game; the game pauses when Claude is done.

A Claude Code mod for Eunuch Mode: while the skill is on, the palace adviser stands above the prompt in pixel art, posing for what the agent is doing; the spinner narrates each action in court language; and the status line reads "Court in session". Canned lines by default; opt-in generative mode (fresh lines from Sonnet) and treachery mode (he plots your downfall, cosmetically). /court toggles...

A card above the prompt that says what Claude is working on, refreshed every few minutes while a turn runs

Clawd as a desktop pet for Claude Code: floats above your windows, shows Running / Needs input / Ready / Blocked, click to jump back into the session, quick chat and stop from the pet.

Monitor tool with persistent (no deadline) watches

When your plan usage gets low, tells every running agent to wrap up before the limit cuts it off.

Segmented, scoped memory for agents: one file, SQLite, no daemon. Wake at session start, recall on every prompt, staleness nag at stop.