SLOPSHOPPER

activity

Live panel of what Claude is doing: running tools with real commands and timers, what is waiting for your approval, subagents, and its current todo plan.

newpaneguardcommandtimer
★ 5v0.1.1MITupdated 2026-10-05mishgoldenberg/claude-mods/plugins/activity
A shopper browsing a rack in a slop shop
Preview · a replayed session in a sandbox
claude · ~/work/app · activity
│ ┃ Activity ✕ › fix the failing auth test and add an audit log call │ ┃ ○ activity Idle: waiting for your next promp │ ┃ ⏺ Read(src/auth.ts) │ ┃ History a: incl. subagents c: clear ⎿ Read 6 lines │ ┃ ✓ Read 0s auth.ts ⏺ Update(src/auth.ts) │ ┃ ✓ Grep 0s /refresh\(/ in src ⎿ Added 2 lines, removed 1 line │ ┃ ✓ Edit 0s auth.ts ⏺ Bash(bun test) │ ┃ ✓ Write 0s audit.ts ⎿ 3 pass, 1 fail │ ┃ ✓ Write 0s cache.ts │ ┃ ✗ Bash 0s $ bun test ● Done. refresh now rejects expired claims and logs an audit event. │ ┃ ✓ Bash 0s $ git status --porcelain │ ┃ ✓ Bash 0s $ rm -rf build && git push ✻ Worked for 42s · done 4:20 PM │ ┃ ✓ Bash 0s $ cat .env │ › /activity │ ⎿ activity: Activity panel opened. │ │ ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── › ? for shortcuts

Draws

Pane · Activity
○ activity Idle: waiting for your next prompt History a: incl. subagents c: clear ✓ Read 0s auth.ts ✓ Grep 0s /refresh\(/ in src ✓ Edit 0s auth.ts ✓ Write 0s audit.ts ✓ Write 0s cache.ts ✗ Bash 0s $ bun test ✓ Bash 0s $ git status --porcelain ✓ Bash 0s $ rm -rf build && git push --force origin m ✓ Bash 0s $ cat .env
README

🧩 claude-mods

Panels, guardrails and quality-of-life mods for Claude Code: see what fills your context, how fast you burn your plan, and what the agent is running right now, and block the commands you never want run.

CI Claude Code TypeScript Mods License: MIT

<img src="docs/demo-guardrails.gif" alt="guardrails blocking an agent's oc delete all --all before it runs" width="900">

<sub>If a mod saves you from one bad approve, a ⭐ on this repo helps other people find it.</sub>


What is this?

Claude Code is a black box while it works. You can't see the context window filling up until it compacts away the decision you made an hour ago. You find out you've burned your 5-hour limit when it stops answering. You approve a command, tab away, and come back ten minutes later to find it has been waiting on a second approval the whole time. And most people discover /rewind only after the edit they wanted to undo.

claude-mods is a set of small plugins that open that box. Each mod is a standalone Claude Code plugin built on function hooks, the in-process plugin API: it sees every prompt, tool call and turn as it happens, and it can draw panels, toasts and status lines inside Claude Code itself. Install all eleven or only the ones you want.

They are deliberately boring about tokens. Nine of the eleven never call a model. The two that do (prompt-coach's review and context-keeper's handoff note) say so and are easy to turn off.


✨ Features

🧩 mod-managerOne panel (/mods) to install, turn on or off, update, or remove each mod, with presets (Safety only, Essentials, Zero tokens, Everything). Shows when a mod has a newer version. Install this first and pick the rest
🚦 quickbarOne line above the prompt: live context % and a button for every claude-mods panel you have installed. Start here
🧠 context-keeperWhat fills your context window, tips to trim it, and checkpoints: a handoff note (goal, decisions, files, TODOs) saved to .claude/checkpoints/ so /clear and /compact stop losing the thread. Archives the raw transcript before every compaction, for zero tokens
📈 usage-meter5-hour and 7-day plan-limit bars with reset countdown, burn rate and "full in ~2.3h", session cost, cache hit ratio (and why it's low), tokens-per-turn sparkline (drawn as charts in the desktop app)
🔔 notifyNotification inbox plus native OS notifications (Windows, macOS, Linux) when a long turn ends, a subagent or background task finishes, Claude asks you something, or an approval has been waiting 15s
👀 activityWhat Claude is doing this second: thinking, running $ npm test for 0m42s, waiting for YOUR approval, which subagents run, and its todo plan with progress
🛡️ guardrailsClickable safety rules with presets (Safe defaults, Locked to project, Read-only review): block rm -rf, mass kubectl/oc deletes, terraform destroy, force-push, destructive git, .env and key files, sudo, installs, network; keep Claude inside the project; add your own patterns. Checks scripts the agent wrote before they run, and keeps a weekly log of what it blocked
✍️ prompt-coachBefore a vague prompt is sent, a small fast model suggests a sharper one. You pick Send improved / Send mine / Edit. Never rewrites silently, never touches "yes" or "continue"
🧰 toolboxEvery tool Claude can use (built-in and MCP, grouped by server) in plain language, how often each was used, and suggestions for the project you're in
⌨️ command-hubThe built-in commands you're probably missing, each with when to use it; a searchable list of everything installed; a form to create your own slash command; tips when your prompt matches one ("undo that" → /rewind)
📝 changesEvery file Claude created or edited this session with +/- counts from git, plus one-click why?, summarize all and self-review
🔁 loop-breakerNotices Claude going in circles (the same command failing 3×, the same code rewritten 3× in a turn), tells you, and tells Claude to stop and rethink

🎬 See it in action

activity: what Claude is running right now, and the moment it's waiting on you

<img src="docs/demo-activity.gif" alt="activity panel showing thinking, waiting for approval, then completed tool calls" width="900">

context-keeper + usage-meter: what fills the window, a checkpoint saved to disk, plan limits

<img src="docs/demo-context.gif" alt="context panel, writing a checkpoint, then the usage meter" width="900">

prompt-coach: a vague prompt, a suggested rewrite, you choose

<img src="docs/demo-coach.gif" alt="prompt coach suggesting a sharper prompt and sending it" width="900">

command-hub: the built-in commands worth knowing, explained

<img src="docs/demo-commands.gif" alt="command hub listing essential slash commands" width="900">


🏗️ How it works

              You ──prompt──▶ ┌──────────────────────────────┐
                              │        Claude Code engine     │
                              │                               │
                              │  prompt.submit   tool.call    │
                              │  turn.start      turn.complete│
                              │  session.compact ui.render    │
                              └──────┬─────────────────▲──────┘
                       events, in    │                 │  allow · deny · rewrite
                       order, live   ▼                 │  panes · toasts · status
                              ┌──────────────────────────────┐
                              │  claude-mods (one plugin each)│
                              │                               │
                              │  guardrails ── may deny ──────┤
                              │  prompt-coach ─ may ask you ──┤
                              │  activity · changes · notify  │
                              │  usage-meter · context-keeper │──▶ .claude/checkpoints/
                              │  toolbox · command-hub ...    │──▶ OS notifications
                              └──────────────────────────────┘

What a mod sees. Each mod registers hooks on engine events. A tool.call hook sits in front of every tool the agent runs (Bash, Edit, MCP tools, subagents) and sees its real arguments before anything executes. That is how activity can show the exact command and guardrails can refuse it.

What it can change. A hook either passes the event on, rewrites it, or answers it itself. Guardrails answers with a denial the model reads ("blocked by the user's guardrails, don't work around it"). Prompt-coach never rewrites on its own: it asks you first, in Claude Code's own question dialog.

What it draws. Panels are ui.render hooks returning a small element tree (Box, Text, Button, Input) that Claude Code draws natively in the terminal and the desktop app. State lives in the engine ($.state), so panels survive a hot reload and redraw only when their data changes.

What it costs. Nothing, for nine of the mods. They read numbers the engine already has ($.session.usage(), $.tool.list(), $.command.list()). The two model calls are opt-out and listed under Honest limits.


🚀 Quick Start

Prerequisites: Claude Code 2.1.286 or newer (claude update). Panels dock beside the chat in the desktop app or a terminal ≥ 144 columns wide, and open inline in narrower terminals.

1. Add the marketplace and the manager

From any terminal:

claude plugin marketplace add mishgoldenberg/claude-mods
claude plugin install mod-manager@claude-mods

(In the Claude Code CLI you can also use /plugin marketplace add mishgoldenberg/claude-mods and the /plugin menu.)

2. Pick your mods

Restart Claude Code. The first session says hello once ("claude-mods ready: /mods to pick your set"). Type /mods: the manager lists every mod with what it does, whether it uses tokens, and whether an update is available. Install, turn on or off, update, or remove each one with a click, or apply a preset:

PresetWhat you get
Safety onlyguardrails, notify
Essentialsguardrails, activity, notify, context-keeper, usage-meter
Zero tokensevery mod that never calls a model
Everythingall eleven

Presets turn off what they don't list and never remove anything. Changes apply in your next session.

3. Use the quickbar

With quickbar installed, a one-line bar sits above the prompt: live context % and a button for every installed panel. /quickbar (or its ×) hides it; /quickbar again brings it back.

Or just ask Claude: "Install the claude-mods plugins from github.com/mishgoldenberg/claude-mods. Follow its INSTALL-FOR-CLAUDE.md."

VS Code

The VS Code extension has no /plugin menu, so install from a terminal with the two commands in step 1, then use /mods inside VS Code. Mods need the extension to run Claude Code 2.1.286 or newer.

for m in quickbar context-keeper usage-meter notify activity guardrails          prompt-coach toolbox command-hub changes loop-breaker; do
  claude plugin install "$m@claude-mods"
done

Try one without installing

git clone https://github.com/mishgoldenberg/claude-mods.git
claude --plugin-dir claude-mods/plugins/activity --plugin-dir claude-mods/plugins/guardrails

💬 Commands

CommandModWhat it does
/modsmod-managerInstall, turn on or off, update, or remove mods; apply a preset
/quickbarquickbarShow or hide the launcher above the prompt
/ctxcontext-keeperOpen the context panel
/checkpointcontext-keeperSave a handoff note of this session now
/resume-checkpointcontext-keeperLoad the latest checkpoint into the prompt box (use after /clear)
/meterusage-meterOpen plan limits, burn rate and cost
/notificationsnotifyOpen the notification inbox
`/mute [on\off]`notifyMute or unmute notifications
/activityactivityOpen the live activity panel
/guardguardrailsOpen the rules panel
`/guard-preset <safe\locked\review\off>`guardrailsApply a preset
/guard-log [json]guardrailsWhat guardrails blocked in the last 7 days
`/coach [on\off]`prompt-coachTurn the prompt coach on or off
/toolstoolboxOpen the tools panel and project suggestions
/cmdscommand-hubOpen the command hub
/new-commandcommand-hubCreate your own slash command
/changeschangesOpen the changed-files panel

⚙️ Configuration Reference

Options appear in /config once a mod is installed, or go in ~/.claude/settings.json under pluginConfigs.<mod>.

context-keeper

OptionDefaultDescription
warnAt70Toast a tip when context passes this %
checkpointAt85Write a handoff note automatically at this % (0 = off)

usage-meter

OptionDefaultDescription
warnAt80Toast when a plan window passes this % (a second toast always fires at 95%)

notify

OptionDefaultDescription
minSeconds30Only notify for turns at least this long
osNotifytrueAlso raise a native OS notification
approvalWaitSeconds15Ping when an approval has waited this long (-1 = off)

activity · prompt-coach · loop-breaker

ModOptionDefaultDescription
activityautoOpenfalseDock the panel on session start when there is room
prompt-coachenabledtrueReview prompts before sending
prompt-coachmodelclaude-haiku-4-5Reviewer model; small keeps the delay near a second
prompt-coachminChars8Never review prompts shorter than this
loop-breakerfailLimit3Same failing command this many times in a row
loop-breakereditLimit3Times the same code is rewritten in one turn (separate edits to different parts of a file never count)

guardrails rules

RuleBlocksIn preset
no-rm-rfrm -rf, rm -fr, Remove-Item -Recurse -Force, rmdir /sSafe · Locked
no-mass-deletekubectl/oc delete --all or -A, delete namespace/project, helm uninstall, terraform destroySafe · Locked · Review
no-force-pushgit push --force / -f (--force-with-lease allowed)Safe · Locked
no-history-rewritegit reset --hard, git clean -f, git checkout -- ., branch -D, stash drop, fetch/pull --prune, remote pruneSafe · Locked
protect-secretsreading or writing .env*, *.pem, *.key, id_rsa, credentials filesSafe · Locked · Review
no-sudosudo, su -, runasSafe · Locked · Review
no-installsnpm i, pip install, cargo add, brew/apt/winget install …Review
no-networkWebFetch, WebSearch, curl, wget, Invoke-WebRequest—
jail-writesWrite/Edit outside the project folder—
jail-allany file tool outside the project, cd out of itLocked
read-onlyall edits; shell limited to look-only commandsReview

Guardrails turns on Safe defaults the first time it loads. /guard-preset off turns everything off.

Whatever the preset, while any rule is on:

  • Scripts are checked before they run. A file the agent creates with Write in this session (and edits after that) is remembered, and when a shell command runs it (bash cleanup.sh, python tools/x.py, ./run, node a.mjs), its code is checked against your enabled rules and patterns first. os.system("rm -rf …") inside a Python file counts.
  • The agent can't edit guardrails' own settings. Write/Edit on them, and the obvious shell writes (sed -i, >, tee, cp, mv, rm), are denied with the same "ask the user" message.
  • Blocks are logged. Every block is kept for 30 days on this machine. The panel shows the last 7 days by rule, /guard-log prints a summary (/guard-log json for the raw list), and clear wipes it. Commands are cut to 200 characters.

🔒 Is it safe to install?

Mods run inside Claude Code with your permissions and no sandbox, so this is the right question to ask about any mod, including these. What these ones do:

  • No network. No mod makes a web request, and there is no telemetry. Nothing leaves your machine except the two opt-in model calls below, which go through your own Claude Code session like any prompt.
  • Processes they start, all of them: git diff --numstat (changes), the claude plugin CLI when you open /mods or click in it (mod-manager; only Install, Update and Check for updates go online, through Claude Code's own plugin installer), your OS notification tool (notify), and gh --version to see whether the GitHub CLI exists (toolbox).
  • Files they write: checkpoints and pre-compaction archives under .claude/checkpoints/ (context-keeper), and a new slash command file when you use the form (command-hub). Settings, and guardrails' 30-day block log, live in Claude Code's own plugin store under ~/.claude. Nothing else.
  • Model calls: prompt-coach and context-keeper's handoff note, both listed below and both easy to turn off.

Every mod is a few hundred lines of TypeScript in plugins/<mod>/hooks/register.tsx. Read the ones you install.


⚠️ Honest limits

  • Guardrails is a seatbelt, not a sandbox. Rules are pattern checks on the commands and paths the agent passes to tools. Scripts the agent wrote this session are checked before they run, but a script that arrives another way (downloaded, generated by a shell command, already in the repo) or an obfuscated command gets through, and so can a shell trick that rewrites guardrails' settings. Quoted prose (commit messages, text written to files) is ignored so that mentioning rm -rf doesn't block you, except when the text is handed to a shell (bash -c, | sh, powershell -Command), which is checked. For hard guarantees use Claude Code's permission rules and sandboxing; use guardrails to catch the honest mistakes.
  • prompt-coach costs a little. A reviewed prompt waits about a second for a small model, and uses a few hundred tokens. When you send the improved version, the chat still shows what you typed; a dim "prompt-coach sent the improved version" line below it shows what was actually sent. Short replies are never reviewed. /coach off turns it off.
  • context-keeper's handoff note costs a little. It asks the model for a summary over the already-cached conversation, so it is mostly cache reads. The pre-compaction archive costs nothing.
  • Function hooks are early access. A Claude Code update can break a mod. CI validates every mod against the engine's own validator, and issues are welcome.

🗂️ Project Structure

claude-mods/
├── .claude-plugin/
│   └── marketplace.json        The marketplace: one entry per mod
├── plugins/
│   ├── activity/
│   │   ├── .claude-plugin/
│   │   │   └── plugin.json     Name, description, userConfig options
│   │   ├── hooks/
│   │   │   ├── hooks.json      Points at the hooks module
│   │   │   └── register.tsx    The mod: hooks, commands, panel
│   │   ├── tests/
│   │   │   └── surfaces.test.tsx   The panel draws on every surface (claude plugin test)
│   │   └── types/
│   │       └── index.d.ts      Its $.state contract
│   ├── guardrails/             …same shape for every mod
│   └── …
├── docs/
│   └── design.md               The shared design spec and kit every mod copies
├── tests/
│   ├── guardrails-rules.test.mjs   Every rule against real commands
│   └── design-kit.test.mjs     Every mod's kit matches docs/design.md
├── INSTALL-FOR-CLAUDE.md       Steps Claude follows when asked to install
└── tsconfig.json               Type-checks all mods against the engine API

🔧 Extending it

Add a guardrail rule. Append an entry to RULES in plugins/guardrails/hooks/register.tsx (an id, a title, and a test that returns the offending text) and add cases to tests/guardrails-rules.test.mjs. The panel and presets pick it up automatically.

Add an essential command. One line in ESSENTIALS in plugins/command-hub/hooks/register.tsx. It only shows when that command exists in the user's Claude Code.

Write a new mod. Copy plugins/changes (a small mod with a panel) or plugins/loop-breaker (no UI), rename it everywhere, and add it to marketplace.json. Or ask Claude Code to "make a mod that …": it has a built-in skill for exactly this, with hot reload.


🤝 Contributing

Issues and pull requests are welcome. Start with CONTRIBUTING.md, which has the mod checklist.

npm install
npm run typecheck
npm test
claude plugin validate plugins/<mod>
claude plugin test plugins/<mod>

Every mod follows one design spec, docs/design.md: theme colors only (Claude orange as the single accent), the same pane header, glyphs, hotkeys and empty states, so the set feels like one product in any theme.

Two house rules worth knowing before you write anything, because the validator enforces both:

  • Helpers that take $ must be top-level function declarations. A closure inside register that receives $ is rejected.
  • Every $.state key is declared in the mod's types/index.d.ts, under the mod's name.

Found a way around guardrails, or another security problem? Please report it privately; see SECURITY.md.


📄 License

MIT © 2026 Michael Goldenberg

Source 2 files
hooks/register.tsx 296 lines
1import { atom, read, update } from 'claude-code'
2import type { ElementTable, EngineInterface, Register, RenderChildren } from 'claude-code'
3
4import type { ActivityCall, CallStatus, Phase, Todo } from '../types'
5
6// ── claude-mods kit v1 (docs/design.md): identical in every mod ──
7const TONE = { accent: 'claude', ok: 'success', warn: 'warning', bad: 'error', dim: 'inactive' } as const
8const GLYPH = { on: '●', off: '○', warn: '▲', ok: '✓', fail: '✗' } as const
9type Kit = Pick<ElementTable, 'Box' | 'Text'>
10
11/** Pane header: state glyph, mod name, one-line live status. */
12function header({ Box, Text }: Kit, glyph: string, tone: string, name: string, status: string) {
13  return (
14    <Box gap={1}>
15      <Text color={tone}>{glyph}</Text>
16      <Text bold>{name}</Text>
17      <Text dimColor wrap="truncate-end">{status}</Text>
18    </Box>
19  )
20}
21
22/** A section: a dim label (with optional small controls beside it), then its rows. */
23function section({ Box, Text }: Kit, label: string, rows: RenderChildren, aside?: RenderChildren) {
24  return (
25    <Box flexDirection="column">
26      <Box gap={1}>
27        <Text dimColor>{label}</Text>
28        {aside}
29      </Box>
30      {rows}
31    </Box>
32  )
33}
34
35/** A number right-aligned in a fixed-width cell. */
36function num({ Box, Text }: Kit, value: string, width: number, color?: string) {
37  return (
38    <Box width={width} flexShrink={0} justifyContent="flex-end">
39      <Text color={color}>{value}</Text>
40    </Box>
41  )
42}
43
44/** Empty state: what will show up here, and how to get it. */
45function empty({ Text }: Kit, text: string) {
46  return <Text dimColor>{text}</Text>
47}
48// ── end kit ──
49
50const PANE = 'activity'
51const calls = atom({ plugin: 'activity', key: 'calls' } as const, [])
52const phase = atom({ plugin: 'activity', key: 'phase' } as const, { kind: 'idle', since: 0, prompt: '' } as Phase)
53const todos = atom({ plugin: 'activity', key: 'todos' } as const, [])
54const showAll = atom({ plugin: 'activity', key: 'showAll' } as const, false)
55
56const STATUS: Record<CallStatus, { icon: string; color: string; label: string }> = {
57  running: { icon: GLYPH.on, color: TONE.accent, label: 'running' },
58  approval: { icon: GLYPH.warn, color: TONE.warn, label: 'waiting for YOUR approval' },
59  done: { icon: GLYPH.ok, color: TONE.ok, label: 'done' },
60  failed: { icon: GLYPH.fail, color: TONE.bad, label: 'failed' },
61  denied: { icon: GLYPH.fail, color: TONE.bad, label: 'denied' },
62}
63
64const TODO_ICON: Record<string, string> = { completed: GLYPH.ok, in_progress: GLYPH.on, pending: GLYPH.off }
65
66const str = (v: unknown) => (typeof v === 'string' ? v : '')
67const base = (p: string) => p.split(/[\\/]/).at(-1) ?? p
68const clip = (s: string, n: number) => (s.length > n ? `${s.slice(0, n - 1)}…` : s)
69
70/** One human line per tool call: what it is actually doing. */
71function describe(tool: string, input: Record<string, unknown>): string {
72  switch (tool) {
73    case 'Bash':
74    case 'PowerShell':
75      return `$ ${str(input.command).replace(/\s+/g, ' ')}`
76    case 'Read':
77    case 'Write':
78    case 'Edit':
79    case 'NotebookEdit':
80      return base(str(input.file_path) || str(input.notebook_path))
81    case 'Grep':
82      return `/${str(input.pattern)}/${input.path ? ` in ${base(str(input.path))}` : ''}`
83    case 'Glob':
84      return str(input.pattern)
85    case 'WebFetch':
86      return str(input.url)
87    case 'WebSearch':
88      return `"${str(input.query)}"`
89    case 'Agent':
90    case 'Task':
91      return `${str(input.subagent_type) || 'agent'}: ${str(input.description)}`
92    case 'TodoWrite':
93      return `${Array.isArray(input.todos) ? input.todos.length : 0} todos`
94    default: {
95      const first = Object.values(input).find(v => typeof v === 'string')
96
97      return typeof first === 'string' ? first : ''
98    }
99  }
100}
101
102const secs = (ms: number) => {
103  const s = Math.max(0, Math.round(ms / 1000))
104
105  return s >= 60 ? `${Math.floor(s / 60)}m${String(s % 60).padStart(2, '0')}s` : `${s}s`
106}
107
108async function setStatus($: EngineInterface, id: string, status: CallStatus, endedAt?: number) {
109  await update($, calls, list => list.map(c => (c.id === id ? { ...c, status, endedAt: endedAt ?? c.endedAt } : c)))
110}
111
112let ticker: { cancel: () => void } | null = null
113
114/** Redraws once a second while something runs, so the timers count up. */
115function startTicking($: EngineInterface) {
116  ticker ??= $.clock.every(1000, () => $.ui.invalidate('ui.render'))
117}
118
119function stopTicking() {
120  ticker?.cancel()
121  ticker = null
122}
123
124export const register: Register = (on, options) => {
125
126  on('session.start', async ($, e, next) => {
127    await $.command.register({ name: 'activity', description: 'Live view: what Claude is running and waiting for right now' })
128    if (options.autoOpen === true) void $.ui.open({ id: PANE, title: 'Activity' })
129
130    return next(e)
131  })
132
133  on('command.run', { command: 'activity' }, async $ => {
134    await $.ui.open({ id: PANE, title: 'Activity' })
135
136    return { text: 'Activity panel opened.' }
137  })
138
139  on('turn.start', async ($, e, next) => {
140    const since = await $.clock.now()
141    await update($, phase, (): Phase => ({ kind: 'thinking', since, prompt: e.text }))
142    startTicking($)
143
144    return next(e)
145  })
146
147  on('turn.complete', async ($, e, next) => {
148    const result = await next(e)
149    if (e.agentId === undefined) {
150      const since = await $.clock.now()
151      await update($, phase, (p): Phase => ({ ...p, kind: 'idle', since }))
152      stopTicking()
153    }
154
155    return result
156  })
157
158  on('tool.call', async ($, e, next) => {
159    const { tool, tool_use_id, agentId, ...input } = e as unknown as { tool: string; tool_use_id: string; agentId?: string } & Record<string, unknown>
160    const call: ActivityCall = {
161      id: tool_use_id,
162      tool,
163      summary: describe(tool, input),
164      agentId,
165      isBackground: input.run_in_background === true,
166      startedAt: await $.clock.now(),
167      status: 'running',
168    }
169    if (tool === 'TodoWrite' && Array.isArray(input.todos)) {
170      await update($, todos, () => (input.todos as Todo[]).map(t => ({ content: t.content, status: t.status, activeForm: t.activeForm })))
171    }
172    await update($, calls, list => [...list, call].slice(-300))
173    if (agentId === undefined) await update($, phase, (p): Phase => ({ ...p, kind: 'tools' }))
174    startTicking($)
175
176    try {
177      const check = await $.tool.check({ tool, input })
178      if (check.decision === 'ask') await setStatus($, tool_use_id, 'approval')
179    } catch {
180      // no verdict available
181    }
182
183    let status: CallStatus = 'failed'
184    try {
185      const ran = await next(e)
186      status = ran.deny !== undefined ? 'denied' : ran.isError === true ? 'failed' : 'done'
187
188      return ran
189    } finally {
190      await setStatus($, tool_use_id, status, await $.clock.now())
191      const stillRunning = (await read($, calls)).some(c => c.agentId === undefined && (c.status === 'running' || c.status === 'approval'))
192      if (agentId === undefined && !stillRunning) await update($, phase, (p): Phase => (p.kind === 'tools' ? { ...p, kind: 'thinking' } : p))
193    }
194  })
195
196  on('ui.render', { component: 'Pane', requestId: PANE }, async ($, e) => {
197    const { Box, Text, Button } = $.ui.resolve(e)
198    const list = await read($, calls)
199    const now = await $.clock.now()
200    const p = await read($, phase)
201    const plan = await read($, todos)
202    const all = await read($, showAll)
203    const cols = e.props.bodyColumns ?? 40
204    const rows = e.viewport?.rows ?? 30
205
206    const live = list.filter(c => c.status === 'running' || c.status === 'approval')
207    const waitingOnYou = live.filter(c => c.status === 'approval')
208    const agents = await $.agent.list().catch(() => [])
209    const runningAgents = agents.filter(a => a.status === 'running')
210    const recent = list.filter(c => !live.includes(c) && (all || c.agentId === undefined)).slice(-Math.max(3, rows - 18 - live.length - plan.length))
211
212    const kit = { Box, Text }
213    const headline =
214      waitingOnYou.length > 0
215        ? { glyph: GLYPH.warn, tone: TONE.warn, text: `Waiting for you: approve ${waitingOnYou.map(c => c.tool).join(', ')}` }
216        : p.kind === 'idle'
217          ? { glyph: GLYPH.off, tone: TONE.dim, text: 'Idle: waiting for your next prompt' }
218          : p.kind === 'tools'
219            ? { glyph: GLYPH.on, tone: TONE.accent, text: `Running ${live.length} tool${live.length === 1 ? '' : 's'} · turn ${secs(now - p.since)}` }
220            : { glyph: GLYPH.on, tone: TONE.accent, text: `Thinking / writing · turn ${secs(now - p.since)}` }
221
222    return (
223      <Box flexDirection="column" gap={1}>
224        <Box flexDirection="column">
225          {header(kit, headline.glyph, headline.tone, 'activity', headline.text)}
226          {p.kind !== 'idle' && p.prompt !== '' && <Text dimColor wrap="truncate-end">for: {clip(p.prompt.replace(/\s+/g, ' '), cols - 6)}</Text>}
227        </Box>
228
229        {live.length > 0 &&
230          section(
231            kit,
232            'Now',
233            live.map(c => (
234              <Box gap={1}>
235                <Text color={STATUS[c.status].color}>{STATUS[c.status].icon}</Text>
236                <Text>{c.tool}</Text>
237                {num(kit, secs(now - c.startedAt), 6, STATUS[c.status].color)}
238                <Text dimColor wrap="truncate-end">
239                  {c.agentId ? '[subagent] ' : ''}
240                  {c.isBackground ? '[background] ' : ''}
241                  {c.summary}
242                </Text>
243              </Box>
244            )),
245          )}
246
247        {runningAgents.length > 0 &&
248          section(
249            kit,
250            'Subagents',
251            runningAgents.map(a => (
252              <Text wrap="truncate-end">
253                <Text color={TONE.accent}>{GLYPH.on}</Text> {a.type} <Text dimColor>{a.description}</Text>
254              </Text>
255            )),
256          )}
257
258        {plan.length > 0 &&
259          section(
260            kit,
261            `Plan ${plan.filter(t => t.status === 'completed').length}/${plan.length}`,
262            plan.map(t => (
263              <Text dimColor={t.status === 'completed'} bold={t.status === 'in_progress'} wrap="truncate-end">
264                <Text color={t.status === 'completed' ? TONE.ok : t.status === 'in_progress' ? TONE.accent : undefined}>{TODO_ICON[t.status] ?? GLYPH.off}</Text> {t.status === 'in_progress' ? (t.activeForm ?? t.content) : t.content}
265              </Text>
266            )),
267          )}
268
269        {section(
270          kit,
271          'History',
272          <Box flexDirection="column">
273            {recent.length === 0 && empty(kit, 'No tool calls yet. Every tool Claude runs shows up here with its command and how long it took.')}
274            {recent.map(c => (
275              <Box gap={1}>
276                <Text color={STATUS[c.status].color}>{STATUS[c.status].icon}</Text>
277                <Box width={7} flexShrink={0}>
278                  <Text wrap="truncate-end">{c.tool}</Text>
279                </Box>
280                {num(kit, secs((c.endedAt ?? now) - c.startedAt), 6)}
281                <Text dimColor wrap="truncate-end">
282                  {c.summary}
283                </Text>
284              </Box>
285            ))}
286          </Box>,
287          <Box gap={1}>
288            <Button key="all" plain hotkey="a" label={all ? 'main only' : 'incl. subagents'} onPress={() => void update($, showAll, v => !v)} />
289            <Button key="clear" plain hotkey="c" label="clear" onPress={() => void update($, calls, l => l.filter(c => c.status === 'running' || c.status === 'approval'))} />
290          </Box>,
291        )}
292      </Box>
293    )
294  })
295}
296
types/index.d.ts 28 lines
1export type CallStatus = 'running' | 'approval' | 'done' | 'failed' | 'denied'
2
3export type ActivityCall = {
4  id: string
5  tool: string
6  summary: string
7  agentId?: string
8  isBackground: boolean
9  startedAt: number
10  endedAt?: number
11  status: CallStatus
12}
13
14export type Phase = { kind: 'idle' | 'thinking' | 'tools'; since: number; prompt: string }
15
16export type Todo = { content: string; status: string; activeForm?: string }
17
18declare module 'claude-code' {
19  interface PluginState {
20    activity: {
21      calls: ActivityCall[]
22      phase: Phase
23      todos: Todo[]
24      showAll: boolean
25    }
26  }
27}
28