SLOPSHOPPER

toolbox

Every tool Claude can use (built-in and MCP) in plain language, how often each was used, and suggestions tailored to the project you are in.

newpaneguardcommandtoastprocess
★ 5v0.1.1MITupdated 2026-10-05mishgoldenberg/claude-mods/plugins/toolbox
A shopper browsing a rack in a slop shop
Preview · a replayed session in a sandbox
claude · ~/work/app · toolbox
│ ┃ Tools ✕ › fix the failing auth test and add an audit log call │ ┃ ● toolbox reading tools… │ ┃ ⏺ Read(src/auth.ts) │ ┃ For this project ⎿ Read 6 lines │ ┃ Looking at this project… suggestions appear ⏺ Update(src/auth.ts) │ ┃ here in a moment. ⎿ Added 2 lines, removed 1 line │ ┃ ⏺ Bash(bun test) │ ┃ Tools 1: [all] 2: used 3: mcp ⎿ 3 pass, 1 fail │ ┃ Reading the tool list… │ ┃ ● Done. refresh now rejects expired claims and logs an audit event. │ ┃ [ Rescan ] │ ✻ Worked for 42s · done 4:20 PM │ │ › /tools │ ⎿ toolbox: Tools panel opened. │ │ ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── › ? for shortcuts

Draws

Pane · Tools
● toolbox reading tools… For this project Looking at this project… suggestions appear here in a moment. Tools 1: [all] 2: used 3: mcp Reading the tool list… [ Rescan ]
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 284 lines
1import { atom, read, update } from 'claude-code'
2import type { ElementTable, EngineInterface, Register, RenderChildren } from 'claude-code'
3
4import type { Suggestion, ToolRow } 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 = 'toolbox'
51const tools = atom({ plugin: 'toolbox', key: 'tools' } as const, [])
52const counts = atom({ plugin: 'toolbox', key: 'counts' } as const, {} as Record<string, number>)
53const suggestions = atom({ plugin: 'toolbox', key: 'suggestions' } as const, [])
54const stack = atom({ plugin: 'toolbox', key: 'stack' } as const, [])
55const filter = atom({ plugin: 'toolbox', key: 'filter' } as const, 'all')
56
57/** Plain-language explanations of the built-in tools, for people new to Claude Code. */
58const EXPLAIN: Record<string, string> = {
59  Bash: 'Runs shell commands (builds, tests, git…)',
60  PowerShell: 'Runs PowerShell commands on Windows',
61  Read: 'Reads files, images, PDFs and notebooks',
62  Write: 'Creates or overwrites a file',
63  Edit: 'Makes exact find-and-replace edits in a file',
64  NotebookEdit: 'Edits Jupyter notebook cells',
65  Glob: 'Finds files by name pattern',
66  Grep: 'Searches file contents (ripgrep)',
67  WebFetch: 'Downloads and reads a web page',
68  WebSearch: 'Searches the web',
69  Agent: 'Starts a subagent for a side task (keeps main context clean)',
70  Task: 'Starts a subagent for a side task (keeps main context clean)',
71  TodoWrite: 'Keeps a visible todo plan for multi-step work',
72  AskUserQuestion: 'Asks you a multiple-choice question',
73  Skill: 'Loads a packaged skill (instructions for a kind of task)',
74  ToolSearch: 'Loads the schemas of deferred tools on demand',
75  EnterPlanMode: 'Switches to plan-first mode',
76  ExitPlanMode: 'Presents a plan for your approval',
77  Monitor: 'Watches a background process for a condition',
78}
79
80const firstSentence = (s: string) => {
81  const line = s.split('\n').find(l => l.trim() !== '')?.trim() ?? ''
82  const cut = line.split(/(?<=\.)\s/)[0] ?? line
83
84  return cut.length > 90 ? `${cut.slice(0, 89)}…` : cut
85}
86
87async function loadTools($: EngineInterface) {
88  const list = await $.tool.list()
89  const rows: ToolRow[] = list.map(t => {
90    const mcp = /^mcp__(.+?)__(.+)$/.exec(t.name)
91    const server = mcp?.[1] ?? ''
92
93    return {
94      name: t.name,
95      group: t.mcp || mcp ? `MCP: ${/^[0-9a-f-]{20,}$/.test(server) ? 'connector' : server}` : 'Built-in',
96      short: EXPLAIN[t.name] ?? firstSentence(t.description),
97      isMcp: t.mcp,
98    }
99  })
100  await update($, tools, () => rows)
101}
102
103async function exists($: EngineInterface, root: string, rel: string) {
104  return $.fs.exists(`${root}/${rel}`).catch(() => false)
105}
106
107/** Looks at the project folder and proposes tools, MCP servers and habits that fit it. */
108async function scan($: EngineInterface) {
109  const root = (await $.session.root()).replace(/\\/g, '/')
110  const has = (rel: string) => exists($, root, rel)
111  const found: string[] = []
112  const out: Suggestion[] = []
113  const toolNames = (await read($, tools)).map(t => t.name.toLowerCase()).join(' ')
114
115  let deps: Record<string, unknown> = {}
116  let scripts: Record<string, unknown> = {}
117  if (await has('package.json')) {
118    found.push('Node')
119    try {
120      const pkg = JSON.parse(await $.fs.read(`${root}/package.json`)) as { dependencies?: Record<string, unknown>; devDependencies?: Record<string, unknown>; scripts?: Record<string, unknown> }
121      deps = { ...pkg.dependencies, ...pkg.devDependencies }
122      scripts = pkg.scripts ?? {}
123    } catch {
124      // unreadable package.json
125    }
126  }
127  const dep = (name: string) => Object.keys(deps).some(d => d === name || d.startsWith(`${name}/`) || d.startsWith(`@${name}/`))
128
129  if (dep('react') || dep('next') || dep('vue') || dep('svelte') || dep('vite') || dep('@angular/core')) found.push('Web UI')
130  if (dep('typescript')) found.push('TypeScript')
131  if ((await has('pyproject.toml')) || (await has('requirements.txt'))) found.push('Python')
132  if (await has('Cargo.toml')) found.push('Rust')
133  if (await has('go.mod')) found.push('Go')
134  if ((await has('Dockerfile')) || (await has('docker-compose.yml')) || (await has('compose.yaml'))) found.push('Docker')
135  if (dep('prisma') || dep('drizzle-orm') || dep('pg') || dep('mongoose') || (await has('prisma/schema.prisma'))) found.push('Database')
136  if (await has('.github/workflows')) found.push('GitHub Actions')
137  const isGit = await has('.git')
138  if (isGit) found.push('git')
139
140  if (!(await has('CLAUDE.md')) && !(await has('.claude/CLAUDE.md'))) {
141    out.push({ id: 'init', title: 'Give Claude a project memory', why: 'No CLAUDE.md here. /init writes one with your build/test commands and conventions, so you stop repeating them.', action: { kind: 'command', value: 'init', label: 'Run /init' } })
142  }
143  if (found.includes('Web UI') && !/browser|playwright|puppeteer|chrome/.test(toolNames)) {
144    out.push({ id: 'browser', title: 'Let Claude see your UI', why: 'Web frontend detected but no browser tool. A browser/Playwright MCP lets Claude click through the app and check its own changes.', action: { kind: 'fill', value: 'Help me set up a browser automation MCP server (e.g. Playwright) for this project so you can check UI changes yourself.', label: 'Ask Claude to set it up' } })
145  }
146  if (found.includes('Database') && !/postgres|sql|supabase|mongo|prisma|neon/.test(toolNames)) {
147    out.push({ id: 'db', title: 'Database access for Claude', why: 'An ORM/DB driver is in this project. A read-only database MCP lets Claude check the real schema and data instead of guessing.', action: { kind: 'fill', value: 'Which database MCP server fits this project? Set up a read-only connection for local development.', label: 'Ask Claude' } })
148  }
149  if (isGit) {
150    const gh = await $.process.run(['gh', '--version']).catch(() => undefined)
151    if (gh === undefined || gh.exitCode !== 0) {
152      out.push({ id: 'gh', title: 'Install the GitHub CLI', why: 'With `gh` Claude can open PRs, read issues and check CI from the terminal.' })
153    }
154  }
155  const testScript = Object.keys(scripts).find(s => /^test/.test(s))
156  if (testScript !== undefined || (await has('pytest.ini')) || (await has('Cargo.toml')) || (await has('go.mod'))) {
157    out.push({ id: 'verify', title: 'Make Claude verify its work', why: 'Tests exist. Telling Claude how to verify (in CLAUDE.md) catches mistakes before you see them.', action: { kind: 'fill', value: `Add a "How to verify changes" section to CLAUDE.md with the exact test${testScript ? ` (npm run ${testScript})` : ''}, lint and type-check commands for this project.`, label: 'Add to CLAUDE.md' } })
158  }
159  if (!(await has('.claude/settings.json'))) {
160    out.push({ id: 'perms', title: 'Fewer permission prompts', why: 'No project settings yet. Allow-listing safe read-only commands (git status, tests) saves a lot of clicking.', action: { kind: 'command', value: 'fewer-permission-prompts', label: 'Scan & suggest' } })
161  }
162  out.push({ id: 'ask', title: 'Ask Claude for a tailored tool review', why: 'Claude reads this project and the tool list above and tells you what is missing or unused.', action: { kind: 'submit', value: 'Look at this project (stack, scripts, CI) and at the tools, MCP servers and skills you currently have. Suggest the 3 most useful additions for this project and anything I have that is unused noise. Be concrete, no setup yet.', label: 'Ask now' } })
163
164  await update($, stack, () => found)
165  await update($, suggestions, () => out)
166}
167
168async function act($: EngineInterface, s: Suggestion) {
169  const action = s.action
170  if (action === undefined) return
171  if (action.kind === 'command') {
172    const available = (await $.command.list()).some(c => c.name === action.value)
173    if (!available) {
174      $.ui.toast(`/${action.value} is not available in this session.`)
175      return
176    }
177    await $.command.run({ command: action.value })
178  } else if (action.kind === 'fill') {
179    await $.prompt.fill({ text: action.value })
180  } else {
181    await $.prompt.submit({ text: action.value })
182  }
183}
184
185export const register: Register = on => {
186  on('session.start', async ($, e, next) => {
187    await $.command.register({ name: 'tools', description: 'See every tool Claude can use, how often it used them, and suggestions for this project' })
188    void loadTools($)
189
190    return next(e)
191  })
192
193  on('command.run', { command: 'tools' }, async $ => {
194    await loadTools($)
195    void scan($)
196    await $.ui.open({ id: PANE, title: 'Tools' })
197
198    return { text: 'Tools panel opened.' }
199  })
200
201  on('tool.call', async ($, e, next) => {
202    await update($, counts, c => ({ ...c, [e.tool]: (c[e.tool] ?? 0) + 1 }))
203
204    return next(e)
205  })
206
207  on('ui.render', { component: 'Pane', requestId: PANE }, async ($, e) => {
208    const { Box, Text, Button } = $.ui.resolve(e)
209    const rows = await read($, tools)
210    const used = await read($, counts)
211    const tips = await read($, suggestions)
212    const found = await read($, stack)
213    const view = await read($, filter)
214
215    const groups = new Map<string, ToolRow[]>()
216    for (const row of rows) {
217      if (view === 'used' && (used[row.name] ?? 0) === 0) continue
218      if (view === 'mcp' && !row.isMcp) continue
219      groups.set(row.group, [...(groups.get(row.group) ?? []), row])
220    }
221    const shortName = (n: string) => n.replace(/^mcp__.+?__/, '')
222
223    const kit = { Box, Text }
224    const usedCount = Object.keys(used).length
225    const shown = [...groups.values()].reduce((n, list) => n + list.length, 0)
226
227    return (
228      <Box flexDirection="column" gap={1}>
229        {header(kit, GLYPH.on, TONE.accent, 'toolbox', rows.length === 0 ? 'reading tools…' : `${rows.length} tools · ${usedCount} used this session`)}
230
231        {section(
232          kit,
233          `For this project${found.length > 0 ? ` (${found.join(', ')})` : ''}`,
234          <Box flexDirection="column">
235            {tips.length === 0 && empty(kit, 'Looking at this project… suggestions appear here in a moment.')}
236            {tips.map(s => (
237              <Box flexDirection="column">
238                <Box gap={1}>
239                  <Text color={TONE.accent}>{GLYPH.on}</Text>
240                  <Text wrap="truncate-end">{s.title}</Text>
241                  {s.action !== undefined && <Button key={`act-${s.id}`} plain label={s.action.label} onPress={() => void act($, s)} />}
242                </Box>
243                <Box paddingLeft={2}>
244                  <Text dimColor>{s.why}</Text>
245                </Box>
246              </Box>
247            ))}
248          </Box>,
249        )}
250
251        {section(
252          kit,
253          'Tools',
254          <Box flexDirection="column" gap={1}>
255            {shown === 0 && empty(kit, view === 'used' ? 'No tools used yet this session. Counts go up as Claude works.' : view === 'mcp' ? 'No MCP tools connected. /mcp adds servers (databases, browsers, issue trackers…).' : 'Reading the tool list…')}
256            {[...groups.entries()].map(([group, list]) =>
257              section(
258                kit,
259                `${group} (${list.length})`,
260                list.map(t => (
261                  <Box gap={1}>
262                    {(used[t.name] ?? 0) > 0 ? num(kit, `${used[t.name]}×`, 5) : num(kit, '·', 5, TONE.dim)}
263                    <Text wrap="truncate-end">
264                      {shortName(t.name)} <Text dimColor>{t.short}</Text>
265                    </Text>
266                  </Box>
267                )),
268              ),
269            )}
270          </Box>,
271          <Box gap={1}>
272            {(['all', 'used', 'mcp'] as const).map((v, i) => (
273              <Button key={`f-${v}`} plain hotkey={String(i + 1)} label={view === v ? `[${v}]` : v} onPress={() => void update($, filter, () => v)} />
274            ))}
275          </Box>,
276        )}
277        <Box>
278          <Button key="rescan" hotkey="r" variant="primary" label="Rescan" onPress={() => void loadTools($).then(() => scan($))} />
279        </Box>
280      </Box>
281    )
282  })
283}
284
types/index.d.ts 16 lines
1export type ToolRow = { name: string; group: string; short: string; isMcp: boolean }
2
3export type Suggestion = { id: string; title: string; why: string; action?: { kind: 'command' | 'fill' | 'submit'; value: string; label: string } }
4
5declare module 'claude-code' {
6  interface PluginState {
7    toolbox: {
8      tools: ToolRow[]
9      counts: Record<string, number>
10      suggestions: Suggestion[]
11      stack: string[]
12      filter: string
13    }
14  }
15}
16