ai_automation_suggester
This custom Home Assistant integration automatically scans your entities, detects new devices, and uses AI (via cloud and local APIs) to suggest tailored automations. It supports multiple AI providers
翻译准备中
个人 GitHub 账号下公开仓库的所有者可以登录并验证所有权,自行管理介绍,无需管理员批准。
登录并生成验证文件,在 30 分钟内将其提交到此仓库的默认分支。其他分支或分叉仓库中的文件无效。然后在下方检查文件,即可无需管理员批准直接管理项目。请保留文件以维持管理权限。
如需登录,将前往登录页面。登录后请回到此处,再次点击所选的验证按钮。
在项目文件夹中运行 /nomorevibe verify,即可验证所有权并自行管理介绍。
一分钟完成验证17 Claude Code plugins in one panel. See every move Claude makes: agents, files, plans, tests and risky commands, live.
翻译准备中
取自仓库 README
正在加载完整 README。 以下为已保存的摘录。
17 mods for Claude Code. One panel.
See every move Claude makes: agents, files, plans, tests and risky commands, live, beside the chat.
In Claude Code, add the marketplace, then install the panel and the mods you want:
Or install all of them at once from a terminal:
Or ask your coding agent: Install MODZ for me. Follow https://partalemre.github.io/MODZ/llms.txt and ask me which mods I want.
Start a new session. The MODZ panel opens on the right with a line from every mod you installed.查看完整 README ↗In Claude Code, add the marketplace, then install the panel and the mods you want:
/plugin marketplace add partalemre/MODZ
/plugin install modz@modz
/plugin install savvy-progress@modz
Or install all of them at once from a terminal:
claude plugin marketplace add partalemre/MODZ
for m in modz savvy-progress savvy-flow filetree plan-steps handoff transceiver blast-radius secret-guard checkpoint \
test-badge replay-theater session-budget cache-tax hud-pro effort-router done-ping reflect-mod skins terminal-browser; do
claude plugin install "$m@modz"
done
Or ask your coding agent: Install MODZ for me. Follow https://partalemre.github.io/MODZ/llms.txt and ask me which mods I want.
Start a new session. The MODZ panel opens on the right with a line from every mod you installed.
terminal-browser draws in the terminal only. Outside the desktop app, done-ping falls back to a macOS banner.modz marketplace, so every mod you installed, transceiver from its own repo included, updates itself in the background a few minutes into a session and loads fresh at the next start. No model call, no command to run. If you already chose under /plugin > Marketplaces, that choice stays; to turn it off, choose Disable auto-update there.MODZ_LANG=tr for Turkish.claude -p, an SDK host), also set CLAUDE_CODE_ARTIFACT=1.Both variables go in the env block of ~/.claude/settings.json:
{ "env": { "MODZ_LANG": "tr", "CLAUDE_CODE_ARTIFACT": "1" } }
The panel opens beside the chat when a session starts. Each mod reports one honest line: what it measured, never a guess. One click opens that mod's own pane next to the panel.
Each subagent gets a crab, a name and a card with its task, step, progress, cost and time, updated as it works. A band above the prompt shows the whole crew while a turn runs.
rm -rf, git reset --hard, git clean, force pushes and migrations stop before they run. The card shows exactly what each would delete or throw away, and the safe choice has the focus.
Transceiver lets you chat with teammates without leaving Claude Code. Your agent can ask theirs for status, diff, tests, log or a file. The answer is computed on their machine and costs zero tokens. Only collaborators on the repo can ask, and secrets never leave your machine. Rooms are private claude.ai artifacts; there is no extra server. Transceiver is in beta: it works end to end, and its rough edges are being found. How it works
| Mod | What it does | |
|---|---|---|
| Panel | modz | The panel itself: one live line per mod and one click to each pane; keeps Claude replying in your language |
| Work | savvy-progress | Agents pane and progress band: each subagent's progress, cost and time; other chats waiting on you; a home crab that levels up |
savvy-flow | Orchestrated delivery: the session model plans, tiered worker agents build | |
filetree | Files Claude touched this turn, what it is doing now, git status | |
plan-steps | The plan's steps as Claude works through them; the plan comes back after /clear and compaction, and a turn that ends with steps open offers to go on | |
handoff | Before the context fills, writes a handoff note and hands it once to your next fresh chat | |
transceiver | Team chat and zero-token agent questions between teammates (beta) | |
| Safety | blast-radius | Holds destructive shell commands and shows what they would change; holds an edit to a file another chat just changed; checks other commands against your .claude/house-rules.md |
secret-guard | Stops keys and tokens in writes, edits, git add and commits; keeps pasted keys out of the chat as placeholders; /rec masks keys, env values and e-mail addresses on screen | |
checkpoint | A silent git snapshot before each turn's first write; undo a turn | |
test-badge | Runs tests and lint after edits and shows the result; watches your PR's GitHub CI | |
replay-theater | Replays the last turn's edits step by step, and earlier turns and past sessions | |
| Meter | session-budget | A spend budget per session, with a stop at 100%; asks before new subagents when the 5-hour window runs low |
cache-tax | Keeps the prompt cache warm through breaks and prices a cold send, a model change included |
Most mods use no model tokens. These can, each with the cheapest model and never more than one call per event:
reflect-mod: one small check per correction it finds, and one per /mine.cache-tax: warming sends a request, only when you turn it on.handoff: one summary per handoff note (summarize, on by default; the note is written without it too).effort-router: one check per prompt, only in auto mode.blast-radius: one check per command it judges, only when .claude/house-rules.md exists.replay-theater: one call when a step has no description of its own.ask: a small model on the other side, at most ten a day per room.plan-steps (while it brings a plan back) and secret-guard (while placeholders exist) add a short section to the system prompt.
Read from the code, not from a promise. "Store" is the mod's own file in ~/.claude; every mod also keeps session state in memory.
| Mod | Reads | Writes | Runs | Network | Model |
|---|---|---|---|---|---|
modz | marketplace, settings | store; once, autoUpdate for its marketplace in user settings | |||
savvy-progress | transcript | store | agents you start | ||
savvy-flow | its worker agents | ||||
filetree | project files | git, open | |||
plan-steps | task list, plan file | store | |||
transceiver | repo, git | its room | git | claude.ai | free-form ask |
handoff | transcript, plan | .claude/handoff/*.md, store | git status, rm (own notes) | optional | |
blast-radius | .claude/house-rules.md | store | git, a read-only look at what a held command would touch | Jev, opt-in | with house rules |
secret-guard | written files | .env, .gitignore (on your press) | git | ||
checkpoint | store, git refs | git | |||
test-badge | project files | store | your test and lint commands, git, gh | GitHub, through gh | |
replay-theater | transcripts | store | rarely | ||
session-budget | store | ||||
cache-tax |
Jev is TypeSafe's classifier: set MODZ_JUDGE=jev and TYPESAFE_API_KEY to use it instead of your own model account. What it is sent is masked first.
/modz does the same./plugin configure modz@modz turns off opening at session start.The panel lists any mod that reports to it, with no change to MODZ. Your mod talks to it through $.state:
{ plugin: '<your-mod>', key: 'hub' } value: { pane, detail, tone, at }, plus your row's title, hint, icon (a kit icon name), section (work, safety or meter) and an optional badge. tone is idle, live, ok, warn or bad; write it only when the text changes.state.set on { plugin: 'modz', key: 'open' }; when its pane is yours, call $.ui.open({ id, title, focus: true }).{ plugin: 'modz', key: 'isOn' } is true, draw HomeButton from kit/home.tsx first in your pane; its press writes your own { plugin: '<your-mod>', key: 'home' } as { at }.DESIGN.md §9 has the full contract, and mods/modz/types/index.d.ts the types. bin/modz new <name> starts a mod from the template.
If a person asks you to install MODZ, do exactly this. Every step is safe to repeat.
claude --version must print 2.1.295 or later. If it is older, ask the person to update Claude Code first.claude plugin marketplace add partalemre/MODZ.claude plugin install modz@modz. Then install each mod the person wants, by the names in the table above, as claude plugin install <name>@modz. If they did not choose, install all twenty with the loop under Install.env block of ~/.claude/settings.json, merging with what is already there and never overwriting it:
"MODZ_LANG": "tr" for a Turkish interface."CLAUDE_CODE_ARTIFACT": "1" if Transceiver is installed and this Claude Code is driven by an SDK host.claude plugin list shows each <name>@modz as enabled./reload-plugins in an open one.To remove a mod: claude plugin uninstall <name>@modz. To remove everything: also run claude plugin marketplace remove modz. A machine-readable summary is at partalemre.github.io/MODZ/llms.txt.
mods/<name>/ holds each mod; kit/ is the shared drawing kit, copied into the mods by bin/kit-sync.
bin/modz check [name] validates each mod and runs its tests, on both the terminal engine and the desktop app's engine.bin/modz desk starts a real session, speaks the desktop app's own protocol to it, and clicks through every panel. Run both before opening a pull request.bin/modz shot [--pane] [--title t] saves the Claude window as a PNG, even when another window covers it. Mods load when a session starts: to look at fresh code, open a new session in its own window and shoot it with --title.version: Claude Code then versions each one by its commit, so every push to main reaches every user. Keep it that way; a pinned version stops updates until someone bumps it..claude-plugin/types/ beside a mod it hot-reloads. Each mod's tsconfig.json extends them, so tsc -p mods/<name> type-checks that mod.tools/kit-gallery draws every kit component; its tests check contrast in both themes.Several mods are adaptations of open-source projects, each under its original license, which lives in that mod's folder:
| Mod | Based on | License |
|---|---|---|
blast-radius, replay-theater | anthropics/claude-code-playground | Apache-2.0 |
cache-tax | karanb192/cache-tax | MIT |
filetree | data-goblin/claude-code-filetree | MIT |
reflect-mod | bayramannakov/claude-reflect | MIT |
savvy-progress, savvy-flow | johnnyvizz/claude-kit | MIT |
skins | hellosverre/claude-skins | MIT |
terminal-browser | zenbu-labs/terminal-browser | MIT |
Everything else is MIT.
upstreams.json records the upstream date each adaptation is synced to; a weekly workflow (.github/workflows/upstream-watch.yml) keeps one open upstream issue per mod listing the newer upstream commits.
A second weekly workflow (.github/workflows/mod-radar.yml) keeps one radar issue with the most-starred new mods from the awesome-claude-code-mods catalogue that MODZ has not adapted. MODZ keeps one mod per job: an idea worth taking is folded into the mod that already does that job.
hud-pro | One line with the 5-hour and 7-day limits, context and cost; when the 5-hour window fills; what fills the context and how many turns are left; 7 and 30 days of usage history |
effort-router | Shows each turn's effort and model; can send light prompts at low effort |
| Comfort | done-ping | A notification when a long turn ends or Claude waits on you, with optional sound packs |
reflect-mod | Saves corrections worth keeping to your CLAUDE.md; /mine turns friction that repeats across past chats into ideas |
skins | Themes for the transcript, switched live with /skin |
terminal-browser | A browser inside the terminal that the agent can drive |
| store |
| when warming |
hud-pro | context breakdown | store |
effort-router | prompts | store | Jev, opt-in | auto only |
done-ping | store | osascript, terminal-notifier, afplay |
reflect-mod | transcripts, CLAUDE.md | CLAUDE.md (on your press), store | tail | yes |
skins | settings | store |
terminal-browser | web pages | a browser | yes |