Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/craftos-dev/craftbot/living-ui-managernpx skills add CraftOS-dev/CraftBot --skill living-ui-managergit clone --depth 1 https://github.com/CraftOS-dev/CraftBotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/craftos-dev/craftbot/living-ui-manager)<a href="https://agentmods.dev/skills/craftos-dev/craftbot/living-ui-manager"><img src="https://agentmods.dev/badge/skills/craftos-dev/craftbot/living-ui-manager.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00035 | $0.00658 |
| Opus 5 | $0.00017 | $0.00329 |
| Sonnet 5 | $0.00007 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
living-ui-manager scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Living UI Manager
Operate and manage existing Living UIs. Never edit code here — if a request needs code changes, that's living-ui-modify.
Inventory
- Registry:
agent_file_system/workspace/living_ui_projects.json— id, name, status, port, path per project. - Per project:
manifest.json(port, authMode, pipeline),LIVING_UI.md(what it does),operations.json(its verbs).
Lifecycle
living_ui_notify_ready(project_id)— validate + launch (or relaunch).living_ui_restart(project_id)— stop then full relaunch.- A running app serves everything on ONE port:
http://localhost:<port>— the UI, the PB REST API (/api/collections/...), declared ops, and discovery atGET /api/_ops.
Operating an app (using it on the user's behalf)
Use the lui CLI via run_shell. ALWAYS use the ABSOLUTE CLI path —
the shell's cwd is NOT the repo root, so relative paths fail. The CLI is
<craftbot-root>/living-ui/tools/src/cli.ts (craftbot-root = parent of
agent_file_system; in a Living UI session the [INTERACTING WITH LIVING UI]
note contains the exact ready-to-run commands). <CLI> and <project> below
are absolute paths.
- Discover what the app can do:
node <CLI> ops <project> - Declared op exists → run it:
node <CLI> run <project> <op-name> --param valueOps markedDESTRUCTIVE→ confirm with the user first. - No op → generic data access:
node <CLI> data <project> <collection> list --filter '...' --sort '-created' --limit 20node <CLI> data <project> <collection> create --json '{"field":"value"}'node <CLI> data <project> <collection> update <id> --json '{...}'/delete <id>Read freely; write only what the app's own UI offers. - Needs new capability → say so and offer a modification instead of hacking around it.
Fallback only when the shell is unavailable: the living_ui_http action
speaks to the same API.
Diagnosing
- Status
error: read the project'serrorfield in the registry, thenlogs/pocketbase.log(server/migrations) andlogs/frontend_console.log(frontend). Report findings honestly; hand fixes to living-ui-modify. - Never start
pocketbase/npmprocesses by hand; never touchpb_data/or.superuser.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 62 lines · 35 tokens per session scan A c2d7de44515b
living-ui-manager is a skill published in the GitHub repository CraftOS-dev/CraftBot (378 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 658 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
turix-mac
Computer Use Agent (CUA) for macOS automation using TuriX. Use when you need to perform visual tasks on the desktop, such as opening apps, clicking buttons, or navigating UIs that don't have a CLI or API.
browser-control
Control web pages in an existing Chromium remote-debugging session with deterministic sagui commands or the browser-only AI Agent. Use when Claude Code needs to inspect tabs, observe semantic elements, navigate, click, type, send keys, scroll, or complete a browser goal through CDP without controlling native macOS UI…
agent-smoke-test
Run manual development checks for SwiftAutoGUI AI Agent actions through the local sagui CLI. Use when Claude or Codex needs to test app-control or Accessibility BasicAction generation on macOS.
macos-control
Control macOS GUI applications via mouse automation, keyboard input, screenshots, image recognition, and AppleScript execution. Use when you need to interact with macOS app UIs, take screenshots, click buttons, type text, scroll, drag, or locate images on screen.
open-record-replay
Record a user-demonstrated macOS workflow with the Open Record/Replay CLI, inspect the captured event stream, prepare a skill evidence package, and hand it to the host agent's native skill creator. Use when the user asks the agent to watch them perform a task, record a workflow, or create/refine a reusable Computer…
artifact-storage-policy
管理 Codex 交付物的專案識別、Google Drive/GitHub 路由、檔名、儲存位置與回讀驗證;凡工作報告、外部保存、交付成果或新 repository 選擇涉及遠端儲存時使用。.