DeepChat is an open-source desktop client for AI agents that keeps user data local first and connects agents with services such as MCP, Skills, ACP, and messaging apps. It is for people who want to use and control AI assistants from a desktop application. The catalogue add-ons extend DeepChat’s agent workflows.
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 skills add ThinkInAIXYZ/deepchat --skill computer-usegit clone --depth 1 https://github.com/ThinkInAIXYZ/deepchatWrote 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/thinkinaixyz/deepchat/computer-use)<a href="https://agentmods.dev/skills/thinkinaixyz/deepchat/computer-use"><img src="https://agentmods.dev/badge/skills/thinkinaixyz/deepchat/computer-use/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thinkinaixyz/deepchat/computer-use"><img src="https://agentmods.dev/badge/skills/thinkinaixyz/deepchat/computer-use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 14 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 117 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 5.1 | $0.00040 | $0.02638 |
| Opus 5.5 | $0.00016 | $0.01055 |
| Sonnet 5.5 | $0.00008 | $0.00528 |
| Haiku 4.5 | $0.00004 | $0.00264 |
Grade A, and why
computer-use 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 1mo ago.
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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
computer-use
Use DeepChat's plugin-provided Computer Use tools as the only action surface for this skill. Do not
ask the user to install cua-driver, configure an external server, or put anything on PATH for the
bundled DeepChat plugin.
Runtime Context
- Plugin id:
${OWNER_PLUGIN_ID}. - Plugin root:
${PLUGIN_ROOT}. - Process arch:
${PROCESS_ARCH}. - Supported targets:
darwin/arm64,darwin/x64,win32/x64,win32/arm64,linux/x64. - Unsupported targets:
linux/arm64. - macOS runtime bundle: packaged builds prefer
DeepChat.app/Contents/Helpers/DeepChat Computer Use.app; the plugin-local fallback is${PLUGIN_ROOT}/runtime/darwin/${PROCESS_ARCH}/DeepChat Computer Use.app. - Windows helper binary:
${PLUGIN_ROOT}/runtime/win32/${PROCESS_ARCH}/cua-driver.exe. - Linux helper binary:
${PLUGIN_ROOT}/runtime/linux/${PROCESS_ARCH}/cua-driver.
Required Loop
- Declare one stable run identity with
start_session({ session, capture_scope: "auto" }). Reuse thatsessionvalue for every state and action call whose advertised schema declares it. Omitcursor_themeduring normal session setup. - Resolve the app with
list_apps. Match localized names, English names, romanized names, bundle identifiers, executable names, and common abbreviations. Prefer stable identifiers when a result provides them. - Start or reuse the target with
launch_app. Use the returnedpidwhen available. - Inspect windows with
list_windows({ pid })when the launch result lacks a usable window. - Snapshot before every UI action with
get_window_state({ pid, window_id, session }). Passinclude_screenshot: truefor the initial view, sparse or ambiguous accessibility trees, pixel actions, and visual verification. Passinclude_screenshot: falsefor a routine cheap re-index when the accessibility target is already unambiguous. - Act with the matching DeepChat tool:
click,right_click,double_click,drag,scroll,type_text,press_key,hotkey,set_value,set_window_frame,invoke_menu, orlaunch_appwith URLs/files when supported by the platform. FollowWEB_APPS.mdfor browser page content. - When an ActionResult-contract tool appends
## CUA action result, read it. Delivery describes dispatch, not effect or task completion. Do not continue as if the action succeeded wheneffectispartial,unverifiable,suspected_noop, orrefused. Legacy lifecycle/app tools without this projection still require postcondition verification. - Verify after each action. Use
verify_statefor an exact-window postcondition expressible as window existence/bounds or a trusted native element's existence/value/enabled/selected state. Otherwise take a freshget_window_state,get_browser_state, orget_desktop_stateand inspect the relevant visible evidence. - Call
end_session({ session })after the run, including orderly error cleanup.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 201 lines · 40 tokens per session scan A 89ec0e98e13c
computer-use is a skill published in the GitHub repository ThinkInAIXYZ/deepchat (6,362 stars, last pushed 4d ago), licensed Apache-2.0. It adds 40 tokens to every session and 2,638 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
youtube-watcher
Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.
search-craft
How to get real coverage out of a search engine that returns a handful of results per query, and when to reach for the crawler or the browser instead. Use at the start of any search that has to be thorough rather than quick.
extremerouter-web-fetch
Fetch URL → markdown / text / HTML via ExtremeRouter /v1/web/fetch using Firecrawl / Jina Reader / Tavily Extract / Exa Contents. Use when the user wants to scrape a webpage, extract URL content, read article, or convert a URL to markdown.
Agent Browser
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
har-derived-api-client
Record a site's XHR into a HAR, derive an HTTP client.
blocked-page-recovery
Use when a fetch fails: 403/429, paywall, WAF, bot wall.