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/songkeys/kimi-computer-use/computer-usenpx skills add songkeys/kimi-computer-use --skill computer-usegit clone --depth 1 https://github.com/songkeys/kimi-computer-useWrote 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/songkeys/kimi-computer-use/computer-use)<a href="https://agentmods.dev/skills/songkeys/kimi-computer-use/computer-use"><img src="https://agentmods.dev/badge/skills/songkeys/kimi-computer-use/computer-use.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 | $0.00597 |
| Opus 5 | $0.00017 | $0.00298 |
| Sonnet 5 | $0.00007 | $0.00119 |
| Haiku 4.5 | $0.00003 | $0.00060 |
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 4d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Computer Use
This plugin exposes OpenAI's locally installed Computer Use service directly as
Kimi MCP tools. Use the tools whose names begin with
mcp__plugin-kimi-computer-use_computer-use__.
The bridge automatically handles the service's app-access elicitation. Do not ask the user to approve Computer Use access and do not attempt to manage the OpenAI app's allowlist.
Required observation and action loop
- Start with
get_app_statefor the named application. Pass the app's display name or bundle identifier directly. - Read the returned accessibility text first. Use the accompanying screenshot when the accessibility tree is incomplete or visual context matters.
- Prefer actions using the latest
element_index. Use coordinates only when the target is unavailable or unreliable through accessibility. - Perform one or more tightly related actions.
- Call
get_app_stateagain before deciding the next action. Re-derive element indices from the latest state and never assume an old index is still valid.
The get_app_state result may be a diff from the preceding state. Request a
full state only when the earlier tree is unavailable or a diff is insufficient.
Tools
list_apps: discover apps only when the requested app cannot be identified from its name or bundle identifier.get_app_state: read accessibility state and capture a screenshot.click: click byelement_index, or by coordinates as a fallback.set_value: replace the value of an editable accessibility element.type_text: type into the target app.press_key: send a key or key combination such asReturn,Tab,super+c, orEscape.scroll: scroll an element or view.drag: drag between coordinates.select_text: select matching text or place the cursor around it.perform_secondary_action: invoke an accessibility action explicitly exposed by an element. Never guess the action name.
App targeting
- No separate launch step is needed.
get_app_statelaunches the app when necessary. - Try the app name or known bundle identifier directly before calling
list_apps. - If targeting by display name fails, call
list_apps, find the bundle identifier, and retry once with that identifier. press_keyandtype_texttarget the selected app; they are not global keyboard shortcuts.
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.
- 4d ago First seen · 63 lines · 35 tokens per session scan A b329dfe839d9
computer-use is a skill published in the GitHub repository songkeys/kimi-computer-use (6 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 597 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 2026-08-31.
Other skills, from other repositories
nova-grounding
AX-first reading and grounded activation workflow for Nova desktop automation on macOS and Windows. Use for reading UI, clicking controls, OCR fallback, screenshots, and coordinate input without guessing.
computer-use
Windows 桌面自动化执行规则。使用 screeninteractor 观察与操作原生桌面应用。.
web-navigator
Web 浏览器自动化路由规则。通过 webnavigator 将 Web 场景路由到 Playwright MCP 或 mcp-chrome。.
computer-use
Control local macOS applications through the installed Computer Use MCP tools. Use for GUI work that is not better served by a dedicated API, connector, or CLI.
computer-use-macos
Top-level macOS computer-use skill with a bundled standalone runtime that bootstraps itself without any local Claude installation, private native modules, or extracted app assets.
desktop-gui-inspect
Full-desktop automation for targets that have no browser and no API at all — a legacy Java-based NMS client, a vendor's Windows-only configuration utility, a terminal emulator with no scriptable interface. Drives OpenClaw's ClawHub computer-use skill (Xvfb+XFCE virtual desktop, xdotool input automation) to read…