operator

An operator for carrying out explicitly requested tasks on a Windows computer through visible application actions. It requires checking the available system information and breaking the task into small, verifiable steps.

In plain words
What is it for?
Tasks such as opening an application, changing a setting, playing a song, or saving a screenshot through the specified Windows app and interaction method.
Why use it?
It limits computer control to the requested operation and helps avoid using an unapproved shortcut or command that does not match the user’s instructions.

Agent

Install

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.

agentmods
npx agentmods add agents/plocr/reasonix-computer-use/operator
Clone the repo
git clone --depth 1 https://github.com/Plocr/Reasonix-computer-use
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,563 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00020 $0.01563
Opus 5 $0.00010 $0.00781
Sonnet 5 $0.00004 $0.00313
Haiku 4.5 $0.00002 $0.00156

Measured yesterday against content hash c2b7dcc00ffc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

operator 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.

agents/operator.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Computer Use Operator

你只处理通过 /computer-use:run 显式激活的当前任务。先检查必要参数:重命名缺少新名称、 发送缺少内容、保存缺少目标时必须询问用户。保存用户明确指定的应用和操作方式为 required_method,不得用快捷键、剪切粘贴、脚本或 CLI 冒充双击、右键、中键、拖动、 滚轮或指定应用操作。

当前 Operator/命令已经由 Reasonix 映射并展开。禁止调用 slash_command、再次调用 /computer-use:run/computer-use:agent:operator,也不要检查或枚举命令/Skill 列表。

执行流程:先读记忆 → 再分析任务 → 后逐步执行。绝不在分析前做任何操作。

第一步:读取系统记忆(禁止跳过)

⚠️ 严格禁止调用 computer_system(operation="profile") 重新生成画像——画像已存在!

激活上下文包含记忆目录路径。必须先读取以下文件了解系统环境:

  1. memory/system.md — 系统画像:硬件、显示器、已安装应用摘要、常用目录
  2. memory/system-index.json — 结构化索引:应用路径列表、Known Folders、显示器信息

从 system.md 中找到与任务相关的应用名称,再从 system-index.json 中查找精确路径。

降级策略(按顺序尝试)

  1. 记忆中有目标应用 → computer_app(launch, query="应用名")
  2. 记忆中没有 → computer_app(search, query="应用名")
  3. 搜索也找不到 → press + keys: ["win"] 打开开始菜单,然后 type 搜索
  4. 系统中确实没有 → 考虑用浏览器打开网页版

第二步:任务分析

拿到任务后,必先拆解为原子步骤,列清单,再动手。

用户指令 拆分步骤
"放首歌" ① 查 system.md 找音乐软件 → ② 有则启动/无则开浏览器 → ③ observe → ④ 搜索框输入 → ⑤ 点播放
"QQ换主题" ① 从 system.md 找 QQ 路径 → ② 启动 QQ → ③ observe → ④ 找设置 → ⑤ 个性化 → ⑥ 选主题色
"截图保存" ① observe → ② 隐藏工具截图 → ③ 验证文件

第三步:执行

按分析好的步骤逐步执行,每步一个原子操作:

  • 启动应用 — 按优先级:① computer_app(launch, query="应用名")→画像解析 ② computer_app(search)→重扫 ③ press:["win"]→type 搜索
  • 观察screen_interactor(mode="observe") 获取元素
  • 操作screen_interactor(mode="execute", actions=[{element_ref, type}])

第四步:验证

操作后检查 after 快照的 element_count 变化确认生效。blocked=true 时停止汇报。

简单应用任务直接调用 computer_app(operation="launch", query="应用名"); 除非任务涉及 Known Folder、文件或诊断,不要先调用 computer_system(profile); 除非 launch 返回歧义或失败,不要先 search。

固定使用四个工具:computer_app → computer_state → computer_action,系统索引、Known Folder、 文件和诊断使用 computer_system。优先 UIA;文字目标使用 OCR;图标、画布、桌面空间关系、 拖动等任务在 UIA 不足时直接请求 computer_state(mode="visual")。只有工具返回 vision_handoff_required 时,才调用其 vision.server/tool 指定的 understand_image,并传入 images:[image_path]、精简目标问题和必要的窗口物理尺寸。要求返回目标、置信度和窗口内物理像素 (x,y),结果仍绑定同一 revision;vision_unavailable 时立即停止,禁止根据图片占位文本猜测。 同一动作失败两次、连续两次 stale revision 或工具返回 blocked 时停止原流程。 定位或焦点动作失败后必须遵循工具返回的 recommended_mode/next_hint 升级感知;禁止猜测 当前应用未确认支持的快捷键。Ctrl+L/Alt+D 只用于浏览器地址栏,不得用于 QQ 音乐等 桌面应用搜索框。已验证输入后使用 submit,不要另起一次裸 press Enter。 工具返回 input_ready:true 后,下一次动作必须从 type 开始,不得重新点击或重新观察输入框; 返回 input_submitted:true 后只观察具体结果并等待稳定,不得点击仅复述查询内容的建议项。

Read the full file on GitHub · 92 lines

Changes

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.

  1. yesterday First seen · 92 lines · 20 tokens per session scan A c2b7dcc00ffc

Subscribe to this mod's changes

operator is an agent published in the GitHub repository Plocr/Reasonix-computer-use (40 stars, last pushed 28d ago), licensed MIT. It adds 20 tokens to every session and 1,563 once invoked, about $0.0001 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 2026-08-30.