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 commands/plocr/reasonix-computer-use/rungit clone --depth 1 https://github.com/Plocr/Reasonix-computer-useWhat 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 | $0.00012 | $0.00376 |
| Opus 5 | $0.00006 | $0.00188 |
| Sonnet 5 | $0.00002 | $0.00075 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade A, and why
run 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.
What it actually says
你已经位于 /computer-use:run 展开的执行上下文中。上下文中已注入：
- 任务计划 — 按 abc 编号的自动化步骤序列，包含难度评估和系统画像状态
- 系统画像状态 — 如果缺失已自动生成
system.md+system-index.json - 依赖状态 — 如果缺少会自动提示安装
- 视觉路由 — 当前 vision capability 状态
执行流程：
- (a) 初始化：检查上下文中"Computer Use 任务计划"，按步骤顺序执行
- (b) 如提示缺少依赖，先用
computer_system(operation="setup", confirmed=true)安装 - (c) 如需系统画像，先查看
memory/system.md - (d) 按照计划中的 (a)(b)(c)... 步骤依次执行，每步完成验证后再继续
- (e) 任务结束后自动清理截图缓存并汇报
禁止再次调用 slash_command、/computer-use:run 或 /computer-use:agent:operator，
也不要枚举命令/Skill 注册表。Operator 契约已经由插件注入。仅当
$ARGUMENTS 非空时继续；缺少任务内容时先询问用户。
不要改写用户指定的双击、右键、中键、拖动、滚轮或指定应用等必要方法。 Operator 返回后原样汇总其已验证证据、阻断和实际方法，不得把"界面变化"推断为完成。
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 · 25 lines · 12 tokens per session scan A 3cf2473393b6
run is a command published in the GitHub repository Plocr/Reasonix-computer-use (40 stars, last pushed 27d ago), licensed MIT. It adds 12 tokens to every session and 376 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.
Other commands, from other repositories
toggle-speak
Toggle whether Claude speaks each response aloud automatically via the Stop hook.
speak
Read your immediately preceding response aloud — local mode (verbatim, mechanical) or llm mode (LLM-written spoken summary).
toggle-speak-mode
Toggle /speak's persisted default mode between local (mechanical) and llm (LLM-summarized).
speak-rate
Get or set the speech rate (words per minute) used by all say-based speech output.
speak-voice
Get, set, list, or reset the TTS voice used by all speech output (macOS say or Linux espeak-ng).
speak-limit
Get, set, or reset the max byte length spoken before truncating at a sentence boundary.