Automate tmux, a tool for managing multiple terminal workspaces, to inspect output, send commands, monitor stalled tasks, and record logs. Coordinate multiple AI terminals with task queues, file locks, status tracking, and handoff reports.
需要用tmux原生命令列出session/window/pane、capture-pane读取终端、确认目标后send-keys发送输入，或排查tmux/oh-my-tmux配置时使用；不提供已退役的蜂群、报告或自动救援封装。
Review the instructions the agent will receive before you install.
用tmux原生CLI完成明确授权的终端观察与操作。原27个自研封装脚本已退役；不依赖旧命令，不重造包装层。
command -v tmux
tmux -V
缺少程序或连接不到指定server时报告实际失败，不自动安装或换到未知server。
tmux list-sessions
tmux list-windows -a -F '#{session_name}:#{window_index} #{window_name}'
tmux list-panes -a -F '#{pane_id} #{session_name}:#{window_index}.#{pane_index} #{pane_current_command} #{pane_current_path}'
只选择用户授权的目标。使用列出的稳定pane_id，不能根据第一个窗口、相似名称或旧截图猜目标。
先把占位符替换成刚核对的真实pane_id；未替换时不能执行后续发送。
target='<已核对的pane_id>'
tmux display-message -p -t "$target" '#{session_name}:#{window_index}.#{pane_index} #{pane_current_command} #{pane_current_path}'
tmux capture-pane -p -S -120 -t "$target"
输出可能含个人资料或凭据，先脱敏再展示；没有授权不写日志或上传。读取成功不授权继续控制。
发送前重新列出并capture，确认pane仍存在、当前程序及其解释输入的方式未变化。 只在已确认的shell里使用下面的无害示例；在模型UI、数据库、安装确认或密码提示中不能套用。
tmux send-keys -t "$target" -l 'printf "hello\\n"'
tmux send-keys -t "$target" Enter
-l按字面文字发送，不把文本误识别为tmux按键名称；文字与Enter分开不是事务，发送中途状态变化应停止。
完成后再次capture检查真实结果。不自动发送y、Ctrl-C、Ctrl-D或广播，不通过重试重复不可逆操作。
assets/tmux-src和assets/oh-my-tmux仍指向固定上游，仅查阅不代表安装或写用户配置。只维护操作指令、来源与权限边界，不再维护自动化程序、共享任务锁、日志报告或多Agent执行框架。 原生发现、原生CLI隔离示例及静态审阅分别报告；未做模型压力实测时不得宣称模型会稳定遵守所有边界。
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Analyze Solidity smart contracts with Slither and Mythril before Ethereum deployment. Combine code inspection with execution path analysis, review potential vulnerabilities, remove duplicate findings, and produce an audit report with severity ratings and suggested fixes.
Audit Solidity contracts in Foundry projects before deployment using code analysis, randomized tests, manual review, and private key checks. Produces a JSON report with findings, remediation, test coverage, and a pass or fail deployment decision.
Build reusable Claude Skills from documentation, APIs, code, and specifications. Organize instructions and reference files, define clear activation conditions, add reproducible examples, and check new or existing skills against a delivery checklist.
Check mathematical expressions, solve equations, and search bounded ranges for counterexamples using symbolic and numerical libraries. Record assumptions, commands, and results so calculations can be repeated, while keeping computational evidence distinct from general mathematical proof.
Turn scattered formulas and theory notes into a derivation that can be checked step by step. Keep definitions and assumptions consistent, distinguish exact identities from approximations, and make hidden conditions and limits explicit.
Shape broad mathematical interests into precise research questions. Search prior work on definitions and theorems, record traceable sources, map supporting and conflicting evidence, and identify gaps that could lead to testable conjectures.