cursor-agent
When the user wants the local cursor-agent CLI run, its installation or login changed, its connected tools changed, or a Cursor worker started.
- License 许可
- MIT
- 最近更新
- 2026-11-10
- Stars
- ★ 6
- Forks
- 0
01 前言 Front Matter
- name
- cursor-agent
- description
- When the user wants the local cursor-agent CLI run, its installation or login changed, its connected tools changed, or a Cursor worker started.
02 资源文件 6
- 参考文档references/install.md643 B
- 参考文档references/integrations.md2.4 KB
- 参考文档references/management.md665 B
- 参考文档references/sessions.md737 B
- 参考文档references/streaming.md928 B
- 参考文档references/worktrees.md766 B
03 SKILL.md 正文
Cursor Agent
Options and boundaries
Default: cursor-agent --print --trust --yolo --workspace <abs-dir> "<prompt>",
mode/model omitted, text output, parent wait 15m. Calling this skill authorizes
that run: pass --trust and --yolo without asking. Print alone can write.
"Plan" / "read-only plan" adds --plan and omits --yolo. "Ask" / "Q&A" adds
--mode ask and omits --yolo. Both stay read-only, still pass --trust, and
wait until exit. "Use <model>" adds --model. "Interactive" / "TUI" omits
print, --trust, and --yolo; the user owns that dialog.
"Resume <id>" adds --resume; "continue" adds --continue; both wait until
exit and keep the same trust/yolo choice as the selected mode.
"Worktree [name]" adds --worktree [name]; record the printed path.
"JSON" / "stream-json" selects that print format. Ambiguity is BLOCKED.
Add sandbox disabled, approve-mcps, or a worker desktop/credential flag only when the user names that control. Auto-review is explicit opt-in. Do not stop to confirm trust or yolo, and do not add those extra flags after a failure.
1. Resolve
Fix workspace, prompt, mode, session/worktree, output, and wait.
Check binary and cursor-agent status --format json without exposing secrets.
Missing binary → follow references/install.md; missing auth → BLOCKED
unless login was requested.
Record cmd | workspace | mode | session | worktree | wait | evidence | terminal.
Done when target, binary, auth, and the trust/yolo choice are fixed.
2. Run
Build argv and quote the prompt literally. Text/json may be quiet until
exit; silence is not a hang. Wait until exit or the recorded deadline;
kill only this run's PID at that deadline. Nonzero exit: capture stderr,
inspect the tree, report BLOCKED. On Workspace Trust Required for a
print run, rerun that argv with --trust if it was missing. Leave a TUI
on its user-owned dialog. Do not ask the user and do not add sandbox, MCP,
or worker flags.
For JSON/stream output, follow references/streaming.md.
For resume, continue, or persist, follow references/sessions.md.
For worktrees/parallel runs, follow references/worktrees.md.
For a TUI or other command syntax, follow references/management.md.
For login, MCP, plugins, workers, or Bedrock, apply the matching branch in
references/integrations.md. On rejected syntax, use scoped --help.
Done when the process exits, an intended live session is recorded, or a
failure is reported.
3. Verify and report
Inspect status and diff; CLI text is unverified. Run the narrowest covering tests for edited executable code. Plan/ask must leave the tree unchanged. Check each worktree and any integrated tree. Clean up only sessions and clean worktrees this run created unless kept; preserve shell integration, MCP, plugins, and workers. Report command, mode, session/worktree, wait, and outcome evidence. Done when each outcome is observed or blocked with evidence.
Terminals: SUCCESS, NO_CHANGES, BLOCKED.
04 同仓库更多 Skills
use-skill
When the user gives a GitHub link to a skill and wants it run without installing it.
todoist-task
When the user wants a Todoist task created, or shown before it is created.
restate
When the user wants the last reply said again in plain words, wants a catch-up since their last message, or wants the decision they need to make.
upfront-design
When the user wants a design agreed before coding, a draft resumed, or an approved milestone checked.
recon
When the user wants this repository's saved map read, created, or refreshed.
prath-mode
When the user wants a goal sent to one skill or one delivery chain.