← 返回 Skills 市场
albinati

Cursor Agent for OpenClaw

作者 Luis Albinati · GitHub ↗ · v1.0.2
cross-platform ⚠ suspicious
404
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install cursor-agent-openclaw
功能描述
Run Cursor Agent CLI for coding tasks — writing, editing, refactoring, reviewing, or planning code — without spending OpenClaw API credits. Use when the user...
使用说明 (SKILL.md)

Cursor Agent

Cursor Agent CLI runs on the user's Cursor subscription — zero API cost. Always prefer it over inline code generation for any non-trivial coding task.

Prerequisites

Required binary: agent (Cursor Agent CLI)

Install from the official site: https://cursor.com/docs/cli/overview — then verify with agent --version. The helper script (scripts/run.sh) will exit with an error if agent is not found in PATH.

User Consent Required — MANDATORY

This skill MUST NOT be invoked autonomously. Every invocation requires:

  1. State intent first — tell the user: the repo, the task, the model, and whether files will be changed
  2. Wait for explicit "yes" — do not proceed without clear user approval
  3. Default to read-only — use run.sh \x3Crepo> \x3Ctask> \x3Cmodel> ask unless the user explicitly asks for changes
  4. Before writing files — run in ask mode first, show the user the plan, then ask: "Apply these changes?"
  5. Before --cloud — explicitly warn: "This will send repo contents to cursor.com. OK to proceed?"
  6. Before committing — show the diff and get confirmation

The helper script (scripts/run.sh) defaults to ask (read-only). Pass write as the mode argument only after the user has confirmed changes should be applied.

Model Routing

Task type Model flag Mode flag
Trivial / exploratory (omit — auto) (omit)
Bug fix / feature / refactor --model sonnet-4.6 (omit)
Code review / explain (read-only) --model sonnet-4.6 --mode=ask
Architecture / design planning --model opus-4.6-thinking --mode=plan
Long background task --model sonnet-4.6 use --cloud instead of -p

Headless Commands

Read-only first — always start with --mode=ask to review before applying changes:

cd \x3Crepo> && agent -p "\x3Ctask>" --model sonnet-4.6 --mode=ask --output-format text --trust

Apply changes — only after user confirms the plan:

cd \x3Crepo> && agent -p "\x3Ctask>" --model sonnet-4.6 --force --output-format text --trust

Cloud/background — warn user that repo data goes to cursor.com:

cd \x3Crepo> && agent -c "\x3Ctask>" --model sonnet-4.6 --trust
# Monitor at: cursor.com/agents

Git Rule

Cursor sandbox blocks git commit. Always commit manually after Cursor edits:

cd \x3Crepo> && git add -A && git commit -m "\x3Cconventional commit message>" && git push

Show the diff to the user and confirm before committing if the change is large or touches sensitive areas.

Repos & Workdirs

  • Always cd to the correct repo before running
  • Check for .cursor/rules and AGENTS.md in the repo root — Cursor loads these automatically for project context

Context & Sessions

  • Add @\x3Cfile> in prompt to include specific files in context
  • --continue or --resume to continue a previous session
  • agent ls to list previous sessions

Output Handling

  • --output-format text → clean final answer, summarise key changes to the user
  • --output-format json → structured, use for scripted parsing
  • Always report back: what changed, what was committed, any issues found

References

  • Model list & details: references/models.md
  • Slash commands (interactive mode): references/slash-commands.md
安全使用建议
This skill is a wrapper for the Cursor 'agent' CLI and the included script defaults to read-only, which is appropriate. However: (1) the SKILL.md insists it must not be run autonomously, but the skill metadata allows autonomous invocation — confirm the platform will not call it without explicit user approval. (2) The registry metadata omitted the 'agent' binary requirement — ensure you have the official Cursor CLI installed from cursor.com before using. (3) The script can run in a 'write' mode and uses flags (--force, --trust) that apply changes; the script does not itself prompt for confirmation, so only invoke 'write' after you (or your agent platform) gets explicit user consent. (4) Be cautious with any '--cloud' mode: it will send repo contents to cursor.com — do not use for sensitive/private repos unless you accept that. If you need this skill, request the publisher update metadata to declare the 'agent' binary requirement and to mark the skill as non-autonomous (or ensure the platform enforces the SKILL.md consent rules) before installing.
功能分析
Type: OpenClaw Skill Name: cursor-agent-openclaw Version: 1.0.2 The skill provides an interface to the Cursor Agent CLI, which possesses high-risk capabilities including arbitrary file modification and shell execution. While the documentation in SKILL.md emphasizes user consent and read-only defaults, the implementation in scripts/run.sh utilizes the --trust and --force flags, which bypasses internal CLI safety prompts. The presence of future-dated model versions (e.g., sonnet-4.6, gpt-5.3) in references/models.md is unusual, though no clear evidence of intentional malice or data exfiltration was found.
能力评估
Purpose & Capability
The SKILL.md and scripts clearly require the 'agent' CLI (Cursor Agent). However the registry 'Requirements' section in the provided metadata lists no required binaries or credentials, which is inconsistent. Requiring the Cursor CLI is reasonable for the stated purpose, but the metadata omission is a mismatch that could hide setup or permission expectations.
Instruction Scope
The SKILL.md imposes strict user-consent rules (MUST NOT be invoked autonomously, always start read-only, ask before write/cloud/commit). The included run.sh implements read/ask/plan/write modes and defaults to read-only, which aligns in spirit, but the script itself does not enforce interactive confirmation — it trusts the caller to pass 'write' only after confirmation. That puts the burden on the platform/agent to follow the SKILL.md rules; the skill does not technically enforce them.
Install Mechanism
There is no install spec (instruction-only plus a small helper script). Nothing is downloaded or executed from remote URLs. This is low install risk.
Credentials
The skill does not request environment variables, secrets, or config paths. It only invokes a local CLI and operates on a user-supplied repo path, which is proportionate to the claimed purpose.
Persistence & Privilege
The skill metadata allows autonomous invocation (disable-model-invocation is false) while the SKILL.md explicitly states the skill MUST NOT be invoked autonomously and requires explicit user consent before any write/cloud/commit actions. This mismatch is the main privilege/behavior concern. 'always' is false, so it won't be force-included, but the ability for the agent to call it autonomously contradicts the documented safety constraints.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install cursor-agent-openclaw
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /cursor-agent-openclaw 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.2
v1.0.2: run.sh defaults to read-only (ask) mode — mode=write required to apply changes; binary check on startup; mandatory user-consent protocol strengthened; binary declaration in metadata.
v1.0.1
v1.0.1: Remove curl|bash install pattern; add explicit user consent step before --force; warn on --cloud data flow to cursor.com; default to read-only (ask) mode first.
v1.0.0
OpenClaw-specific Cursor Agent CLI integration. Headless coding via Cursor subscription with smart model routing (Sonnet for code, Opus+thinking for planning). Zero API cost. Uses --print + --trust for reliable headless execution — no tmux needed.
元数据
Slug cursor-agent-openclaw
版本 1.0.2
许可证
累计安装 0
当前安装数 0
历史版本数 3
常见问题

Cursor Agent for OpenClaw 是什么?

Run Cursor Agent CLI for coding tasks — writing, editing, refactoring, reviewing, or planning code — without spending OpenClaw API credits. Use when the user... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 404 次。

如何安装 Cursor Agent for OpenClaw?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install cursor-agent-openclaw」即可一键安装,无需额外配置。

Cursor Agent for OpenClaw 是免费的吗?

是的,Cursor Agent for OpenClaw 完全免费(开源免费),可自由下载、安装和使用。

Cursor Agent for OpenClaw 支持哪些平台?

Cursor Agent for OpenClaw 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Cursor Agent for OpenClaw?

由 Luis Albinati(@albinati)开发并维护,当前版本 v1.0.2。

💬 留言讨论