Install
$ agentstack add skill-winterddo-claude-code-skill-autopilot-config ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Autopilot settings
Map the user's request to one command, run it, read the value back, confirm in one line.
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/config.py" "$HOME/.claude/command-autopilot" get
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/config.py" "$HOME/.claude/command-autopilot" set
| User intent | Setting | |---|---| | "太烦了 / too noisy / stop suggesting" | set aggressiveness quiet (silent help + /rewind safety only) | | "完全闭嘴 / mute it" | set muted true (zero injection, zero tokens) | | "把提示打开 / teach me again" | set aggressiveness teaching | | "正常模式" | set aggressiveness normal | | "中文提示 / English guidance" | set language zh / set language en | | "别自动进计划模式" | set enable_plan_gate false |
Always mention: changes take effect from the next message, no restart needed. If the user muted it, tell them the one phrase that brings it back ("unmute autopilot").
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: WinterDDo
- Source: WinterDDo/claude-code-skill-autopilot
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.