安全编辑 edit_script search_and_replace validate_scripts 确认令牌 remove_node headless 改盘 editor 覆盖 沙箱 防误用 CRLF tab 缩进 —— 当你编辑 .gd/.tscn、删节点或执行危险操作时使用
Scanned 9/13/2026
Install to Claude Code
npx -y skills add wgt19861219/godot-mcp-enhanced --skill godot-mcp-safe-edit --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Godot Mcp Safe Edit?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/wgt19861219-godot-mcp-safe-edit-godot-mcp-enhanced)More formats (shields.io, HTML) on the badges page.
---
name: godot-mcp-safe-edit
description: "安全编辑 edit_script search_and_replace validate_scripts 确认令牌 remove_node headless 改盘 editor 覆盖 沙箱 防误用 CRLF tab 缩进 —— 当你编辑 .gd/.tscn、删节点或执行危险操作时使用"
---
## 安全编辑流
编辑 `.gd`/`.tscn`、删节点、运行危险操作时的防护 checklist。工具细节见 `godot-mcp-core.md` 与 `godot-mcp-editor.md`。
**何时用**:编辑 `.gd`/`.tscn`、删节点、执行危险操作时。
**checklist**:
- [ ] 1. `edit_script` **优先 search_and_replace**(内容匹配、行号偏移鲁棒、CRLF 安全、免确认 token);**禁用内置 Edit 工具改 .gd**(tab 缩进匹配率极低)
- [ ] 2. 改 `.gd` 后必跑 `validate_scripts`(验证语法)
- [ ] 3. headless 改盘 + editor 开同场景 → Ctrl+S 覆盖风险:建议 editor 内 Reload 场景或关闭该场景后再操作
- [ ] 4. 危险操作(`remove_node` 等)需显式确认令牌
- [ ] 5. GDScript 沙箱是**防误用层非防对抗**(间接构造可绕过;真正隔离须容器/VM + `GODOT_MCP_ALLOW_UNSAFE=false`)
- [ ] 6. `write_script`/`edit_script` 写 .gd 前也走沙箱扫描(与 `execute_gdscript` 同威胁面,发现已知危险 API 模式(含 @tool 加载即执行等,清单不列举防被侦察)阻断 SANDBOX_VIOLATION;双 opt-in 旁路 `UNRESTRICTED + DISABLE_SAFETY`)
**常见偏离**:
- 用内置 Edit 工具改 `.gd`(tab 缩进失败)
- 改完不 validate
- headless 改盘后被 editor 旧版本 Ctrl+S 覆盖(MCP 不可控,须 Reload)
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling