원클릭으로
원클릭으로
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.
Orchestrate building a brand-new feature end to end — research, plan, TDD implementation, review, and gated commit — by delegating each phase to the matching ECC agent. Use when adding a capability that does not exist yet.
Orchestrate bootstrapping a working MVP from a design or spec document — ingest the doc, plan thin vertical slices, scaffold the first end-to-end slice, then TDD-implement, review, and gated commit. Use to turn an SDD/PRD into a running starting point.
Orchestrate altering an existing, working feature to new desired behavior — update its tests to the new spec, change the implementation to match, review, and gated commit. Use when behavior is not broken but should be different.
Orchestrate fixing a bug — reproduce it as a failing regression test, fix to green, review, and gated commit — by delegating each phase to the matching ECC agent. Use when existing behavior is broken or wrong.
Shared orchestration engine for the orch-* skill family. Defines the gated Research-Plan-TDD-Review-Commit pipeline, the size classifier, the agent map, and the two human gates that the orch-* operation skills delegate to. Not usually invoked directly.
| name | safety-guard |
| description | 使用此技能可防止在生产系统上工作或自主运行代理时进行破坏性操作。 |
| origin | ECC |
三种保护模式:
在执行破坏性命令前进行拦截并发出警告:
已监控的模式:
- rm -rf(特别是 /、~ 或项目根目录)
- git push --force
- git reset --hard
- git checkout .(丢弃所有更改)
- DROP TABLE / DROP DATABASE
- docker system prune
- kubectl delete
- chmod 777
- sudo rm
- npm publish(意外发布)
- 任何带有 --no-verify 的命令
检测到时:显示命令功能、请求确认、建议更安全的替代方案。
将文件编辑锁定到特定目录树:
/safety-guard freeze src/components/
任何在 src/components/ 之外的写入/编辑操作都会被阻止并附带说明。适用于希望代理专注于某个区域而不触及无关代码的场景。
双重保护同时生效。为自主代理提供最高安全性。
/safety-guard guard --dir src/api/ --allow-read-all
代理可读取任何内容,但仅能写入 src/api/。破坏性命令在所有位置均被阻止。
/safety-guard off
通过 PreToolUse 钩子拦截 Bash、Write、Edit 和 MultiEdit 工具调用。在执行前根据活动规则检查命令/路径。
codex -a never 会话中启用~/.claude/safety-guard.log