Files
everything-claude-code/skills/safety-guard/SKILL.md
Affaan Mustafa df4f2df297 feat: add 6 gap-closing skills — browser QA, design system, product lens, canary watch, benchmark, safety guard
Closes competitive gaps with gstack:
- browser-qa: automated visual testing via browser MCP
- design-system: generate, audit, and detect AI slop in UI
- product-lens: product diagnostic, founder review, feature prioritization
- canary-watch: post-deploy monitoring with alert thresholds
- benchmark: performance baseline and regression detection
- safety-guard: prevent destructive operations in autonomous sessions
2026-03-23 04:31:17 -07:00

70 lines
1.7 KiB
Markdown

# Safety Guard — Prevent Destructive Operations
## When to Use
- When working on production systems
- When agents are running autonomously (full-auto mode)
- When you want to restrict edits to a specific directory
- During sensitive operations (migrations, deploys, data changes)
## How It Works
Three modes of protection:
### Mode 1: Careful Mode
Intercepts destructive commands before execution and warns:
```
Watched patterns:
- rm -rf (especially /, ~, or project root)
- git push --force
- git reset --hard
- git checkout . (discard all changes)
- DROP TABLE / DROP DATABASE
- docker system prune
- kubectl delete
- chmod 777
- sudo rm
- npm publish (accidental publishes)
- Any command with --no-verify
```
When detected: shows what the command does, asks for confirmation, suggests safer alternative.
### Mode 2: Freeze Mode
Locks file edits to a specific directory tree:
```
/safety-guard freeze src/components/
```
Any Write/Edit outside `src/components/` is blocked with an explanation. Useful when you want an agent to focus on one area without touching unrelated code.
### Mode 3: Guard Mode (Careful + Freeze combined)
Both protections active. Maximum safety for autonomous agents.
```
/safety-guard guard --dir src/api/ --allow-read-all
```
Agents can read anything but only write to `src/api/`. Destructive commands are blocked everywhere.
### Unlock
```
/safety-guard off
```
## Implementation
Uses PreToolUse hooks to intercept Bash, Write, Edit, and MultiEdit tool calls. Checks the command/path against the active rules before allowing execution.
## Integration
- Enable by default for `codex -a never` sessions
- Pair with observability risk scoring in ECC 2.0
- Logs all blocked actions to `~/.claude/safety-guard.log`