Safety Guard — Prevent Destructive Operations
## When to Use
Best use case
Safety Guard — Prevent Destructive Operations is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
## When to Use
Teams using Safety Guard — Prevent Destructive Operations should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/safety-guard/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Safety Guard — Prevent Destructive Operations Compares
| Feature / Agent | Safety Guard — Prevent Destructive Operations | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
## When to Use
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# 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`
Related Skills
clay-policy-guardrails
Implement credit spending limits, data privacy enforcement, and input validation guardrails for Clay pipelines. Use when enforcing spending caps, blocking PII enrichment, or adding pre-enrichment validation rules. Trigger with phrases like "clay policy", "clay guardrails", "clay spending limit", "clay data privacy rules", "clay validation", "clay controls".
clade-policy-guardrails
Implement content safety guardrails for Claude — input filtering, Use when working with policy-guardrails patterns. output validation, usage policies, and prompt injection defense. Trigger with "anthropic content policy", "claude safety", "claude guardrails", "anthropic prompt injection", "claude content filtering".
canva-policy-guardrails
Implement Canva Connect API lint rules, policy enforcement, and automated guardrails. Use when setting up code quality rules for Canva integrations, implementing pre-commit hooks, or configuring CI policy checks. Trigger with phrases like "canva policy", "canva lint", "canva guardrails", "canva best practices check", "canva eslint".
anth-policy-guardrails
Implement content policy guardrails, input/output validation, and usage governance for Claude API integrations. Trigger with phrases like "anthropic guardrails", "claude content policy", "claude input validation", "anthropic safety rules".
adobe-policy-guardrails
Implement Adobe-specific lint rules, CI policy checks, and runtime guardrails covering credential scanning (p8_ patterns), Firefly content policy pre-screening, PDF Services quota enforcement, and OAuth scope validation. Trigger with phrases like "adobe policy", "adobe lint", "adobe guardrails", "adobe eslint", "adobe content policy".
typespec-api-operations
Add GET, POST, PATCH, and DELETE operations to a TypeSpec API plugin with proper routing, parameters, and adaptive cards
graphql-operations
Guide for writing GraphQL operations (queries, mutations, fragments) following best practices. Use this skill when: (1) writing GraphQL queries or mutations, (2) organizing operations with fragments, (3) optimizing data fetching patterns, (4) setting up type generation or linting, (5) reviewing operations for efficiency.
../../../business-growth/revenue-operations/SKILL.md
No description provided.
azure-ai-contentsafety-ts
Analyze text and images for harmful content using Azure AI Content Safety (@azure-rest/ai-content-safety). Use when moderating user-generated content, detecting hate speech, violence, sexual content, or self-harm, or managing custom blocklists.
azure-ai-contentsafety-py
Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification. Triggers: "azure-ai-contentsafety", "ContentSafetyClient", "content moderation", "harmful content", "text analysis", "image analysis".
azure-ai-contentsafety-java
Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text/image analysis, blocklist management, or harm detection for hate, violence, sexual content, and self-harm.
file-header-guardian
文件头三行契约注释。触发：create file、新建文件、编写代码。