destructive-operation-guard

destructive-operation-guard is a skill for Claude Code from latestaiagents/agent-skills. It costs 74 tokens per session (2,186 once invoked), scanned C, original, MIT.

A general safety guard for irreversible operations involving files, databases, migrations, Git, and production systems. It requires explicit confirmation before actions that delete, overwrite, reset, or affect other people's data.

In plain words
What is it for?
Use it as a broad safeguard for destructive file, database, migration, Git, and production operations.
Why use it?
It prevents an agent from carrying out a destructive action without the user's approval. This adds a confirmation step before changes that may be difficult to undo.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the safety plugin — 5 skills shipped together , and of ai-safety-guardrails, latestaiagents

Good fit Use it as a broad safeguard for destructive file, database, migration, Git, and production operations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/latestaiagents/agent-skills/destructive-operation-guard
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add latestaiagents/agent-skills --skill destructive-operation-guard
Clone the repo
git clone --depth 1 https://github.com/latestaiagents/agent-skills

Made for: Claude Code.

Or install safety, the plugin that ships this one along with the rest of its 5 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for destructive-operation-guard

README.md
[![agentmods](https://agentmods.dev/badge/skills/latestaiagents/agent-skills/destructive-operation-guard/github.svg)](https://agentmods.dev/skills/latestaiagents/agent-skills/destructive-operation-guard)
Your own site
<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/destructive-operation-guard"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/destructive-operation-guard/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for destructive-operation-guard

Your own site · 80×15
<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/destructive-operation-guard"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/destructive-operation-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,186 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00074 $0.02186
Opus 5 $0.00037 $0.01093
Sonnet 5 $0.00015 $0.00437
Haiku 4.5 $0.00007 $0.00219

Measured 8d ago against content hash ca850e5bbb7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

destructive-operation-guard scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- [ ] `rm -rf` on any directory
skills/safety/ai-safety-guardrails/destructive-operation-guard/SKILL.md · 326 lines

How it starts

The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Destructive Operation Guard

CRITICAL: This skill defines mandatory safety protocols for AI agents.

Core Principle

NEVER execute a destructive operation without EXPLICIT user confirmation.

"Destructive" means any operation that:

  • Deletes data
  • Overwrites existing data
  • Resets state
  • Cannot be easily undone
  • Affects production systems
  • Modifies data belonging to others

Destructive Operations Checklist

ALWAYS ASK BEFORE:

Database Operations
  • DROP TABLE, DROP DATABASE
  • TRUNCATE TABLE
  • DELETE without specific WHERE clause
  • DELETE affecting more than 10 rows
  • UPDATE without specific WHERE clause
  • UPDATE affecting more than 10 rows
  • Running migrations on production
  • Running migrations that delete columns/tables
  • Seeding that overwrites existing data
  • Any --force flag on database commands
File System Operations
  • rm -rf on any directory
  • rm on multiple files
  • Overwriting existing files
  • Moving files that might overwrite destinations
  • Clearing directories
  • Any recursive delete operation
Git Operations
  • git push --force or git push -f
  • git reset --hard
  • git clean -fd
  • git checkout . (discards all changes)
  • git stash drop
  • git branch -D (force delete)
  • git rebase on shared branches
  • Amending pushed commits
Deployment Operations
  • Deploying to production
  • Rolling back deployments
  • Scaling down to zero
  • Deleting cloud resources
  • Modifying environment variables in production
API/Service Operations
  • Calling DELETE endpoints
  • Bulk update operations
  • Cache invalidation (full flush)
  • Queue purging
  • Session/token invalidation for all users

Mandatory Confirmation Protocol

Step 1: Identify the Risk

Before ANY potentially destructive operation, assess:

## Risk Assessment

**Operation:** [What you're about to do]
**Scope:** [What will be affected]
**Reversibility:** [Can this be undone? How?]
**Data at Risk:** [What data could be lost]
**Affected Users:** [Who will be impacted]

Read the full file on GitHub · 326 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 326 lines · 74 tokens per session scan C ca850e5bbb7a

Subscribe to this mod's changes

destructive-operation-guard is a skill published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 74 tokens to every session and 2,186 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.