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.
npx skills add GoldenWing-360/claude-security-skills --skill backup-disaster-recoverygit clone --depth 1 https://github.com/GoldenWing-360/claude-security-skillsWrote 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.
[](https://agentmods.dev/skills/goldenwing-360/claude-security-skills/backup-disaster-recovery)<a href="https://agentmods.dev/skills/goldenwing-360/claude-security-skills/backup-disaster-recovery"><img src="https://agentmods.dev/badge/skills/goldenwing-360/claude-security-skills/backup-disaster-recovery/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.
<a href="https://agentmods.dev/skills/goldenwing-360/claude-security-skills/backup-disaster-recovery"><img src="https://agentmods.dev/badge/skills/goldenwing-360/claude-security-skills/backup-disaster-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00083 | $0.03254 |
| Opus 5 | $0.00042 | $0.01627 |
| Sonnet 5 | $0.00017 | $0.00651 |
| Haiku 4.5 | $0.00008 | $0.00325 |
Grade C, and why
backup-disaster-recovery scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| Accidental delete (DROP TABLE, rm -rf, bad migration) | Point-in-time backup, retained N days | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS -m 10 --retry 3 "$HEARTBEAT_URL" How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backups & Disaster Recovery
The line that defines a backup strategy: "a backup you have not restored is a wish, not a backup." Most teams have something called "backups" that have never been restored end-to-end. Sometimes they don't actually work; sometimes they work but are too slow; sometimes they work but the team forgot a critical piece of state and ends up with a half-restored system.
This skill builds a strategy that survives the first real incident — not the strategy that looks good in a slide deck.
Pairs with incident-response (where backups get used) and postgres-hardening / backend-architecture (where the data lives).
When to invoke
- "We have backups but nobody has ever restored them"
- Adding a new system that holds production data
- After a near-miss (almost lost data) or an actual data-loss incident
- Before a major migration, version upgrade, or refactor that touches storage
- Ransomware attack in the news that affects your stack (always periodic, treat as a prompt)
- Periodic re-audit (quarterly is reasonable)
Step 1 — Define what you're protecting against
The right strategy depends on the failure class. Backups for ransomware look different from backups for "developer dropped the table accidentally."
| Failure class | What you need |
|---|---|
| Hardware failure (disk, server) | Replica or snapshot in a different physical location |
| Accidental delete (DROP TABLE, rm -rf, bad migration) | Point-in-time backup, retained N days |
| Application bug corrupting data | Point-in-time backup + ability to surgically restore subsets |
| Ransomware encrypting everything reachable from the app | Backups the ransomware cannot reach — immutable or offline |
| Cloud-account compromise | Backups in a separate account / provider, separate credentials |
| Provider going under / region outage | Backups in a different provider / region |
| Legal hold / subpoena / SAR request | Selective archive, retention policy that complies with your jurisdiction |
| Force majeure (data center fire, country-level outage) | Off-region / off-provider backups, restore plan that does not assume continuity |
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.
- 12d ago First seen · 266 lines · 83 tokens per session scan C fde3ce9d5183
backup-disaster-recovery is a skill published in the GitHub repository GoldenWing-360/claude-security-skills (17 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 3,254 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
cloudflare-api
Hit the Cloudflare REST API directly for operations that wrangler and MCP can't handle well. Bulk DNS, custom hostnames, email routing, cache purge, WAF rules, redirect rules, zone settings, Worker routes, D1 cross-database queries, R2 bulk operations, KV bulk read/write, Vectorize queries, Queues, and fleet-wide…
hono-api-scaffolder
Scaffold Hono API routes for Cloudflare Workers. Produces route files, middleware, typed bindings, Zod validation, error handling, and APIENDPOINTS.md documentation. Use after a project is set up with cloudflare-worker-builder or vite-flare-starter, when you need to add API routes, create endpoints, or generate API…
cloudflare-worker-builder
Scaffold and deploy Cloudflare Workers with Hono routing, Vite plugin, and Static Assets. Describe project, scaffold structure, configure bindings, deploy. Use whenever the user wants to create a Worker project, set up Hono on Cloudflare, configure D1 / R2 / KV / Queues bindings, or troubleshoot Worker export syntax…
cloud-browser-automation
Use cloud browser services (Browserbase) for Cloudflare bypass, JavaScript rendering, and stealth scraping when local tools fail.
nemoclaw-setup
Install and configure NVIDIA NemoClaw (sandboxed OpenClaw agent platform) on Linux. Handles cloudflared tunnels, Docker cgroup fixes, OpenShell, sandbox creation, remote access via Cloudflare Tunnel, and known bug workarounds. Use whenever the user mentions installing NemoClaw, setting up OpenClaw, configuring an…
latchbio-integration
Build, register, debug, and operate bioinformatics workflows on Latch using the Python SDK, CLI, Latch Data and Registry, Nextflow, Snakemake, programmatic execution, and Latch MCP. Use when authoring or deploying Latch workflows, configuring resources or interfaces, moving data, integrating Registry, or launching and…