disaster-recovery-plan

disaster-recovery-plan is a skill for Claude Code from fattain-naime/engineering-docs. It costs 84 tokens per session (4,666 once invoked), scanned A, original, MIT.

A plan for restoring important systems after events such as infrastructure loss, data corruption, ransomware, or regional outages. It defines RTO, the maximum acceptable downtime, and RPO, the maximum acceptable data loss.

In plain words
What is it for?
Use it before launching systems that hold critical or financial data to define backups, replication, failover, recovery tiers, and restoration drills.
Why use it?
It turns vague backup arrangements into tested recovery procedures with clear limits for downtime and lost data.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the AskUserQuestion tool; mentions Claude Code; mentions Codex.

Part of the engineering-docs plugin — 22 skills, 4 agents, 1 hook, 1 MCP server shipped together

Good fit Use it before launching systems that hold critical or financial data to define backups, replication, failover, recovery tiers, and restoration drills.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fattain-naime/engineering-docs/disaster-recovery-plan
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 fattain-naime/engineering-docs --skill disaster-recovery-plan
Clone the repo
git clone --depth 1 https://github.com/fattain-naime/engineering-docs

Made for: Claude Code.

Or install engineering-docs, the plugin that ships this one along with the rest of its 22 skills, 4 agents, 1 hook, 1 MCP server.

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 disaster-recovery-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/fattain-naime/engineering-docs/disaster-recovery-plan.svg)](https://agentmods.dev/skills/fattain-naime/engineering-docs/disaster-recovery-plan)
Your own site
<a href="https://agentmods.dev/skills/fattain-naime/engineering-docs/disaster-recovery-plan"><img src="https://agentmods.dev/badge/skills/fattain-naime/engineering-docs/disaster-recovery-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,666 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 70
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00084 $0.04666
Opus 5 $0.00042 $0.02333
Sonnet 5 $0.00017 $0.00933
Haiku 4.5 $0.00008 $0.00467

Measured 8d ago against content hash d328001d02e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

disaster-recovery-plan scanned grade A with 0 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 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/disaster-recovery-plan/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Produce a disaster recovery (DR) and business continuity plan that defines, per system, how much downtime (RTO) and data loss (RPO) is tolerable, and the concrete backup, replication, and failover procedure required to stay within those limits when the primary environment is lost entirely.

A backup that has never been restored is not a backup - it is an unverified assumption. This skill treats the recovery drill, not the document, as the real proof the plan works.

Input

Works best with: The name of the system or service, and what infrastructure it currently runs on. Also valuable: Current backup tooling and frequency, any prior outage or data-loss history, compliance obligations (PCI-DSS, SOC 2), and the business cost of downtime or data loss for this system.

Example invocation: Write a DR plan for our production system. We run on a single VPS with MySQL, daily automated backups to object storage, no secondary region, and no replica database. Extended downtime and data loss are both expensive for us, but we've never tested a full restore.

Key Concepts

RTO vs RPO

  • RTO (Recovery Time Objective): The maximum acceptable time the system can be down before the business impact becomes unacceptable. Answers "how long can we be down?"
  • RPO (Recovery Point Objective): The maximum acceptable amount of data loss, measured in time. Answers "how much data can we afford to lose?" An RPO of 1 hour means backups/replication must run at least hourly.
  • These are business decisions with a cost curve attached - lower RTO/RPO requires more expensive infrastructure (replicas, multi-region, continuous backup).

DR Tiers (Cost vs. Recovery Speed Trade-off)

Tier Strategy Typical RTO Typical RPO Cost
Tier 0 Backup only, manual restore Hours to days Hours (backup interval) Lowest
Tier 1 Backup + documented restore procedure, tested Hours Backup interval Low
Tier 2 Warm standby (replica, not serving traffic) Minutes to 1 hour Near-zero to minutes Medium
Tier 3 Hot standby / active-active (multi-region) Seconds to minutes Near-zero High

Read the full file on GitHub · 278 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 278 lines · 84 tokens per session scan A d328001d02e2

Subscribe to this mod's changes

disaster-recovery-plan is a skill published in the GitHub repository fattain-naime/engineering-docs (6 stars, last pushed 3d ago), licensed MIT. It adds 84 tokens to every session and 4,666 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.