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 fattain-naime/engineering-docs --skill disaster-recovery-plangit clone --depth 1 https://github.com/fattain-naime/engineering-docsWrote 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/fattain-naime/engineering-docs/disaster-recovery-plan)<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>- NVIDIA SkillSpector warn
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.
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 | $0.00084 | $0.04666 |
| Opus 5 | $0.00042 | $0.02333 |
| Sonnet 5 | $0.00017 | $0.00933 |
| Haiku 4.5 | $0.00008 | $0.00467 |
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.
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 |
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.
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.
- 8d ago First seen · 278 lines · 84 tokens per session scan A d328001d02e2
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.
Other skills, from other repositories
companion-clis
Companion CLIs for Runpod workflows — HuggingFace, GitHub, Docker, and AWS.
cloud-deployment-routing-workflow
Choose a cloud deployment path before implementation. Route AWS work to the official AWS Agent Toolkit and Azure work to Microsoft's Azure Skills plugin while keeping credentials, regions, and mutation boundaries explicit.
macos-distribution-workflow
Inspect, prepare, validate, and troubleshoot exported macOS distribution artifacts. Use when checking signing identities, entitlements, hardened runtime, nested code, Gatekeeper, notarization readiness/results, stapling, or distribution-only launch failures.
prepare-isolated-analysis-lab
Prepare a verified disposable Linux or macOS analysis lab from an approved isolation decision. Use before active research to control host integration, networking, baseline, monitoring, evidence export, reset, and teardown.
flash
Write code locally, iterate with flash dev — it runs your functions on remote Runpod GPUs/CPUs with hot-reload and live worker logs — then flash deploy to ship. Endpoint handles provisioning.
runpodctl
Runpod CLI to manage your GPU workloads.