Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add basher83/lunar-claude/plugin install omni-scaleWrote 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/commands/basher83/lunar-claude/disaster-recovery)<a href="https://agentmods.dev/commands/basher83/lunar-claude/disaster-recovery"><img src="https://agentmods.dev/badge/commands/basher83/lunar-claude/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/commands/basher83/lunar-claude/disaster-recovery"><img src="https://agentmods.dev/badge/commands/basher83/lunar-claude/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 | $0.00011 | $0.01134 |
| Opus 5 | $0.00005 | $0.00567 |
| Sonnet 5 | $0.00002 | $0.00227 |
| Haiku 4.5 | $0.00001 | $0.00113 |
Grade A, and why
disaster-recovery 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 7d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Disaster Recovery
Full cluster destruction and recreation from declarative specs.
WARNING: This destroys the entire cluster. Only run for DR drills or actual recovery.
NOTE: Cluster spec path hardcoded to ~/dev/infra-as-code/Omni-Scale/clusters/talos-prod-01.yaml.
Pre-flight Gate
STOP if omni-talos skill is not loaded.
Check: Do you have knowledge of provider-ctl.py and the provider operations table? If not, instruct user:
Required setup not complete. Run this chain first:
/omni-scale:omni-prime && /omni-scale:status && /omni-scale:omni-talos
Then re-run /omni-scale:disaster-recovery
Instructions
Phase 1: Confirm Intent
Use AskUserQuestion to confirm destruction of talos-prod-01 and all workloads. If user aborts, stop immediately.
Phase 2: Destroy Cluster
Outcome: Cluster deleted, no talos VMs remain on Proxmox.
Pre-step: Restart provider via ${CLAUDE_PLUGIN_ROOT}/skills/omni-talos/scripts/provider-ctl.py --restart to ensure it's listening before destruction.
Delete cluster using omnictl cluster template delete with --destroy-disconnected-machines flag. Cluster spec at ~/dev/infra-as-code/Omni-Scale/clusters/talos-prod-01.yaml.
Poll: Verify no machines remain via omnictl.
- Max wait: 10 min
- After 3 attempts, increase interval to 60s
- On timeout: consult omni-talos
references/debugging.md
Confirm destruction complete with user before proceeding.
Phase 3: Recreate Cluster
Outcome: Cluster recreated, all nodes reach running state.
Apply cluster template using omnictl cluster template sync.
Poll: Check machine status via omnictl with cluster label selector.
- Max wait: 20 min
- After 3 attempts, increase interval to 60s
- On timeout: consult omni-talos
references/debugging.md
IMPORTANT: Machines showing READY: false is normal during bootstrap. This can persist
for 10+ minutes while etcd forms quorum and Talos configures. Do NOT attempt to troubleshoot
infrastructure (SSH, logs) — just wait. Only escalate if max wait exceeded.
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.
- 7d ago First seen · 134 lines · 11 tokens per session scan A dddf2a5c03e8
disaster-recovery is a command published in the GitHub repository basher83/lunar-claude (23 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 1,134 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
cost-optimize
You are a cloud cost optimization expert specializing in reducing infrastructure expenses while maintaining performance and reliability. Analyze cloud spending, identify savings opportunities, and implement cost-effective architectures across AWS, Azure, GCP, and OCI. Where provider-specific code appears below, adapt…
deploy
Deploy a frontend (React, Next.js, or static HTML) to a live URL on Butterbase.
integrate
Set up third-party service integrations.
env
Manage Vercel environment variables. Commands include list, pull, add, remove, and diff. Use to sync environment variables between Vercel and your local development environment.
scan
Scan AWS account for cost optimization.
finops-feedback
Step 5 (Feedback Loop & Celebration) — measure realized against projected savings, compute a labelled Cloud Entropy proxy, close the opportunity, and emit at least one new idea or policy update so the loop actually closes. Applies the double-loop gate. Mutates on the closure path.