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 agentmods add commands/dberuben/claude-code-backup/restoregit clone --depth 1 https://github.com/dberuben/claude-code-backupWhat 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 | $0.00013 | $0.00354 |
| Opus 5 | $0.00006 | $0.00177 |
| Sonnet 5 | $0.00003 | $0.00071 |
| Haiku 4.5 | $0.00001 | $0.00035 |
Grade A, and why
restore 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 yesterday.
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.
What it actually says
You are running the claude-restore CLI. Restore is destructive, so behave
conservatively. Never pass --force on your own.
The user's arguments are: $ARGUMENTS
Map each space-separated keyword to a flag (ignore unknown words):
| keyword | flag |
|---|---|
dry-run |
--dry-run |
home-only |
--home-only |
project-only |
--project-only |
Procedure:
- First run
claude-restore --dry-run(plus any home-only/project-only flag) to show the restore plan. - Show the plan to the user and ask them to confirm in chat.
- Only after the user explicitly confirms, re-run with
--forceadded so the restore can proceed non-interactively, keeping the pre-restore backup enabled (the default).
Examples:
/restore→ show the dry-run plan, then on confirmation runclaude-restore --force/restore dry-run→ justclaude-restore --dry-run(never escalate)/restore project-only→claude-restore --dry-run --project-only, then on confirmationclaude-restore --project-only --force
Remind the user that some credentials (Keychain, OAuth, env vars) may require re-authentication after restore.
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.
- yesterday First seen · 39 lines · 13 tokens per session scan A 3112e06b3b88
restore is a command published in the GitHub repository dberuben/claude-code-backup (2 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 354 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 2026-08-31.
Other commands, from other repositories
seo-drift
Compare two SEO snapshots (GSC / GSC AI Performance / rank tracker / AEO probe) and surface top movers per metric with auto-classification — growth / decline / reshuffle / stable / new / lost.
brand-setup
Configure a new brand profile with colors, fonts, logo, visual style, platforms, and compliance rules.
save
Save this conversation as a new or existing reusable context.
ros-first-dollar
Step-by-step playbook to get your first paying customer.
screens
Structures product UX screen design — inventory, flow, states, and reusable briefs for external design tools — without generating pixels or UI code.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.