Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/davekilleen/Dexnpx agentmods add skills/davekilleen/dex/backup-restoreWrote 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/davekilleen/dex/backup-restore)<a href="https://agentmods.dev/skills/davekilleen/dex/backup-restore"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/backup-restore/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/davekilleen/dex/backup-restore"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/backup-restore.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 | $0.00076 | $0.00659 |
| Opus 5.5 | $0.00030 | $0.00264 |
| Sonnet 5.5 | $0.00015 | $0.00132 |
| Haiku 4.5 | $0.00008 | $0.00066 |
Grade A, and why
backup-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 1mo 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backup Restore
Three jobs, in increasing weight: prove a backup is intact, prove it actually restores, and bring one back. All three are driven by one tool, and none of them will ever overwrite the live vault: a restore always goes to a fresh folder the user chooses, to inspect and move into place themselves.
Test mode (the one to suggest routinely)
python3 core/backup/restore_vault.py test
This checks the newest set's fingerprints, verifies the version-history bundle with git's own verifier, extracts the whole archive into a throwaway temporary folder, counts what came out, and deletes the extraction. It proves a restore works without touching anything. Suggest running it once after setup and occasionally after that; a backup that has never been test-restored is a hope, not a backup.
Verify only (quick integrity check)
python3 core/backup/restore_vault.py verify
Fingerprint and history checks only, no extraction. Add --set <stamp> for a specific older set, or --source /path for a folder other than the configured destination.
Restore for real
First ask which set they want (default is the newest) and where the restored copy should go. The target must be a new or empty folder.
python3 core/backup/restore_vault.py restore --to /path/to/fresh-folder
Then be explicit about three things:
- The live vault was not touched. The restored copy sits in the folder they chose. Comparing, cherry-picking files, or swapping the whole vault over is their deliberate next step, not something this tool does behind their back.
- The version history comes back separately. The history bundle is copied alongside;
git clone dex-vault-<stamp>.bundle restored-historyrecovers it. - Secrets and schedules are not in the backup, on purpose. API keys, the scheduled backup job itself, and macOS permissions all need re-establishing. Walk them through
docs/backup-restore.mdfor the full list.
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.
- 1mo ago First seen · 49 lines · 76 tokens per session scan A fa9d97328db8
backup-restore is a skill published in the GitHub repository davekilleen/Dex (507 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 659 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-02.
Other skills, from other repositories
meeting-notes
Use when the user asks to capture, structure, or summarize meeting notes / call notes / 1:1 discussion / standup notes. Produces a standard template with attendees, agenda, decisions, action items (owner + deadline), and open questions.
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
schedule
Reminders, automations, and recurring page, dashboard, or status monitoring (cron, RRULE, or fire-at).
inbox-cleanup
Run a high-recall, multi-pass email inbox cleanup. Pattern-based subject queries catch 25x more archivable email than sender scans alone. Includes urgency triage, classification signals, and post-cleanup filter setup.
inbox-management
Ongoing Gmail inbox management via scheduled runs. Archives known noise, flags urgent items, drafts replies in-thread (never auto-sends), and catches stale follow-ups. Empty polls spend no model tokens. Starts in flag-only mode.
notifications
Send notifications through the unified notification router.