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 dryvist/claude-code-plugins --skill workstation-offbox-backupgit clone --depth 1 https://github.com/dryvist/claude-code-pluginsWrote 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/dryvist/claude-code-plugins/workstation-offbox-backup)<a href="https://agentmods.dev/skills/dryvist/claude-code-plugins/workstation-offbox-backup"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/workstation-offbox-backup/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/dryvist/claude-code-plugins/workstation-offbox-backup"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/workstation-offbox-backup.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 | $0.00060 | $0.00963 |
| Opus 5.5 | $0.00024 | $0.00385 |
| Sonnet 5.5 | $0.00012 | $0.00193 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade A, and why
workstation-offbox-backup 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 27d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workstation data → off-box backup pattern
A workstation app that continuously records data (activity trackers, recorders, local-first tools with a growing SQLite file) tends to grow an ever-larger local database plus a pile of bulk media. Left alone it bloats the machine and slows the app's own queries. The goal: keep the local store small and fast, never lose history, and keep old data directly accessible without a restore round-trip.
The trick is to split by what the data is for, and lean on infrastructure you already run rather than writing a custom uploader.
The split: searchable text vs. bulk bytes
| Data | Destination | Why |
|---|---|---|
| Searchable text (anything you'd query) | A log/search platform you already run | Indexed and retained centrally — far more searchable than a local file, and it doubles as the backup |
| Bulk media (large binary files) | Durable, snapshotted storage | Heavy, not searchable — just needs point-in-time copies |
Once a row's text is indexed centrally and its media is on durable storage, the local row is disposable — that's what makes aggressive local pruning safe.
Text → search platform (pull, don't push)
Most apps have no native log-forwarding sink. Rather than script an exporter, pull with a collector you already run against the app's local API or database on a schedule. Use a short collection window with a small overlap, and de-duplicate on the row's monotonic id — if rows are immutable, overlap plus dedup means no gaps and no duplicates, with no cursor state to maintain by hand.
If the app exposes only a local database file and no API, a filesystem/database-native collector is the equivalent pull — still declarative collector config, not a maintained script.
Bulk media → durable storage
Push media off-box with the app's own native sync if it has one (e.g. SFTP
to an existing host), otherwise a scheduled rsync. Land it on storage
that's already snapshotted and replicated — you inherit point-in-time
history and off-node durability for free instead of building your own. Run
the sync on a timer that fires on wake, so a machine that sleeps overnight
simply catches up the next time it's awake.
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.
- 27d ago Changed · -40 tokens per session ee803098956e
- 1mo ago First seen · 92 lines · 100 tokens per session scan A 422d22613043
workstation-offbox-backup is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 60 tokens to every session and 963 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
data-tier-cutover
The stateful-tier migration PROCEDURE skill — cut an app's SQL database + cache over from self-managed instances to a managed serverless target. A read-only procedure the generic agent runs alongside the id- infra-delivery steps: it drives the fail-closed cutover-mechanism DECISION TREE (snapshot-restore vs…
redis-patterns
Apply production Redis patterns including caching strategies, rate limiting, distributed locks, pub/sub, streams, and memory optimization with TypeScript and Go examples.
redis-state-management
Comprehensive guide for Redis state management including caching strategies, session management, pub/sub patterns, distributed locks, and data structures.
cache
Design caching strategies with Redis.
pinecone
Managed vector DB for production RAG and search.
google-cloud-storage-fuse
Mounts Cloud Storage buckets on Google Cloud as a POSIX file system using Cloud Storage FUSE (and the gcsfuse CLI tool). Use when interacting with the gcsfuse CLI or Cloud Storage FUSE mounts: decide whether FUSE, native gs:// reads, or Filestore/Managed Lustre fits a workload, deploy tuned mounts on GKE, Compute…