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.
git clone --depth 1 https://github.com/benbjohnson/litestream-skillsWrote 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/benbjohnson/litestream-skills/restore)<a href="https://agentmods.dev/commands/benbjohnson/litestream-skills/restore"><img src="https://agentmods.dev/badge/commands/benbjohnson/litestream-skills/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/commands/benbjohnson/litestream-skills/restore"><img src="https://agentmods.dev/badge/commands/benbjohnson/litestream-skills/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 | $0.00000 | $0.01146 |
| Opus 5.5 | $0.00000 | $0.00458 |
| Sonnet 5.5 | $0.00000 | $0.00229 |
| Haiku 4.5 | $0.00000 | $0.00115 |
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 2mo 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
restore Command
Restore a SQLite database from a backup.
Synopsis
# Restore from replica URL
litestream restore -o OUTPUT_PATH REPLICA_URL
# Restore from configured database
litestream restore [-config PATH] [-o OUTPUT_PATH] DB_PATH
Description
The restore command recovers a SQLite database from LTX backup files. It can:
- Restore to the latest available state
- Restore to a specific point in time
- Restore to a specific transaction ID
- Skip restoration if database already exists
Flags
| Flag | Description |
|---|---|
-o PATH |
Output path for restored database (required with URL) |
-config PATH |
Configuration file path |
-no-expand-env |
Disable environment variable expansion |
-timestamp TIME |
Restore to specific timestamp (RFC3339 format) |
-txid TXID |
Restore to specific transaction ID |
-parallelism N |
Number of parallel downloads (default: runtime.NumCPU) |
-if-db-not-exists |
Skip if output file already exists |
-if-replica-exists |
Skip if no backup files found |
Examples
Basic Restore
# From replica URL
litestream restore -o /data/app.db s3://bucket/app-backup
# From configured database
litestream restore /data/app.db
Point-in-Time Recovery
Restore to a specific timestamp:
litestream restore -timestamp 2024-01-15T10:30:00Z -o /data/app.db s3://bucket/backup
Timestamp must be in RFC3339 format (ISO 8601 with timezone).
Restore to Transaction ID
litestream restore -txid 1000 -o /data/app.db s3://bucket/backup
Conditional Restore
# Only restore if database doesn't exist
litestream restore -if-db-not-exists -o /data/app.db s3://bucket/backup
# Skip silently if no backups available
litestream restore -if-replica-exists -o /data/app.db s3://bucket/backup
Parallel Downloads
Speed up large restores:
litestream restore -parallelism 8 -o /data/app.db s3://bucket/backup
Restore Process
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.
- 2mo ago First seen · 189 lines · 0 tokens per session scan A de52554c6379
restore is a command published in the GitHub repository benbjohnson/litestream-skills (5 stars, last pushed 9mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,146 tokens. 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.
restore compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| restorebenbjohnson/litestream-skills | Command | 5 | 9mo ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| initfcakyon/claude-codex-settings | Command | 1.2k | today | Apache-2.0 | A | 0 | Claude Code |
| securityajitpratap0/GoSQLX | Command | 124 | 3d ago | Apache-2.0 | A | 21 | Claude Code |
| database-setupimsaif/design-with-claude | Command | 11 | 2d ago | MIT | A | 36 | Claude Code |
| new-migrationRaNDoM6913/claude-code-superkit | Command | 3 | today | MIT | A | 22 | Claude Code |
| json.batch_getstratalab/strata-core | Command | 5 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| json.index.dropstratalab/strata-core | Command | 5 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |