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/replicate)<a href="https://agentmods.dev/commands/benbjohnson/litestream-skills/replicate"><img src="https://agentmods.dev/badge/commands/benbjohnson/litestream-skills/replicate/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/replicate"><img src="https://agentmods.dev/badge/commands/benbjohnson/litestream-skills/replicate.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 | $0.00962 |
| Opus 5.5 | $0.00000 | $0.00385 |
| Sonnet 5.5 | $0.00000 | $0.00192 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
replicate 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
replicate Command
Continuously replicate SQLite databases to cloud storage.
Synopsis
# With config file
litestream replicate [-config PATH]
# With command line arguments
litestream replicate [flags] DB_PATH REPLICA_URL [REPLICA_URL...]
# Run application alongside replication
litestream replicate -exec "myapp serve"
Description
The replicate command is the main Litestream daemon. It:
- Opens configured SQLite databases
- Monitors the WAL for changes
- Converts changes to LTX format
- Uploads to configured storage backends
- Manages checkpoints and compaction
Flags
| Flag | Description |
|---|---|
-config PATH |
Configuration file path (default: /etc/litestream.yml) |
-no-expand-env |
Disable environment variable expansion |
-exec COMMAND |
Run command as subprocess (shutdown when it exits) |
-restore-if-db-not-exists |
Restore from replica if database doesn't exist |
-once |
Replicate once and exit |
-force-snapshot |
Force snapshot creation (requires -once) |
-enforce-retention |
Enforce snapshot retention (requires -once) |
Examples
Using Config File
# Use default config location
litestream replicate
# Specify config file
litestream replicate -config /path/to/litestream.yml
Command Line Arguments
# Single replica
litestream replicate /data/app.db s3://bucket/backup
# Multiple replicas (deprecated: use config file)
litestream replicate /data/app.db s3://bucket/backup sftp://user@host/backup
Run Application Subprocess
# Via command line
litestream replicate -exec "myapp serve --port 8080"
# Via config file
# exec: "myapp serve --port 8080"
Litestream will:
- Start replication
- Execute the command
- Shut down gracefully when command exits
Auto-Restore on Startup
litestream replicate -restore-if-db-not-exists
If the database doesn't exist, restore it from the replica before starting replication.
One-Shot Replication
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 · 166 lines · 0 tokens per session scan A 63f37a0978fb
replicate 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 962 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.
replicate compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| replicatebenbjohnson/litestream-skills | Command | 5 | 9mo ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| pullfcakyon/claude-codex-settings | Command | 1.2k | today | Apache-2.0 | A | 0 | Claude Code |
| d1-migrationjezweb/claude-skills | Command | 1.1k | 28d ago | MIT | A | 11 | Claude Code |
| datasphere-clisecondsky/sap-skills | Command | 493 | 3d ago | GPL-3.0 | A | 12 | Claude Code |
| bootstrapbuild-with-dhiraj/ai-workflow-framework-portability-kit | Command | 5 | 1mo ago | MIT | A | 31 | Claude Code |
| vector-searchfrankxai/claude-code-oracle-skills | Command | 2 | 13d ago | Apache-2.0 | A | 9 | Claude Code |
| setup-bigquery.esminicoohei/ai-agent-camp | Command | 347 | 1mo ago | none | A | 2 | Claude Code |