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/jmagar/claude-homelab/deploygit clone --depth 1 https://github.com/jmagar/claude-homelabWrote 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/jmagar/claude-homelab/deploy)<a href="https://agentmods.dev/commands/jmagar/claude-homelab/deploy"><img src="https://agentmods.dev/badge/commands/jmagar/claude-homelab/deploy.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.00446 |
| Opus 5 | $0.00007 | $0.00223 |
| Sonnet 5 | $0.00003 | $0.00089 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade B, and why
deploy scanned grade B with 1 finding 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 6d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
The marketplace lives at: `!cat ~/.claude/plugins/marketplaces/claude-homelab/.claude-plugin/marketplace.json 2>/dev/null || cat ~/claude-homelab/.claude-plugin/marketplace.json` What it actually says
Deploy MCP plugin servers defined in the homelab marketplace. Arguments (if provided): $ARGUMENTS
The marketplace lives at: !cat ~/.claude/plugins/marketplaces/claude-homelab/.claude-plugin/marketplace.json 2>/dev/null || cat ~/claude-homelab/.claude-plugin/marketplace.json
Instructions
-
Parse the marketplace to get the list of external plugins (those with
source.source == "github"). Extractnameandversionfor each. -
Detect docker compose variant:
docker compose version→ usedocker composedocker-compose version→ usedocker-compose- If neither found, report error and stop
-
Determine which plugins to deploy:
- If
$ARGUMENTSis a plugin name (e.g.synapse-mcp), deploy only that one - If no arguments, deploy all external plugins from the marketplace
- If
-
For each plugin to deploy:
- Find its compose file at:
~/.claude/plugins/cache/claude-homelab/<name>/<version>/docker-compose.yaml(also check.ymlvariants) - Skip
tests/subdirectory compose files - If compose file not found, warn and skip that plugin — do not stop
- Find its compose file at:
-
Run the deploy from each compose file's parent directory:
cd ~/.claude/plugins/cache/claude-homelab/<name>/<version> docker compose up --build -d -
Report results as a table:
- Plugin name | Status (✓ up / ✗ failed / ⚠ skipped) | Notes
- On any failure: show last 20 lines of that plugin's output
- At the end: run
docker compose psin each successfully deployed directory to show running containers
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.
- 6d ago First seen · 39 lines · 14 tokens per session scan B 105f76ba310d
deploy is a command published in the GitHub repository jmagar/claude-homelab (77 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 446 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
figma-style
Generate styling code from Figma designs matching the project's design system.
statusline-help
Explain the custom statusline — what every line/field means, data source, colors, and the location knob.
jira-fix
Thin entry point for /jira-fix [--dry-run] [--repo ] — parses and validates the argument shape only, then hands control to @jira-task-runner. No run logic lives here.
impact
Cross-repo impact analysis — graph-aware (Graphify) with a live ripgrep fallback.
sweep-stale-flags
Find feature flags, env vars, and config keys referenced in code but absent from env-check / settings — dead toggles that pretend to gate behaviour.
find
Find files by pattern across the project's repositories.