Borrowing it
Nothing to install: this file belongs to rahmanef63/control-room. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rahmanef63/control-room/main/.claude/commands/vps-collector.mdgit clone --depth 1 https://github.com/rahmanef63/control-roomWrote 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/rahmanef63/control-room/vps-collector)<a href="https://agentmods.dev/commands/rahmanef63/control-room/vps-collector"><img src="https://agentmods.dev/badge/commands/rahmanef63/control-room/vps-collector.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 | $0.00000 | $0.00307 |
| Opus 5 | $0.00000 | $0.00153 |
| Sonnet 5 | $0.00000 | $0.00061 |
| Haiku 4.5 | $0.00000 | $0.00031 |
Grade A, and why
vps-collector 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 2d 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.
What it actually says
VPS Control Room — Agent Collector Pattern
Use this pattern for host telemetry/collector work under agent/.
Principles
- Collectors run in the Node 22 agent, never in the frontend.
- One collector failure must not terminate the agent or block unrelated collectors.
- Keep collection bounded in time/output and avoid unbounded process spawning.
- Prefer bounded Node/os/fs helpers; use a child process only for a specific telemetry source when necessary. Do not create a browser-callable generic exec wrapper.
- Persist shared durable state through the existing agent JSON/state layer when persistence is required.
- Never add a database dependency just to expose collector output to the UI.
Shape
export async function collectExample(): Promise<ExampleSnapshot | null> {
try {
// Gather bounded host data from a specific OS/API source.
return snapshot;
} catch (error) {
// Log a bounded diagnostic; never include secrets/environment dumps.
return null;
}
}
Frontend exposure
Expose collector results through an authenticated agent HTTP endpoint and the corresponding SvelteKit proxy route. The browser must not access privileged host interfaces directly.
Verification
- success path
- unavailable dependency/path returns a safe empty/null result
- timeout/failure does not terminate agent
- output shape remains stable
- gateway endpoint rejects unauthenticated requests
Then run:
bun run --cwd agent test:all
bun run --cwd agent build
git diff --check
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.
- 2d ago Changed · -139 lines scan B → A b3d2faa6aa93
- 8d ago First seen · 186 lines · 0 tokens per session scan B edf3ecb02804
vps-collector is a command published in the GitHub repository rahmanef63/control-room (18 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 307 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 2026-08-30.
Other commands, from other repositories
portaljs-architect
Recommend a data-portal architecture (storage, compute, catalog, access, hosting, metadata) from your needs, then hand off to the build skills. The advisory entry point.
portaljs-check-data-quality
Audit a local or remote tabular file (CSV/TSV) for common data quality issues. Read-only. Use only when the user explicitly asks to check or audit data quality.
plan-feature
Plan a feature from BRD-lite brief or clear intent into PRD (What), decisions, implementation plan, and task slices.
retro-learn
Convert delivery findings into skill, eval, workflow, and documentation improvements.
memory-store
Store an insight, decision, or pattern to memory.
dev
Runs Vendure in development mode. By default it starts three processes: the GraphQL server (ts-node ./src/index.ts), the worker (ts-node ./src/index-worker.ts), and the dashboard (a Vite dev server).