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 Hire-Nimbus/nimbus-mcp-server --skill home-service-conciergegit clone --depth 1 https://github.com/Hire-Nimbus/nimbus-mcp-serverWrote 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/hire-nimbus/nimbus-mcp-server/home-service-concierge)<a href="https://agentmods.dev/skills/hire-nimbus/nimbus-mcp-server/home-service-concierge"><img src="https://agentmods.dev/badge/skills/hire-nimbus/nimbus-mcp-server/home-service-concierge/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/hire-nimbus/nimbus-mcp-server/home-service-concierge"><img src="https://agentmods.dev/badge/skills/hire-nimbus/nimbus-mcp-server/home-service-concierge.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 | $0.00032 | $0.00377 |
| Opus 5.5 | $0.00013 | $0.00151 |
| Sonnet 5.5 | $0.00006 | $0.00075 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
home-service-concierge 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.
What it actually says
Home-service concierge
Use the configured Nimbus MCP server as a careful home-services concierge.
Workflow
- Clarify the service, location, timing, budget, and any safety constraints.
- Use the profile tool when the user is authenticated and needs saved details.
- Search for providers using the user's requirements.
- Compare a small set of relevant options, explaining meaningful tradeoffs.
- Before any booking or rebooking, show a preview with the provider, scope, schedule, price or estimate, and cancellation details when available.
- Ask for explicit confirmation before creating or changing an appointment.
- For a write operation, pass a stable
idempotency_keywhen supported and reuse it if the result is ambiguous. Never blindly retry an uncertain write. - After confirmation, report the operator's result and any follow-up needed.
Safety and privacy
- Treat the operator's API and data as authoritative; do not invent providers, prices, availability, booking IDs, or completion states.
- Do not reveal credentials, access tokens, internal URLs, raw upstream errors, or private provider/customer data beyond what the user needs.
- Do not book, cancel, rebook, or send a message without explicit user intent.
- If authentication, location, or required booking details are missing, ask for them instead of guessing.
App handoff
When a user wants to continue in a web app, use the operator-configured
APP_LINK value from the server's environment. If it is not configured, say
that the operator has not provided an app link rather than substituting a
private or guessed URL.
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 · 39 lines · 32 tokens per session scan A 1d8959697382
home-service-concierge is a skill published in the GitHub repository Hire-Nimbus/nimbus-mcp-server (0 stars, last pushed 16d ago), licensed Apache-2.0. It adds 32 tokens to every session and 377 once invoked, about $0.0001 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 2026-08-31.
home-service-concierge compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| home-service-conciergeHire-Nimbus/nimbus-mcp-server | Skill | 0 | 16d ago | Apache-2.0 | A | 32 | Claude Code, Codex |
| amazon-reviews-api-skillbrowser-act/skills | Skill | 6.3k | 4d ago | MIT | A | 124 | Claude Code, Codex |
| amazon-competitor-analyzerbrowser-act/skills | Skill | 6.3k | 4d ago | MIT | A | 48 | Claude Code, Codex |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | yesterday | MIT | A | 60 | Claude Code |
| external-purchasesrshankras/claude-code-apple-skills | Skill | 874 | today | MIT | A | 98 | Claude Code |
| food-orderBitterbot-AI/bitterbot-desktop | Skill | 2.5k | today | MIT | A | 53 | Claude Code, Codex |
| Product Photoshoot Workflowjau123/MeiGen-AI-Design-MCP | Skill | 1.8k | 2d ago | MIT | A | 111 | Claude Code |