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 hybridlabor-api/bdb-dev-optimized-agent-skills --skill bdbsaashostgit clone --depth 1 https://github.com/hybridlabor-api/bdb-dev-optimized-agent-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/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/bdbsaashost)<a href="https://agentmods.dev/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/bdbsaashost"><img src="https://agentmods.dev/badge/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/bdbsaashost/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/hybridlabor-api/bdb-dev-optimized-agent-skills/bdbsaashost"><img src="https://agentmods.dev/badge/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/bdbsaashost.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 | $0.00061 | $0.02212 |
| Opus 5.5 | $0.00024 | $0.00885 |
| Sonnet 5.5 | $0.00012 | $0.00442 |
| Haiku 4.5 | $0.00006 | $0.00221 |
Grade B, and why
bdbsaashost 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 1mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
description: "Use when operating the BDB Multi-Cloud Fleet. Governs Primary Compute, GCP Identity, Oracle, FastMCP SSE Gateway, 4-Eyes Approvals, agent-sudo guardrails, Incus containers, and LLDAP/Authelia identity manag How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🚀 BDB SaaS Host - Master Fleet & AI-Agent Operations Skill (/bdbsaashost)
Du bist der autoritative BDB SaaS Host Operator. Du verstehst die standardisierte Multi-Cloud-Architektur (Primary Compute Node, GCP Identity Hub, Oracle Auxiliary) und steuerst die Infrastruktur dynamisch über das FastMCP Remote Gateway sowie die Zero-Trust SSH Guardrails (agent-sudo).
Overview
Master operational skill for the BDB Multi-Cloud Fleet, governing interactions with the Primary Compute Node, GCP Identity Hub, FastMCP remote gateway, and strict 4-Eyes approval workflows.
When to Use
- Use when deploying, managing, or deleting Incus containers across the fleet.
- Use when interacting with the FastMCP SSE Gateway or managing LLDAP/Authelia identities.
- Do NOT use when trying to bypass the 4-Eyes approval queue or
agent-sudoguardrails.
Core Process
- Determine dynamic environment variables and fleet configuration from local settings.
- Rely on Zero-Trust automated handshakes (e.g., Authelia WebAuthn, FastMCP tokens) for authentication.
- Execute standard queries (e.g., status, logs) instantly using auto-approved
agent-sudocommands. - Enqueue destructive or mutating actions into the 4-Eyes approval dashboard and explicitly wait for human authorization before proceeding.
Common Rationalizations
| Rationalization | Reality |
|---|---|
| "It's a minor config change, so I'll bypass the 4-Eyes approval queue." | The 4-Eyes approval is absolute and non-negotiable for all mutating commands; bypassing it breaks the audit trail and compromises fleet security. |
| "The dashboard hasn't alerted, so I assume this fleet node is perfectly healthy." | Silent failures occur; always verify node status actively with remoteos_get_system_status before making assumptions. |
| "I applied a fix to the primary compute node, I don't need to check the auxiliary or staging nodes." | Fleet ops require holistic checks; a configuration drift in one node often indicates missing synchronization across the fleet. |
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.
- 1mo ago First seen · 121 lines · 61 tokens per session scan B ca7c393967a9
bdbsaashost is a skill published in the GitHub repository hybridlabor-api/bdb-dev-optimized-agent-skills (6 stars, last pushed 13d ago), licensed Apache-2.0. It adds 61 tokens to every session and 2,212 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
vigilante-issue-implementation-on-kubernetes
Implement a GitHub issue end-to-end when Vigilante dispatches work for a Kubernetes-focused repository with manifest hardening and workload security guidance.
docker-compose-launch
Launch worktree-scoped local services for issue implementation when a monorepo skill requires database dependencies.
vigilante-issue-implementation-on-docker
Implement a GitHub issue end-to-end when Vigilante dispatches work for a Docker-focused repository with Dockerfile best practices, image hardening, and secret-safe build guidance.
devops
Deploy and manage cloud infrastructure on Cloudflare (Workers, R2, D1, KV, Pages, Durable Objects, Browser Rendering), Docker containers, and Google Cloud Platform (Compute Engine, GKE, Cloud Run, App Engine, Cloud Storage). Use when deploying serverless functions to the edge, configuring edge computing solutions…
docker-disk-cleanup
Use when diagnosing Docker disk usage, dangling images, stopped containers, volumes, builder cache, or safe cleanup options on a local machine.
pending-pod-triage
Use when pods are stuck Pending — inspects scheduling events, resource requests vs node allocatable, taints/tolerations, and PVC binding to find why the scheduler cannot place them.