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 confighub/confighub-skills --skill cub-querygit clone --depth 1 https://github.com/confighub/confighub-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/confighub/confighub-skills/cub-query)<a href="https://agentmods.dev/skills/confighub/confighub-skills/cub-query"><img src="https://agentmods.dev/badge/skills/confighub/confighub-skills/cub-query/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/confighub/confighub-skills/cub-query"><img src="https://agentmods.dev/badge/skills/confighub/confighub-skills/cub-query.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 | $0.00072 | $0.05107 |
| Opus 5 | $0.00036 | $0.02554 |
| Sonnet 5 | $0.00014 | $0.01021 |
| Haiku 4.5 | $0.00007 | $0.00511 |
Grade A, and why
cub-query 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.
How it starts
The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cub-query
Execution mode: follow references/execution-modes.md. This Skill grants no automatic tool permission. Run scoped reads through the host's normal permission flow. Route a newly requested write to its owning Skill instead of treating this query Skill as a mutation path.
The database-like query surface of ConfigHub. Most users don't discover this from the CLI help alone; the skill makes it the first-reach tool for any "find / list / audit" intent.
Why this matters
Configuration is stored as data. Every field of every resource in every Unit in every Space is queryable — by metadata (--where), by content (--where-data), by resource type, and via functions that return structured values. This replaces "clone the repo, grep, try to figure out which env does what." Also, it is generally unnecessary to list all configuration Units or other entities and post-process locally — prefer server-side --where plus -o jq/-o yq.
Ask about resources when the question is about resources. A Unit is a container; the Deployment, Service, or ConfigMap inside it is what users actually ask about. ConfigHub extracts those resources from Unit data and indexes them, so cub k8s get and cub resource list answer resource questions directly — one row per resource, filtered server-side — instead of listing Units and digging into each one's YAML. Reach for them first for "which Deployments…", "show me the Ingresses in prod", "what's in this namespace". See Browsing resources.
The same toolkit covers two scopes:
- Fleet sweeps — "which workloads across the fleet match ?" — think
SELECT ... FROM units WHERE ...over the database. - Single-workload reads — "what is desired for our frontend in us-east?" / "what image is recorded for our worker?" — think
SELECT * FROM units WHERE id = ?orcat workload.yaml.
Single-workload desired-state lookups belong here too: cub unit data and getter functions scoped with --unit are the right ConfigHub tools. Legacy livedata is historical bridge evidence only. A currently-running claim requires controller and Kubernetes evidence through verify-apply.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 6d3d44117bb7
- 12d ago First seen · 324 lines · 72 tokens per session scan A 321b8b925cc1
cub-query is a skill published in the GitHub repository confighub/confighub-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 5,107 once invoked, about $0.0004 per session on Opus 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.
Other skills, from other repositories
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
implementing-rbac-hardening-for-kubernetes
Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.