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 skills/agent-hellboy/mcp-runtime/qa-cluster-bringupnpx skills add Agent-Hellboy/mcp-runtime --skill qa-cluster-bringupgit clone --depth 1 https://github.com/Agent-Hellboy/mcp-runtimeWrote 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/agent-hellboy/mcp-runtime/qa-cluster-bringup)<a href="https://agentmods.dev/skills/agent-hellboy/mcp-runtime/qa-cluster-bringup"><img src="https://agentmods.dev/badge/skills/agent-hellboy/mcp-runtime/qa-cluster-bringup.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 | $0.00130 | $0.03126 |
| Opus 5 | $0.00065 | $0.01563 |
| Sonnet 5 | $0.00026 | $0.00625 |
| Haiku 4.5 | $0.00013 | $0.00313 |
Grade B, and why
qa-cluster-bringup scanned grade B with 2 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 4d 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/go-example-mcp-manifests Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
command -v docker kind kubectl curl jq python3 go How it starts
The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA — Cluster bring-up (real Kind contributor flow)
Overview
This skill provisions or recovers the real contributor cluster described in
docs/getting-started.md#3-contributor-test-mode-cluster. It is the entry
point for every other qa-e2e-* skill. It is not a unit-test skill — it
boots a Kind cluster, builds and pushes runtime images, installs the operator
and Sentinel stack, deploys the bundled Go MCP server, applies a working
grant + session, and exits only after a real MCP tools/call succeeds through
Traefik.
Regression evidence contract: this skill is not successful until it records a
live cluster context, image/build inputs, rollout health, and a real MCP
tools/call result through the public ingress path. If any live gate cannot
run, report blocked with the failing command; do not downgrade to unit tests
or static checks.
Default policy: reuse if present, create if missing. Never tear down an
existing kind-mcp-runtime cluster without explicit user confirmation —
contributors may have in-flight work on it.
Step 1 — Decide cluster mode
State the mode in the report.
- reuse (default if
kind-mcp-runtimecluster exists andkubectl --context kind-mcp-runtime get nodessucceeds). Skip Kind creation; re-runbootstrapandcluster doctoronly. - create (no
kind-mcp-runtimecontext, or user asked for a clean cluster). Full path: Kind create → build → setup → deploy demo → grant. - rebuild-from-broken (cluster exists but
cluster doctorfails). Try targeted repair first (rollout restart, re-applypipeline deploy); only recreate with the user's explicit ok.
Detect with:
kind get clusters | grep -qx mcp-runtime && echo "reuse" || echo "create"
kubectl config get-contexts -o name | grep -qx kind-mcp-runtime || echo "no-context"
Step 2 — Host preflight
Run from repo root. Missing tools become recorded blockers, not silent skips.
command -v docker kind kubectl curl jq python3 go
docker info >/dev/null
STRICT_DEPS_CHECK=1 make deps-check
What ships with it
3 files 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.
- 4d ago First seen · 302 lines · 130 tokens per session scan B 93518900cc07
qa-cluster-bringup is a skill published in the GitHub repository Agent-Hellboy/mcp-runtime (5 stars, last pushed 10d ago), licensed Apache-2.0. It adds 130 tokens to every session and 3,126 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (recursive force delete, makes network calls). 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…
local-frontend-check
Smoke-test or verify UI behaviour on the local Jarvis Registry frontend running at http://localhost/gateway. Use for manual regression checks, bug-fix verification, and end-to-end confirmation of specific flows without running the automated test suite.
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.