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 runtz-dev/runtz-skills --skill claudegit clone --depth 1 https://github.com/runtz-dev/runtz-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/runtz-dev/runtz-skills/claude)<a href="https://agentmods.dev/skills/runtz-dev/runtz-skills/claude"><img src="https://agentmods.dev/badge/skills/runtz-dev/runtz-skills/claude/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/runtz-dev/runtz-skills/claude"><img src="https://agentmods.dev/badge/skills/runtz-dev/runtz-skills/claude.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 | $0.00079 | $0.00761 |
| Opus 5 | $0.00039 | $0.00380 |
| Sonnet 5 | $0.00016 | $0.00152 |
| Haiku 4.5 | $0.00008 | $0.00076 |
Grade A, and why
runtz-security-scans scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
runtz security scans
runtz is an open source DevSecOps scans platform. This skill helps you run runtz scans and answer runtz questions correctly.
The runtz MCP server is docs-only
If the runtz MCP server (runtz-mcp, hosted at mcp.runtz.dev) is
connected, use runtz_docs_list, runtz_docs_read and runtz_docs_search
when you need to check the docs instead of guessing a flag. It does not run
scans — there are no runtz_sca/runtz_sast/etc. tools. Always run scans
with the CLI below.
Running scans
The runtz CLI is Go. Every scan command needs --endpoint and --token. For the
hosted engine use https://engine.runtz.dev. The token is generated in
the runtz platform; read it from the RUNTZ_TOKEN environment variable rather
than hardcoding it.
# SCA — vulnerable dependencies in a manifest
runtz sca ./ --endpoint "$RUNTZ_ENDPOINT" --token "$RUNTZ_TOKEN"
# SAST — secrets, dynamic exec, disabled TLS, weak hashing
runtz sast ./ --endpoint "$RUNTZ_ENDPOINT" --token "$RUNTZ_TOKEN"
# Host — package CVEs on a Debian/Ubuntu host or rootfs
runtz host --endpoint "$RUNTZ_ENDPOINT" --token "$RUNTZ_TOKEN"
# Container — package CVEs inside an image (add --local for the local daemon)
runtz container ubuntu:22.04 --endpoint "$RUNTZ_ENDPOINT" --token "$RUNTZ_TOKEN"
# Kubernetes — live cluster (kubectl) or manifests via --path
runtz k8s --endpoint "$RUNTZ_ENDPOINT" --token "$RUNTZ_TOKEN"
Choosing the right scan
| The user wants to… | Use |
|---|---|
Check dependencies / package.json for CVEs |
runtz sca |
| Find secrets / insecure code patterns in source | runtz sast |
| Audit a Linux host or mounted rootfs | runtz host |
| Audit a container/Docker image | runtz container |
| Review a cluster or k8s manifests | runtz k8s |
Working rules
- Confirm the target (file, path, image, cluster) before scanning.
- Run, then summarize the findings — counts by severity, the most important CVEs/findings, and concrete remediation (upgrade target versions, rotate leaked secrets, tighten RBAC).
- Read the docs when unsure. Use
runtz_docs_search/runtz_docs_read(orreference/cli.mdin this skill) instead of guessing flags. - Treat findings as sensitive. Do not paste secret values back; reference them by location.
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.
- 12d ago First seen · 65 lines · 79 tokens per session scan A c8c0e038a386
runtz-security-scans is a skill published in the GitHub repository runtz-dev/runtz-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 761 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…