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 instructions/aidas-dev/k8s-agent-skills/agents-mdgit clone --depth 1 https://github.com/Aidas-dev/k8s-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/instructions/aidas-dev/k8s-agent-skills/agents-md)<a href="https://agentmods.dev/instructions/aidas-dev/k8s-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/aidas-dev/k8s-agent-skills/agents-md.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 | $0.00333 | $0.00333 |
| Opus 5 | $0.00167 | $0.00167 |
| Sonnet 5 | $0.00067 | $0.00067 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
k8s-agent-skills AGENTS.md 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 5d 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
AGENTS.md — k8s-agent-skills
Skills Must Be User-Agnostic
Every skill in this repo is published to npm and consumed by agents of any user, on any cluster. Skills must work standalone for anyone, anywhere.
Never hardcode cluster-specific data
Forbidden in skills:
- Node names, IPs, tailnet addresses, hostnames (
controlplane-svt,100.x.x.x,talos-cluster) - Cluster names, endpoints, API URLs, domain names
- Secrets, tokens, certs, private keys
- Node counts, hardware specs, disk layouts of a specific deployment
- Provider account IDs, tenant IDs, region names specific to one infra
What to write instead
- Placeholder patterns:
<node-ip>,<cluster-name>,https://<endpoint>:6443 - Generic role labels:
cp1/cp2/cp3,controlplane/worker - "Source of truth" references when a real repo pattern is genuinely instructive — but abstract the specifics (e.g. "secrets come from the live cluster, stored gitignored" — not the actual JSON path of one deployment)
If a real-world example adds value
Genericize it: describe the pattern, keep the structure, strip the specifics. The reader's cluster is different — the skill must survive that.
Review gate
Before committing any skill, grep for: IP literals, tailnet 100.x ranges, node hostnames, cluster names, and URLs pointing at personal infrastructure. If any present — rewrite before committing.
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.
- 5d ago First seen · 30 lines · 333 tokens per session scan A 4b4e525e44a0
k8s-agent-skills AGENTS.md is an instructions file published in the GitHub repository Aidas-dev/k8s-agent-skills (2 stars, last pushed 21d ago), licensed MIT. It adds 333 tokens to every session, about $0.0017 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 instructions, from other repositories
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
selfhost-ai CLAUDE.md
Claude Code instructions for kossakovsky/selfhost-ai, covering claude.md, project overview, core architecture, key files and installation flow.
openlakeforge AGENTS.md
AGENTS.md instructions for malon64/openlakeforge, covering agent and contributor guide, what this project is, non-goals, orientation — read in this order and repository map.
docker-zoneminder CLAUDE.md
Instructions for jantman/docker-zoneminder, covering claude.md, project overview, build and test, ci/cd and architecture.
mitos CLAUDE.md
Instructions for mitos-run/mitos, covering claude.md, project overview, operating principles, commands and architecture.
MoaV AGENTS.md
AGENTS.md instructions for MotherofallVPNs/MoaV, covering what moav is, install & run, everyday operations, dashboards & access — what to hand the owner and where things live.