Borrowing it
Nothing to install: this file belongs to vlasenkoalexey/tpu_performance_autoresearch_wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vlasenkoalexey/tpu_performance_autoresearch_wiki/main/.claude/skills/scan-gke-clusters/SKILL.mdgit clone --depth 1 https://github.com/vlasenkoalexey/tpu_performance_autoresearch_wikiWrote 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/vlasenkoalexey/tpu_performance_autoresearch_wiki/scan-gke-clusters)<a href="https://agentmods.dev/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/scan-gke-clusters"><img src="https://agentmods.dev/badge/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/scan-gke-clusters/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/vlasenkoalexey/tpu_performance_autoresearch_wiki/scan-gke-clusters"><img src="https://agentmods.dev/badge/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/scan-gke-clusters.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 127 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00192 | $0.03144 |
| Opus 5 | $0.00096 | $0.01572 |
| Sonnet 5 | $0.00038 | $0.00629 |
| Haiku 4.5 | $0.00019 | $0.00314 |
Grade A, and why
scan-gke-clusters 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/scan-gke-clusters — refresh GKE TPU cluster inventory
Updates the inventory under .env/ that /start-experiment Step 5 consults when picking a cluster. Reads it by running gcloud + kubectl probes against each project's clusters; writes both a per-project file (deep dive) and updates the combined inventory (cross-project overview).
When to invoke
- New cluster reported — colleague spun up a cluster, your inventory is missing it.
- Cluster changed — node-pool added/removed, XPK setup completed, pool composition changed.
- Periodic batch refresh — once every few weeks, pass every project the user maintains access to as separate
--projectargs, to catch all drift. - NOT for occupancy — "which cluster has free capacity right now" is a live query, not inventory.
/start-experimenthandles occupancy via its Step 6 (xpk workload list + name-based attribution).
Cardinal rules
- Outputs go in
.env/, scripts live in.claude/scripts/. Same convention as the rest of the autoresearch infra. - Per-project file is the source of truth for that project's clusters. The combined file is a cross-project view; its rows are owned by per-project files.
- The combined file's structure is preserved verbatim — TPU-gen H2 sections, sort within each section (largest single-slice topology first, then cluster name), prose intro/outro. Only the rows for the scanned project change.
- gcsfuse + Spot columns: NOT in the bash probe TSV. New rows get
?. Existing rows from OTHER projects are preserved verbatim. Detecting gcsfuse + spot would require additional kubectl + gcloud calls — deferred to v2. - Do NOT auto-commit. The skill produces artifacts; the user reviews + commits per existing convention.
.env/is gitignored on this repo so committing is opt-in if desired.
Arguments
Required (at least one):
<project-name>— bare positional. Skill treats any argument NOT starting with--as shorthand for--project <arg>. Most common form:/scan-gke-clusters <project>.--project <p>— repeatable; for multi-project refresh, pass once per project:/scan-gke-clusters --project <project> --project <project>.
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 · 209 lines · 192 tokens per session scan A e2dbfcf85754
scan-gke-clusters is a skill published in the GitHub repository vlasenkoalexey/tpu_performance_autoresearch_wiki (55 stars, last pushed 8d ago), licensed MIT. It adds 192 tokens to every session and 3,144 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
remote-compute-ops
Operate GPU and remote compute across RunPod (Pods and Serverless), Massed Compute VMs, and owned or virtual remote servers through existing bridges, SSH sessions, MCP/API adapters, bounded polling, cost controls, and resumable lifecycle checks. Use when the user mentions RunPod, Massed Compute, a remote…
customer_support_agent
You have access to Leeroopedia, a curated ML/AI knowledge base, via MCP tools. These are real MCP tools registered in your environment -- call them directly like any other tool. They contain framework-specific docs, code examples, API references, and best practices.
ml_inference_optimization
This document describes the Leeroopedia MCP tools available during the with-KB benchmark run. It is a standalone reference and is not fed to the agents automatically.
leeroopedia-mcp
Use Leeroopedia MCP to fetch grounded ML/AI best practices, build and review ML plans, debug failures, verify code/math correctness, and expand KB citations via getpage.
self_evolve_rag
This document describes how to use the Leeroopedia MCP tools for the Self-Evolving RAG task. It is kept as a reference and is NOT included in the agent prompt.
llm_post_training
You have access to the Leeroopedia MCP tools. Use them throughout this pipeline to make informed decisions. Specifically.