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 golemcloud/golem --skill golem-add-llm-tsgit clone --depth 1 https://github.com/golemcloud/golemWrote 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/golemcloud/golem/golem-add-llm-ts)<a href="https://agentmods.dev/skills/golemcloud/golem/golem-add-llm-ts"><img src="https://agentmods.dev/badge/skills/golemcloud/golem/golem-add-llm-ts.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 5.1 | $0.00046 | $0.01323 |
| Opus 5 | $0.00023 | $0.00661 |
| Sonnet 5 | $0.00009 | $0.00265 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade B, and why
golem-add-llm-ts scanned grade B with 1 finding 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
const response = await fetch('https://api.openai.com/v1/chat/completions', { method: 'POST', The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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 · 170 lines · 46 tokens per session scan B 5e3dc98d8576
golem-add-llm-ts is a skill published in the GitHub repository golemcloud/golem (1,513 stars, last pushed today), with no licence file. It adds 46 tokens to every session and 1,323 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
ray-train
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.
starlark-dev
Develop and debug Kurtosis Starlark packages. Create packages from scratch, understand the plan-based execution model, use print() debugging, handle future references, and test packages locally. Use when writing or troubleshooting .star files.
distributed-systems
Distributed systems patterns for locking, resilience, idempotency, and rate limiting. Use when implementing distributed locks, circuit breakers, retry policies, idempotency keys, token bucket rate limiters, or fault tolerance patterns.
ray-train
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.
kitaru-hosted-onboarding-tour
Guide the ZenML Pro hosted Kitaru onboarding tour from preloaded traces through human review, one reusable evaluator, and one bounded replay. Use only inside the controlled hosted onboarding runner. Resume exact durable workspace state, handle existing agents without name collisions, and keep the tour concise.
aar-public-runtime
Operate OAuth-authenticated, tenant-isolated AAR structured workspaces and caller-delegated RLM jobs through the curated public MCP tools. Use when a user wants bounded JSON-compatible state to persist across ChatGPT or Codex tasks, or wants AAR to coordinate one or more exact model calls while the current host…