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/golemcloud/golem/golem-js-runtimenpx skills add golemcloud/golem --skill golem-js-runtimegit clone --depth 1 https://github.com/golemcloud/golemWhat 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 | $0.00044 | $0.01507 |
| Opus 5 | $0.00022 | $0.00754 |
| Sonnet 5 | $0.00009 | $0.00301 |
| Haiku 4.5 | $0.00004 | $0.00151 |
Grade A, and why
golem-js-runtime scanned grade A 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 3d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- `node:child_process` The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 3d ago First seen · 143 lines · 44 tokens per session scan A 88917558821a
golem-js-runtime is a skill published in the GitHub repository golemcloud/golem (1,509 stars, last pushed today), with no licence file. It adds 44 tokens to every session and 1,507 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
workflow
Creates durable, resumable workflows using Vercel's Workflow SDK. Use when building workflows that need to survive restarts, pause for external events, retry on failure, or coordinate multi-step operations over time. Triggers on mentions of "workflow", "durable functions", "resumable", "workflow sdk", "queue"…
sage-memory
Persistent, consensus-validated memory for AI agents via SAGE MCP server. Gives you institutional memory that survives across conversations — memories go through BFT consensus, carry confidence scores, and decay over time. Use this skill when working with a SAGE MCP server to manage persistent agent memory, recall…
kitaru-adapter-development
Add or change a Kitaru framework adapter that records native agent runs or supports bounded replay. Use for Python adapter distributions under plugins/packages or TypeScript adapter packages under packages, not trace importers or core API work.
create-agent-dotnet
This skill creates a durable AI agent application in .NET using Microsoft Agent Framework on Dapr Workflow. Use this skill when the user asks to "create an agent in .NET", "build an agent app in C#", or "scaffold a .NET agent with Microsoft Agent Framework".
resonate-basic-ephemeral-world-usage-java
Use when writing Java code in main(), an HTTP handler, or any entry point that launches or coordinates Resonate workflows from the ephemeral world (the Client API surface, not code inside a durable function). Core patterns for the Resonate Java SDK's Client APIs — building a Resonate instance with the fluent builder…
resonate-human-in-the-loop-pattern-typescript
Implement human-in-the-loop workflows where durable functions pause for human decisions, approvals, or reviews. Use this pattern for approval gates, manual review workflows, and human-assisted processes.