GOD is a control room for observing and directing societies of language-model agents running in simulated worlds. It lets researchers inspect replays, question individual agents, alter future events, reset simulations, and export experiments for reuse. The catalogue entries are skills and agents for operating and investigating these simulations.
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 XiaoLuoLYG/GOD --skill script.automategit clone --depth 1 https://github.com/XiaoLuoLYG/GODWrote 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/xiaoluolyg/god/script.automate)<a href="https://agentmods.dev/skills/xiaoluolyg/god/script.automate"><img src="https://agentmods.dev/badge/skills/xiaoluolyg/god/script.automate/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/xiaoluolyg/god/script.automate"><img src="https://agentmods.dev/badge/skills/xiaoluolyg/god/script.automate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00013 | $0.00187 |
| Opus 5.5 | $0.00005 | $0.00075 |
| Sonnet 5.5 | $0.00003 | $0.00037 |
| Haiku 4.5 | $0.00001 | $0.00019 |
Grade A, and why
script.automate 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 1mo 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
Script Automate
This is a real executable GOD agent skill. Its local skill.json describes
its own targets, interaction preferences, status changes, speech template,
memory template, and fallback strategy. scripts/run_skill.py returns a
standard SkillResult; the JiuwenClawAgent runtime validates and applies the
result to movement, interaction, speech, state, and memory.
What ships with it
2 files 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.
- 1mo ago First seen · 27 lines · 13 tokens per session scan A 01108886a533
script.automate is a skill published in the GitHub repository XiaoLuoLYG/GOD (1,233 stars, last pushed 2d ago), licensed Apache-2.0. It adds 13 tokens to every session and 187 once invoked, about $0.0001 per session on Opus 5.5. 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
e2a
Use when operating an already-connected e2a inbox over MCP: reading, composing, sending, replying, forwarding, handling attachments, managing contacts/outreach, scheduling mail, or using templates. Teaches correct threading, conversation correlation, concise multipart composition, and accepted/pending-review no-retry…
hr-assistant
An HR support procedure for answering questions about employee policies, pay, leave, hiring, training, and workplace matters using an employee handbook. It can also handle employee records, HR requests, and current labour-policy checks when needed.
meeting-copilot
A two-machine live meeting copilot. A Windows laptop streams two audio channels (your mic, and a loopback of the other side's voice) to a parent machine, which transcribes them, drives a teleprompter you read from, watches every incoming utterance against a ledger of pre-agreed facts, and answers off-script questions.…
script-exec-blocked
Sandbox approval policy blocks executecode and python3 -c; use readfile/writefile + manual transforms instead of retrying both runners.
meeting-board
A one-machine live meeting board. A small browser extension reads Google Meet's own live captions together with the speaker names, hands them to a tiny helper that listens on 127.0.0.1 only, and the helper periodically asks the local Claude Code (claude -p) to keep a structured, speaker-attributed "story so far".…
yesmem-cap-builder
Use when a user wants to persist a working REPL snippet, bash command, or multi-step workflow as a reusable cap (CAP.md tool) available in future sessions. Trigger on savecap, capstore, autoactive, capblob-pipe, "/build-tool", "make this reusable", or when a one-off shell pipeline is about to be retyped a third time.