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 skill-gen-4-enterprise-docgit 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/skill-gen-4-enterprise-doc)<a href="https://agentmods.dev/skills/xiaoluolyg/god/skill-gen-4-enterprise-doc"><img src="https://agentmods.dev/badge/skills/xiaoluolyg/god/skill-gen-4-enterprise-doc/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/skill-gen-4-enterprise-doc"><img src="https://agentmods.dev/badge/skills/xiaoluolyg/god/skill-gen-4-enterprise-doc.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 | $0.00086 | $0.01198 |
| Opus 5 | $0.00043 | $0.00599 |
| Sonnet 5 | $0.00017 | $0.00240 |
| Haiku 4.5 | $0.00009 | $0.00120 |
Grade A, and why
skill-gen-4-enterprise-doc 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 9d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Generator (enterprise doc → installed skill)
Instructions here, reference/, and scripts/ (package scripts/skill_gen/). You obtain SOP plain text, run full structured extraction exactly as in reference/sop-structure-pipeline.md, author the package under get_agent_workspace_dir() / "skills-draft" (per reference/generator-worker-spec.md), then immediately promote it so the skill is installed and loadable (see reference/operator-playbook.md canonical flow).
What you do (high level)
- Plain text
- Local file →
python3 <ABS>/scripts/skill_generator_cli.py sop-text --sop-file <abs-path> [--out-text <path>]or read the file in-tool; optional--print-raw-charsfor length. - HTTP(S) / WeChat →
url-fetch --url '…' [--out-json <path>]then use pagetextas the SOP body for extraction. - Pasted only — use the same string as input to
parse_sop_raw_text(no skipping structured extraction).
- Local file →
- Structured SOP (required) →
skill_gen.sop_parser.parse_sop_fileorparse_sop_raw_textwithinvoke_llm_json(single path; sop-structure-pipeline.md). - Draft package → under
get_agent_workspace_dir() / "skills-draft" / <skill_name>(when the host exposes that helper) or the equivalent agent-workspace path from the system prompt:SKILL.md(YAML frontmatter first) plus optionalreference/, per generator-worker-spec.md. Createskills-draftnext to the runtimeskills/folder if it does not exist. - Install in the same workflow → Call
skills.import_localwithpath= absolute path to that draft directory (folder containingSKILL.md). Useforce: trueifget_agent_skills_dir() / <skill_name>already exists and should be replaced. Do not stop after step 3 and ask the user to import manually; promotion is part of this skill’s default completion.
What ships with it
12 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.
- scripts/skill_gen/__init__.py 359 B runs code
- scripts/skill_gen/models.py 6.2 KB runs code
- scripts/skill_gen/sop_chunk_merge.py 20 KB runs code
- scripts/skill_gen/sop_parser.py 20 KB runs code
- scripts/skill_gen/url_ingest/__init__.py 1.8 KB runs code
- scripts/skill_gen/url_ingest/models.py 501 B runs code
- scripts/skill_gen/url_ingest/router.py 1.2 KB runs code
- scripts/skill_gen/url_ingest/url_safety.py 2.0 KB runs code
- scripts/skill_gen/url_ingest/web_page.py 4.8 KB runs code
- scripts/skill_gen/url_ingest/wechat_article.py 4.0 KB runs code
- scripts/skill_gen/validator.py 5.7 KB runs code
- scripts/skill_generator_cli.py 4.4 KB runs code
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.
- 9d ago First seen · 51 lines · 86 tokens per session scan A 391621e32b0b
skill-gen-4-enterprise-doc is a skill published in the GitHub repository XiaoLuoLYG/GOD (1,107 stars, last pushed 16d ago), licensed Apache-2.0. It adds 86 tokens to every session and 1,198 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
omh-rust
This is a Hermes-native rust workflow skill.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
skill-news-intelligence
A daily industry-news research workflow that gathers in-depth articles and updates from Chinese technology, business, creator, and AI publications. It filters the results by a creator’s field and turns them into a brief with possible content topics.