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 teamskill-creatorgit 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/teamskill-creator)<a href="https://agentmods.dev/skills/xiaoluolyg/god/teamskill-creator"><img src="https://agentmods.dev/badge/skills/xiaoluolyg/god/teamskill-creator/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/teamskill-creator"><img src="https://agentmods.dev/badge/skills/xiaoluolyg/god/teamskill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Rogue Agent · line 312 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium MCP Rug Pull · line 95 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 229 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00074 | $0.06182 |
| Opus 5.5 | $0.00030 | $0.02473 |
| Sonnet 5.5 | $0.00015 | $0.01236 |
| Haiku 4.5 | $0.00007 | $0.00618 |
Grade A, and why
teamskill-creator 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **Scan local tools** — probe CLI tools available in the current environment (e.g., `gh`, `python`, `rg`, `jq`, `curl`, `docker`). Use `where` (Windows) or `which` (Unix). How it starts
The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teamskill Creator
Authoring tool for Teamskills — the multi-role extension of the Anthropic Skills standard. Encodes the Teamskill spec into a repeatable workflow with templates, decision trees, and an automated validator.
Workflow
This skill has three modes. Pick one based on the user's request, then follow the matching pipeline:
| Mode | Trigger | Output |
|---|---|---|
| CREATE | User has a fresh need ("build a team for X") | New <teamskill-name>/ directory with the full 5-file set |
| CONVERT | User points at an existing single-agent skill | Transformed <teamskill-name>/ directory + a delta report explaining what the team adds |
| MODIFY | User edits an existing Teamskill (add/remove role, change workflow, adjust bind, fix validator errors) | Updated files in the existing <teamskill-name>/ directory |
All three modes share Stages 2–6. CONVERT differs only in Stage 1 (decomposition replaces fresh design). MODIFY skips Stage 0 and Stage 1 (justification and pattern are already settled — re-open them only if the change alters the pattern, e.g. adding a parallel role to a pipeline team), touches only the affected stages in 2–5, and MUST run Stage 6 (validator) — this is the most-skipped, most-critical step in MODIFY mode. See the MODIFY impact matrix for which stages to re-run per change type.
Stage 0: Triage — is a Teamskill even justified?
A Teamskill is only justified when at least one of these is true:
- Adversarial blind spot — a single agent role-playing N personas produces converging outputs because it cannot escape its own analytical priors. Examples: PR review, security audit, design critique.
- Parallel decomposition gain — N independent sub-tasks can run concurrently and the integration is non-trivial. Examples: multi-angle research, multi-perspective due diligence.
- Specialization pipeline with hard handoffs — sequential stages with quality gates where blurring stage boundaries causes regressions. Examples: marketing copy (brief → draft → edit → audit), incident response (declare → triage → mitigate → postmortem).
What ships with it
6 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 · 315 lines · 74 tokens per session scan A 0c6f1229a497
teamskill-creator is a skill published in the GitHub repository XiaoLuoLYG/GOD (1,233 stars, last pushed 2d ago), licensed Apache-2.0. It adds 74 tokens to every session and 6,182 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
canopy
Given a natural-language question about a vehicle data session, Canopy.
create-tech-design
Only use when the user explicitly invokes this skill by name.
iterate-tech-design
Only use when the user explicitly invokes this skill by name.
iterate-implementation
Only use when the user explicitly invokes this skill by name.
flux-analyzer
Analyse FBA flux distributions to extract biological insights. Covers gene essentiality, phenotypic phase planes, flux sampling, pathway-level aggregation, secretion product prediction, and production of publication- quality figures.
tencent-ima-wiki
A browser-automation workflow for reading articles from a logged-in Tencent ima knowledge base. It extracts article links and text from the ima.qq.com/wikis site, including pages whose details are not directly visible in the webpage.