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 agentmods add skills/xiaoluolyg/god/cognitionnpx skills add XiaoLuoLYG/GOD --skill cognitiongit 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/cognition)<a href="https://agentmods.dev/skills/xiaoluolyg/god/cognition"><img src="https://agentmods.dev/badge/skills/xiaoluolyg/god/cognition.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 | $0.00013 | $0.03164 |
| Opus 5 | $0.00006 | $0.01582 |
| Sonnet 5 | $0.00003 | $0.00633 |
| Haiku 4.5 | $0.00001 | $0.00316 |
Grade A, and why
cognition 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 6d 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 — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cognition
Read available workspace context and produce state/emotion.json and state/intention.json.
Research basis: references/research_basis.md.
Internal Logic (One Sentence)
Appraise the current tick for novelty, pleasantness, goal conduciveness, urgency, controllability, norm pressure, and need pressure, then write bounded emotion/mood state to state/emotion.json and the highest-scoring TPB intention to state/intention.json.
Output Files
state/emotion.json: Current emotional state (includes mood layer)state/intention.json: Current intention/goal
Input Files (optional, read if present)
Read any existing files from the workspace as context. Common inputs include:
| File | Use |
|---|---|
state/observation.txt |
Main grounding for this tick |
state/thought.txt |
Inner monologue context |
state/needs.json, state/current_need.txt |
Urgency context |
state/memory.jsonl |
Last 5–10 lines for continuity |
state/emotion.json, state/intention.json |
Prior state for continuity |
state/plan_state.json |
Whether a multi-step plan is in flight |
Also use Agent Identity from the system prompt. Other JSON in the workspace (state/beliefs.json, etc.) can be read if present. Skip missing files gracefully.
What to do
- Integrate whatever inputs exist into one appraisal.
- Write
state/emotion.json:primary,mood, dimensionalintensities, plusvalence/arousal/note. - Write
state/intention.json: one chosen goal with TPB scores.
If deterministic baseline is preferred, run scripts/update_cognition.py first, then optionally refine labels, reasoning, and candidate goals with LLM context.
python skills/cognition/scripts/update_cognition.py --state-dir state --tick 120
The script uses Scherer-style appraisal checks and TPB scoring. It is intentionally conservative: it clamps emotion changes per tick and records appraisal values for debugging.
Emotion Layers
Emotions operate on three timescales (based on psychological research):
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.
- 6d ago First seen · 333 lines · 13 tokens per session scan A 6926d9df58be
cognition is a skill published in the GitHub repository XiaoLuoLYG/GOD (1,098 stars, last pushed 9d ago), licensed Apache-2.0. It adds 13 tokens to every session and 3,164 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
game-design-theory
Comprehensive game design theory covering MDA framework, player psychology, balance principles, and progression systems. Master why games are fun.
team
AgentWorld development team. Trigger: '组建团队', '开会', '/team', 'build team', 'review architecture'.
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements.
typescript-advanced-types
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects.
code-review-excellence
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.
prompt-engineering-patterns
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.