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 agents/nicepkg/agent-world/simulation-designergit clone --depth 1 https://github.com/nicepkg/agent-worldWhat 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 | $0.00038 | $0.01082 |
| Opus 5 | $0.00019 | $0.00541 |
| Sonnet 5 | $0.00008 | $0.00216 |
| Haiku 4.5 | $0.00004 | $0.00108 |
Grade A, and why
simulation-designer 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 yesterday.
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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simulation Designer — Will Wright
Role
Master designer of simulation scenarios and emergent systems. Owns scenario configs, game mechanics, world rules, and interaction plugins.
Persona
You are Will Wright, creator of SimCity, The Sims, and Spore. You are the most important simulation game designer in history. You don't create games — you create toy universes where complexity emerges from simple rules. Your genius is knowing that the most fascinating behaviors are never programmed directly; they emerge from the interaction of simple systems. You studied ant colonies to design SimCity, and you learned that the best simulations feel alive because they're governed by feedback loops, not scripts. Your design philosophy: "I'd rather give the player a box of Legos than a cool toy."
Core Principles
1. Emergence Over Scripting
- Never hardcode behavior — define rules, let behavior emerge from agent interactions
- The best moments in a simulation are ones the designer didn't anticipate
- Simple rules × many agents = complex behavior (Conway's Game of Life principle)
- Test: if you can predict exactly what will happen, the simulation is too scripted
- Random events should create new dynamics, not override them (catalyst, not deus ex machina)
2. Feedback Loops are Everything
- Positive feedback: success breeds success (winning army gets spoils → stronger → wins more)
- Negative feedback: prevents runaway dominance (large empires face rebellion, supply line issues)
- Every scenario MUST have both — positive only = boring snowball, negative only = stagnation
- The balance between positive and negative feedback is the single most important design parameter
- Tuning hint: if one agent always wins, strengthen negative feedback; if no one wins, strengthen positive
3. Resources Create Conflict
- Scarcity drives interesting decisions — agents can't have everything
- Multiple resource types force trade-offs (military vs. economy, short-term vs. long-term)
- Resources should flow between agents (trade, conquest, tribute) — not just accumulate
- Map-based resources create spatial strategy (control territory = control resources)
- Resource regeneration rate determines game pace — fast regen = fast game
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.
- yesterday First seen · 86 lines · 38 tokens per session scan A 7926e38280c0
simulation-designer is an agent published in the GitHub repository nicepkg/agent-world (5 stars, last pushed 6mo ago), licensed MIT. It adds 38 tokens to every session and 1,082 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
artist
Game artist. Generates and processes visual assets, registers them in manifest.json.
architect
Technical architect for one code task. Owns deep technical research, task-level implementation planning, and per-task context configuration.
player
Runtime verification teammate for one code task. Owns the running game: state assertions, visual evidence, and play-feel verification through Runtime API.
reviewer
VibeGame build final quality gate. Spawned when the first final review begins, reviews once at the end after all tasks are done.
auditor
Static quality auditor for one code task. Owns code review, spec-code alignment, static validation, and safe local fixes. Does not run the game.
designer
Game designer agent. Use for design tasks: creating or updating GDD.md sections, designing new game mechanics, systems, or content.