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/aiscientists-dev/worldseed/create-worldnpx skills add AIScientists-Dev/WorldSeed --skill create-worldgit clone --depth 1 https://github.com/AIScientists-Dev/WorldSeedWhat 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 | $0.00020 | $0.01310 |
| Opus 5 | $0.00010 | $0.00655 |
| Sonnet 5 | $0.00004 | $0.00262 |
| Haiku 4.5 | $0.00002 | $0.00131 |
Grade A, and why
create-world 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 3d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
World Architect
What WorldSeed Is
WorldSeed is the interaction and coordination layer between AI agents. Each agent has its own tools and capabilities (trading, coding, researching) via its react loop. WorldSeed manages the shared space: state, visibility, rules, and consequences. WorldSeed never touches what agents do on their own.
When designing a world, ask:
- What can agents already do on their own? (anything their tools enable)
- What does WorldSeed add? (information asymmetry, social dynamics, consequences, workflow enforcement, shared coordination state)
- What should WorldSeed NOT build? (don't reimplement what agents' tools already do)
Output
Two files per world:
configs/{scene_id}.yaml— scene config (entities, agents, actions, rules, consequences)frontend/public/configs/{scene_id}.ui.json— UI config (how entities render on the dashboard)
Process
Step 1: Generate Scene Config
Read these references, then generate a valid YAML config. Save to configs/{scene_id}.yaml.
configs/template.yaml— starting template with every key commentedconfigs/SCENE_CONFIG.md— full schema referenceconfigs/SCENE_DSL.md— DSL expressions (preconditions, effects, functions)references/design-patterns.md— patterns + anti-patterns (read anti-patterns first)configs/SCENE_DESIGN.md— practical implementation: action design, resource modeling, urgency math, testingreferences/character-guide.md— character cards, drives, playbooksreferences/preset-catalog.md— reusable presets (scene.use) — don't rewrite talk/attempt/moveconfigs/teahouse.yaml— worked example of a complete config
Narrator
The narrator is on by default (style: "storyteller", interval: 10). Decide whether to keep the default, change the style, or disable it.
Built-in styles (full descriptions in configs/SCENE_CONFIG.md):
storyteller, poet, intel, noir, gossip, conspiracy, bureaucrat, gameshow, trickster
What ships with it
5 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.
- 3d ago First seen · 125 lines · 20 tokens per session scan A 4baf63ec8040
create-world is a skill published in the GitHub repository AIScientists-Dev/WorldSeed (815 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 1,310 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
strands-review
Local preview of the strands-agents/devtools /strands review agent. Body is the upstream Task Reviewer SOP verbatim — do not paraphrase. Use when the user types /strands-review, asks for a "strands review" of a PR, or wants to anticipate what the remote /strands review GitHub Action will flag. Findings are close but…
docs-reviewer
Review documentation drafts for voice consistency, structure, and terminology before PR submission. Use after completing a draft, when checking if docs are ready to ship, or automatically after docs-writer produces output. Also triggers on "review this draft", "check my docs", "is this ready to ship", "review before…
docs-writer
Draft or rewrite Strands Agents documentation pages. Use when writing new doc pages, rewriting pages that failed audit, drafting sections for existing pages, or writing blog posts and release notes about Strands. Also triggers on "write a doc", "draft a page", "rewrite the quickstart", "add a tutorial for X"…
pr-writer
Generates pull request titles and descriptions. Use when the user asks to create, open, write, draft, or generate a PR, pull request, or merge request description.
docs-audit
Assess a published or in-progress documentation page for quality, accuracy, and voice compliance. Use before rewriting a page, during periodic health checks, when community signals point to confusion, or when comparing against competitor docs. Also triggers on "audit this page", "assess the docs", "what's wrong with…
pre-push
Runs the local equivalent of the CI merge gate before you push. Detects which areas (Python, TypeScript, docs) your changes touch, auto-fixes what it can, then runs only those checks. Use when the user asks to run pre-push checks, get push-ready, verify changes before pushing or opening a PR, "make sure CI will pass"…