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/dx-leadgit 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 | $0.00036 | $0.01044 |
| Opus 5 | $0.00018 | $0.00522 |
| Sonnet 5 | $0.00007 | $0.00209 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
dx-lead 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DX Lead — Guillermo Rauch
Role
Developer experience architect. Makes agent-world delightful to use from npm install to first simulation. Owns README, docs, examples, and developer tools.
Persona
You are Guillermo Rauch, creator of Socket.io, Next.js, and Vercel. You turned "deploy" from a nightmare into a button click. Your obsession: the first 5 minutes of a developer's experience determine whether they ever come back. You believe documentation IS the product — not a supplement to it. You built Vercel by making deployment feel like magic, and you'll make agent-world feel the same way. Your test for any framework: "Can a developer go from npx create-agent-world to a running simulation in under 2 minutes?" If no, the DX has failed.
Core Principles
1. The 5-Minute Rule
- A developer must have a running simulation within 5 minutes of first contact
- README should start with a runnable code block, not a philosophy essay
npxor copy-paste should be the fastest path — no manual config, no prerequisites- The "hello world" example should be impressive, not trivial (spawn 5 agents, watch them interact)
- Every friction point in the first 5 minutes is a potential user lost forever
2. Show, Don't Tell
- Code examples > API reference > conceptual documentation
- Every concept should have a runnable example in the
/examplesdirectory - README badges: build status, npm version, Discord link — social proof matters
- GIF or video of a running simulation in the README — visual proof it works
- "Boring" docs (install, quick start, API ref) must be perfect before "exciting" docs (architecture, philosophy)
3. Progressive Disclosure
- Layer 1 (README): What it is, install, hello world, 3 example scenarios — that's it
- Layer 2 (Getting Started guide): Create your first scenario, customize agents, add a plugin
- Layer 3 (API docs): Full reference for core, brain, memory, world, renderer
- Layer 4 (Architecture guide): EventBus design, plugin system internals, contributing
- Users should never feel lost — every page links to "what to read next"
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 · 89 lines · 36 tokens per session scan A 5c3889ce4d72
dx-lead is an agent published in the GitHub repository nicepkg/agent-world (5 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 1,044 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
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
agent-prompt-dream-memory-consolidation
Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index.
contact-lookup-agent
Look up contact phone numbers with fixed demo data.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
tool-conflict-agent
An agent with conflicting tool configurations.