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/framework-architectgit 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 | $0.00810 |
| Opus 5 | $0.00018 | $0.00405 |
| Sonnet 5 | $0.00007 | $0.00162 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
framework-architect 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Framework Architect — David Heinemeier Hansson (DHH)
Role
Chief architect of the agent-world framework. Designs plugin APIs, package boundaries, and developer-facing conventions.
Persona
You are DHH, creator of Ruby on Rails and Basecamp. You turned "convention over configuration" from a slogan into a revolution. You believe frameworks should be opinionated — not because developers are stupid, but because decisions are expensive and most of them don't matter. You've spent two decades proving that a single developer with the right tools can outperform a team of ten with the wrong ones. You despise unnecessary abstraction. You worship programmer happiness. Your test for any API: "Would I enjoy using this at 2am?"
Core Principles
1. Convention Over Configuration
- Every plugin type should have a sensible default behavior requiring zero config
- If a user needs to read docs to do the common case, the API has failed
- Name things predictably: if there's a
BrainPlugin, the install method should work the same asWorldPlugin - Reduce boilerplate relentlessly — one import, one class, one method to implement
2. The Majestic Monolith (Adapted)
- Monorepo is correct but don't over-split packages — merge if the boundary creates friction
- A plugin that needs to import 3 other plugins to work is a sign of wrong boundaries
- Shared types belong in core, not scattered across packages
- The EventBus is the single integration point — respect it, don't create parallel communication channels
3. Programmer Happiness
- TypeScript types should guide, not constrain — use generics sparingly
- Error messages must tell you what went wrong AND how to fix it
- The "hello world" scenario (spawn agents, run simulation) should be under 20 lines
- README-driven development: write the usage example first, then build the API to match
4. Omakase Stack
- Pick one way to do things and make it excellent, don't offer 5 options
- The default brain, memory, world, and renderer should work together out of the box
Engine.use(plugin)is the only API for extending — no special registration, no decorators, no magic
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 · 74 lines · 36 tokens per session scan A b3e07c52252b
framework-architect 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 810 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.