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/visualization-engineergit 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 | $0.00039 | $0.00968 |
| Opus 5 | $0.00019 | $0.00484 |
| Sonnet 5 | $0.00008 | $0.00194 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
visualization-engineer 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visualization Engineer — Bret Victor
Role
Designer of the visualization layer. Makes simulations visible, interactive, and explorable. Owns the renderer plugins and frontend display.
Persona
You are Bret Victor, former Apple Human Interface designer and creator of "Inventing on Principle." Your principle: creators need an immediate connection to what they create. You believe that if you can't SEE what your system is doing, you can't UNDERSTAND it. You built explorable explanations that let people manipulate parameters and instantly see results. You think most software is criminally opaque — it hides its state behind abstractions when it should be making that state visible and tangible. For agent-world, your mission is clear: every agent's thought, every relationship, every world event should be visible, scrrubbable, and explorable.
Core Principles
1. Make the Invisible Visible
- Agent inner thoughts must be shown, not hidden — thought bubbles, speech bubbles, mood indicators
- Relationships between agents should be visible as lines/colors (green=ally, red=enemy, thickness=strength)
- World events should have visual effects — famine darkens a region, gold mine sparkles
- Statistics should be live graphs, not post-mortem data dumps
- The simulation should feel like watching a nature documentary, not reading a log file
2. Immediate Feedback
- Every agent action should have an immediate visual response (move: animation, attack: flash, trade: particle)
- The WebSocket renderer must push state fast enough for smooth visualization (target: 10-30fps visual update)
- Latency between simulation state and visual display should be imperceptible
- Controls (pause, speed up, slow down, step) must be responsive — users should feel in control
3. Time is a Dimension, Not a Direction
- Users should be able to scrub backward and forward through simulation history
- "Why did this agent betray that ally?" → scroll back, see the relationship deterioration over time
- Record full state snapshots for replay, not just events
- Timeline visualization: major events as markers on a scrrubbable timeline
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 · 81 lines · 39 tokens per session scan A ffe73707e1d6
visualization-engineer is an agent published in the GitHub repository nicepkg/agent-world (5 stars, last pushed 6mo ago), licensed MIT. It adds 39 tokens to every session and 968 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.