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 skills add nirholas/three.ws --skill giza-zkml-visualizationgit clone --depth 1 https://github.com/nirholas/three.wsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nirholas/three.ws/giza-zkml-visualization)<a href="https://agentmods.dev/skills/nirholas/three.ws/giza-zkml-visualization"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/giza-zkml-visualization/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nirholas/three.ws/giza-zkml-visualization"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/giza-zkml-visualization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00029 | $0.00911 |
| Opus 5.5 | $0.00012 | $0.00364 |
| Sonnet 5.5 | $0.00006 | $0.00182 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
giza-zkml-visualization 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 1mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Giza ZKML Agent Visualization
Overview
Giza is a protocol for deploying verifiable AI agents on-chain using Zero-Knowledge Machine Learning (ZKML). This skill covers how Giza agents work, proof verification, and how to interpret the visualization dashboards in SperaxOS.
Key Concepts
Zero-Knowledge Machine Learning (ZKML)
ZKML allows AI model inferences to be verified on-chain without revealing the model weights or input data. This creates trustless AI — anyone can verify that a model produced a specific output from a specific input, without needing to trust the model operator.
Giza Agents
On-chain AI agents deployed via the Giza protocol. Each agent:
- Runs a specific ML model (e.g., price prediction, risk scoring)
- Generates ZKML proofs for each inference
- Can be deployed on multiple chains (Starknet, Ethereum, Arbitrum, etc.)
- Has a verifiable track record of accuracy and performance
Proof Systems
Giza supports multiple proof backends:
- Cairo — Native to Starknet, fastest proving time for StarkNet deployments
- Noir — Aztec Labs' DSL for ZK circuits, good for Ethereum L1
- RISC Zero — General-purpose zkVM, supports any computation
SperaxOS Visualization Tool
Agent Overview Dashboard
Shows all deployed Giza agents with:
- Status indicators — Green (active), Yellow (pending), Red (inactive)
- Summary stats — Total active agents, inference count, proof count
- Agent rows — Name, chain, inference count, proof count per agent
Proof History View
Visualizes ZKML proof verification pipeline:
- Verification rate bar — Color-coded segments showing verified/pending/failed ratios
- Proof rows — Individual proofs with status badge, proof type (Cairo/Noir/RISC0), chain, duration, and timestamp
- Use this to monitor proof verification health and identify failures
Model Performance Dashboard
Detailed metrics for a specific AI model:
- Accuracy gauge — Green >95%, Yellow 85-95%, Red <85%
- Inference latency — Average time per inference
- Proof generation time — Average time to generate ZKML proof
- Inference volume sparkline — 30-day trend of inference activity
- Chain deployment tags — Which chains the model is deployed on
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.
- 1mo ago First seen · 88 lines · 29 tokens per session scan A a899964c4316
giza-zkml-visualization is a skill published in the GitHub repository nirholas/three.ws (250 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 911 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
system-prompts
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
mantis-threat-model
Synthesizes trust boundaries, attack surfaces, and attacker profiles into a living threat model. Use as Stage B of the Knowledge Base generation process, reading architecture and entity definitions from the KB. Don't use for analyzing source code or extracting raw learnings from JSONL files.
blockrun
Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana), or a BlockRun account API key. No subscriptions. Start here when you have the BlockRun MCP installed and need to know WHICH tool answers a question, how the wallet works, or how to…
bridgenode
BridgeNode — x402 pay-per-request AI inference for agents. OpenAI-compatible API + MCP server with tool calling, Solana USDC, gas-free micropayments. No API keys. Free models included. Live prices: bridgenode.cc/v1/models Use when an agent lacks a provider API key or wants privacy-preserving per-request AI inference…
llava
Vision-language chat: VQA, captioning, image dialogue.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…