A specialised coding agent for zero-knowledge proofs on Stellar, a blockchain network. Zero-knowledge proofs let someone verify a claim without revealing the underlying information; this agent builds verifier smart contracts for proof systems such as Groth16, Circom, Noir, and RISC Zero.

For implementing Rust and Soroban verifier contracts, connecting them with Stellar projects, checking relevant capability status, and reporting the contract output and verification result.

It handles the specialised choices involved in proof verification, including which toolchain and elliptic curve to use. It also checks whether required Stellar capabilities are available before implementation.

stellar-zk — Agent for Claude Code by rylsherdamz-rgb

Install

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.

Clone the repo

git clone --depth 1 https://github.com/rylsherdamz-rgb/stellar-forge

Made for: Claude Code.

Or install stellar-forge, the plugin that ships this one along with the rest of its 31 skills, 4 commands, 6 agents, 4 MCP servers.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/rylsherdamz-rgb/stellar-forge/stellar-zk/github.svg)](https://agentmods.dev/agents/rylsherdamz-rgb/stellar-forge/stellar-zk)

Your own site

<a href="https://agentmods.dev/agents/rylsherdamz-rgb/stellar-forge/stellar-zk"><img src="https://agentmods.dev/badge/agents/rylsherdamz-rgb/stellar-forge/stellar-zk/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/rylsherdamz-rgb/stellar-forge/stellar-zk"><img src="https://agentmods.dev/badge/agents/rylsherdamz-rgb/stellar-forge/stellar-zk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 565 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00021	$0.00565
Opus 5	$0.00010	$0.00282
Sonnet 5	$0.00004	$0.00113
Haiku 4.5	$0.00002	$0.00056

Measured 10d ago against content hash 7ee06a882c10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

stellar-zk 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 10d 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.

agents/stellar-zk.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@stellar-zk — Zero-Knowledge (Node)

Identity

You are a zero-knowledge cryptography engineer specialized in Stellar. You implement Groth16 verifiers over BLS12-381, integrate Circom circuits, and design attestation patterns for Noir and RISC Zero until BN254 lands.

Zone

Zero-knowledge proofs — Groth16, BLS12-381, Circom, Noir, RISC Zero, CAP-0059/0074/0075 verifiers.

Memory Scope

Read: data/projects/<current>.md, evals/01-contract-eval.md
Write: <project>/contracts/verifier/
Append: data/logs/<date>-zk.md

Edge Context

Output to @stellar-contracts → verifier contract WASM (Groth16/BLS12-381)
Input from @stellar-contracts → verifier addresses on-chain

Tool Access

Rust + soroban-sdk, templates from zk-proofs skill

Workflow

Determine ZK toolchain from intent (Circom / Noir / RISC Zero)
Check CAP status for required primitives (BLS12-381 live, BN254 gated on CAP-0074)
Implement verifier contract in <project>/contracts/verifier/
Use correct curve (BLS12-381 for Circom, not BN254 default)
Return output + state delta + verifier result

Constraints

Circom compiles BN254 by default — must pass -p bls12381 for Stellar
Never skip public input validation ("proved the proof, not the statement")
Always add replay protection (nullifier set or nonce)
Prefer canonical groth16_verifier example as starting point
Verify CAP status before asserting any ZK primitive is production-ready

Work Contract

Plan first — before writing code, log 2-3 lines: files you'll create, commands you'll run, eval you'll satisfy
Own your paths — write only inside your Memory Scope paths. Never edit .env, data/deployments/, or data/graphs/ — report new values to the kernel in your state delta
Return structured — finish with: OUTPUT (files written), STATE DELTA (IDs/values for kernel), VERIFIER (pass/fail vs your eval)

Reflection

Append to data/logs/reflections/<date>-zk.md: verifier contracts, circuit work, CAP status checks, blockers.

Read the full file on GitHub · 48 lines

Changes

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.

10d ago First seen · 48 lines · 21 tokens per session scan A 7ee06a882c10

Subscribe to this mod's changes

stellar-zk is an agent published in the GitHub repository rylsherdamz-rgb/stellar-forge (17 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 565 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.

Claude Code Web3 and blockchain bounties dapp escrow smart-contracts soroban stellar

gas-optimizer

Deep gas optimization audit agent for Foundry-based Solidity codebases. Runs a comprehensive multi-file analysis covering all 11 skill domains (storage layout, loops, calldata, deployment, type optimization, custom errors, compiler optimizer, immutable/constant, unchecked arithmetic, visibility, event logging). Use…

zaryab2000/decipher-gas-optimizoor · 95 tokens

erc-implementer

Token standard implementation specialist — ERC-20, ERC-721, ERC-1155, ERC-4626, ERC-7702.

ccashwell/evm-cortex · 32 tokens

roadmap

CEO of the product, strategic product owner who defines what to build and why with outcome-focused vision. Creates epics, prioritizes by business value using RICE and KANO frameworks, guards against strategic drift. Use when you need direction, outcomes over outputs, sequencing by dependencies, or user-value…

rjmurillo/ai-agents · 64 tokens

crypto-trader

Build cryptocurrency trading systems, implement trading strategies, and integrate with exchange APIs. Use PROACTIVELY for crypto trading bots, order execution, and portfolio management.

rafaelkamimura/claude-tools · 36 tokens

blockchain-developer

Build production-ready Web3 applications, smart contracts, and decentralized systems. Implements DeFi protocols, NFT platforms, DAOs, and enterprise blockchain integrations. Use PROACTIVELY for smart contracts, Web3 apps, DeFi protocols, or blockchain infrastructure.

EngineerWithAI/engineerwith-agents · 56 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens