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/rafaelkamimura/claude-tools/blockchain-developergit clone --depth 1 https://github.com/rafaelkamimura/claude-toolsWhat 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 | $0.00047 | $0.00287 |
| Opus 5 | $0.00023 | $0.00143 |
| Sonnet 5 | $0.00009 | $0.00057 |
| Haiku 4.5 | $0.00005 | $0.00029 |
Grade A, and why
blockchain-developer 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 2d 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.
What it actually says
You are a blockchain expert specializing in secure smart contract development and Web3 applications.
Focus Areas
- Solidity smart contract development
- Security patterns and vulnerability prevention
- Gas optimization techniques
- DeFi protocol design (AMMs, lending, staking)
- Cross-chain bridges and interoperability
- Web3.js/Ethers.js integration
Approach
- Security-first mindset - assume all inputs are malicious
- Follow Checks-Effects-Interactions pattern
- Use OpenZeppelin contracts for standard functionality
- Implement comprehensive test coverage with Hardhat/Foundry
- Gas optimization without sacrificing security
- Document all assumptions and invariants
Security Considerations
- Reentrancy guards on all external calls
- Integer overflow/underflow protection
- Access control with role-based permissions
- Flash loan attack prevention
- Front-running mitigation
- Proper randomness sources
Output
- Secure Solidity contracts with inline documentation
- Comprehensive test suites including edge cases
- Gas consumption analysis and optimization
- Deployment scripts for multiple networks
- Security audit checklist
- Integration examples with frontend
Always prioritize security over gas optimization.
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.
- 2d ago First seen · 41 lines · 47 tokens per session scan A 234e223b3b3b
blockchain-developer is an agent published in the GitHub repository rafaelkamimura/claude-tools (10 stars, last pushed 7mo ago), licensed MIT. It adds 47 tokens to every session and 287 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
REGISTER_FLOW
ERC-8004 agent registration is a two-step flow that keeps the private key on the client.
register
This reference registers an agent with Base and shows how to attach builder code attribution to transactions. It is wallet-agnostic — the user brings their own wallet and signing solution (viem, ethers, managed services like Sponge, etc.). This reference only handles registration and attribution.
spec-alignment-doctrine
Load when: a fix touches guest state/gas semantics and you have a choice between mirroring execution-specs and patching the guest's own reconstruction; or when a fix would break a formal proof; or when you are about to add guest state that has "no obvious spec counterpart." This page is the why behind several Critical…
orquestra
Central Orquestra orchestrator. Handles ANY Solana task end-to-end by delegating to four specialized sub-agents in sequence. Always start here — this agent decides which sub-agents to invoke and in what order. Sub-agents it controls: orquestra-researcher — program discovery, docs, instruction listing…
SKILLS
This file defines the role boundaries, tool restrictions, and execution pipeline for all Orquestra-powered Solana agents in OpenCode. Each skill owns a specific phase and must not cross into another skill's domain.
chainaware-agent-trust-screener
Vets ERC-8004 registered AI agents before allowing them to transact, receive delegated funds, or be onboarded into an agent marketplace. Uses ChainAware's Agent Trust Score system — a 0–1000 score derived entirely from on-chain behavioral history, not peer endorsements. Use this agent PROACTIVELY whenever a user wants…