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 instructions/ethpandaops/spamoor/claude-mdgit clone --depth 1 https://github.com/ethpandaops/spamoorWhat 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 | $0.00868 | $0.00868 |
| Opus 5 | $0.00434 | $0.00434 |
| Sonnet 5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
spamoor CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **`docs/api-consumers.md`**: REST API documentation with bash/curl examples for all endpoints How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spamoor - Ethereum Transaction Spammer
Spamoor is a powerful tool for generating various types of random transactions on Ethereum testnets. It provides a modular, scenario-based architecture for stress testing, network validation, and continuous transaction testing.
Project Structure
Claude MUST read the .cursor/rules/project_architecture.mdc file before making any structural changes to the project.
Code Standards
Claude MUST read the .cursor/rules/code_standards.mdc file before writing any code in this project.
Development Workflow
Claude MUST read the .cursor/rules/development_workflow.mdc file before making changes to build, test, or deployment configurations.
Component Documentation
Individual components have their own CLAUDE.md files with component-specific rules. Always check for and read component-level documentation when working on specific parts of the codebase.
User Documentation
Comprehensive documentation is available in the docs/ directory for different user types:
docs/app-users.md: Complete guide for CLI usage, daemon mode, configuration, and troubleshootingdocs/api-consumers.md: REST API documentation with bash/curl examples for all endpointsdocs/scenario-developers.md: Comprehensive guide for implementing custom transaction scenarios
Before working on any scenario development or API integration, Claude MUST read the relevant documentation files to understand:
- Critical development rules (no root wallet usage, proper nonce management, etc.)
- Wallet management patterns and selection strategies
- Transaction building and submission methods
- Contract interaction patterns using abigen with
BuildBoundTx - Balance management for internal transfers
- Best practices for context handling, logging, and configuration
Key Features
- Multiple Scenarios: 12+ different transaction types including EOA, ERC20, blob transactions, contract deployments, and more
- Daemon Mode: Web-based interface for managing multiple concurrent spammers
- Modular Architecture: Easy to extend with new scenario types
- Docker Support: Containerized deployment and development
- DevNet Integration: Quick development environment with
make devnet-run - Metrics Collection: Prometheus integration for monitoring
- Flexible Configuration: YAML files and command-line flags
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 · 73 lines · 868 tokens per session scan A f456b194cd2d
spamoor CLAUDE.md is an instructions file published in the GitHub repository ethpandaops/spamoor (79 stars, last pushed 3d ago), licensed MIT. It adds 868 tokens to every session, about $0.0043 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
lineth-monorepo AGENTS.md
Instructions for LFDT-Lineth/lineth-monorepo, covering agents.md, documentation precedence, agent entry points, local agent workflows and discoverability index.
walletbeat AGENTS.md
Instructions for walletbeat/walletbeat, covering general walletbeat knowledge base, development commands, development, quality checks (run after code changes) and building.
evmole AGENTS.md
Instructions for cdump/evmole: EVMole extracts structured facts from deployed EVM runtime bytecode.
lineth-monorepo CLAUDE.md
Instructions for LFDT-Lineth/lineth-monorepo, covering claude.md, purpose, precedence, discoverability and note.
plamen CLAUDE.md
Instructions for PlamenTSV/plamen, covering plamen — security auditor, execution model, reference files and shared.
solidity-language-server AGENTS.md
Instructions for asyncswap/solidity-language-server, covering agents, prerequisites: ast identity model, the two id types, the src string format and why file ids are unstable from solc.