OPEN-SOURCE AGENT TOOLKIT

Give your coding agent Web3 superpowers.

Free, testable workflows for AI coding agents — built to help developers debug transactions, scaffold stateful Foundry invariants, design safer blockchain agents, verify Slither findings, and ship resilient event pipelines. Not longer prompts. Better engineering workflows.

QUICK INSTALL (VERCEL SKILLS CLI)

$npx skills add theweb3wizard/spellbook-skills --list

✓ 100% Free & Open Source·✓ Zero Secret Handling·✓ Claude Code & Cursor Ready·✓ MIT License

THE INITIAL COLLECTION

Five workflows for real EVM problems

#01DEBUGGING

EVM Transaction Failure Diagnoser

Move from a confusing revert or failed call to an evidence-backed root-cause diagnosis, reproduction steps, and regression tests.

BUILT TO PRODUCE

✓Evidence-backed root cause report with decoded function selector and revert reason
✓Minimal reproducible local fork test (Foundry or Hardhat)
✓Actionable candidate patch and regression-test guidance

View deep dive

#02TESTING

Foundry Invariant Test Scaffolder

Scaffold stateful invariant and property fuzz tests with meaningful accounting handlers, bounded actions, and ghost variables.

BUILT TO PRODUCE

✓Custom Handler contract constraining fuzzer inputs to realistic parameter spaces
✓Targeted invariant test contract asserting formal protocol properties
✓Ghost variable tracking for off-chain accounting and oracle simulation
✓Foundry.toml campaign tuning recommendations (depth, runs, fail-on-revert)

View deep dive

#03AI AGENT SAFETY

Web3 AI-Agent Transaction Safety

Design and enforce strict transaction policies, execution guardrails, simulations, and human approval gates for autonomous agents.

BUILT TO PRODUCE

✓JSON policy configuration establishing chain, contract, selector, and value limits
✓Independent policy evaluation gate decoupled from LLM context
✓Preflight simulation requirements and state validation checks
✓Negative security test suite verifying denied transactions fail closed

View deep dive

#04SECURITY WORKFLOW

Slither Finding Verifier & Triage

Turn noisy static-analysis findings into an actionable triage queue with source context, exploitability criteria, and verification proofs.

BUILT TO PRODUCE

✓Structured triage worksheet categorizing detector confidence and real-world exploitability
✓Code context analysis identifying mitigations, modifiers, or missing guards
✓Focused proof-of-concept test case verifying reproducible security issues

View deep dive

#05PRODUCTION RELIABILITY

RPC & Event Reliability Hardener

Harden Web3 backends, event indexers, and RPC clients against rate limits, reconnect gaps, duplicate delivery, and chain reorgs.

BUILT TO PRODUCE

✓Provider fallback strategy with health checks and exponential backoff jitter
✓Idempotent event processing schema tracking txHash + logIndex + blockHash
✓Reorganization handler detecting removed logs and rolling back state cleanly
✓Automated reliability test suite simulating node timeouts and dropped connections

View deep dive

How Web3 agent skills work

Install the skill pack

Run the npx skills command or copy the skill folder directly into your repo's .claude/skills/ or .agents/skills/ directory.

Prompt your agent

When you run into a revert, need an invariant test, or build an agent policy, your coding agent reads the skill rules automatically.

Evidence-backed execution

Your agent produces verified tests, decoded traces, or safe policies with zero hallucinations and explicit uncertainty flags.

Optional Developer Mailing List

Get notified when new Web3 agent skills drop

Join the developer updates list. No spam, just new testable workflows, Foundry tools, and agent prompts.

BEYOND OPEN-SOURCE SKILLS

Need these workflows running as autonomous production agents?

Spellbook builds and deploys dedicated Web3 AI agents for Telegram, Discord, treasury monitoring, and DeFi operations with escrow checkout, 48h turnaround, and full source code handover.

Browse 20+ Production Agents Commission Custom Build

Give your coding agent Web3 superpowers.

QUICK INSTALL (VERCEL SKILLS CLI)

$npx skills add theweb3wizard/spellbook-skills --list

✓ 100% Free & Open Source·✓ Zero Secret Handling·✓ Claude Code & Cursor Ready·✓ MIT License

How Web3 agent skills work

Install the skill pack

Run the npx skills command or copy the skill folder directly into your repo's .claude/skills/ or .agents/skills/ directory.

Prompt your agent

When you run into a revert, need an invariant test, or build an agent policy, your coding agent reads the skill rules automatically.

Evidence-backed execution

Your agent produces verified tests, decoded traces, or safe policies with zero hallucinations and explicit uncertainty flags.