bb-methodology
The "3rd eye" for pentesting — reminds agent to understand before assuming, validate before…
Master index for the web3 smart contract security knowledge base. Use this to navigate the skill chain. Read files in order — each ends with NEXT.
$ npx -y skills add Gabson0x/bountyforge --skill web3-start-here --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/web3-start-hereContext preview
The summary Claude sees to decide when to auto-load this skill.
Master index for the web3 smart contract security knowledge base. Use this to navigate the skill chain. Read files in order — each ends with NEXT.
name: web3-start-here description: Master index for the web3 smart contract security knowledge base. Use this to navigate the skill chain. Read files in order — each ends with NEXT.
Built from: 2,749 Immunefi reports + 100+ paid writeups + DeFiHackLabs + ConsenSys + SlowMist + Trail of Bits.
See also: [[Web3 Audit]], [[Methodology]], [[Trust Map]], [[Web3 Bug Classes]], [[Web3 Hunt Foundation]]
---
00-START-HERE.md ← YOU ARE HERE 01-foundation.md ← Mindset, target selection, recon setup 02-bug-classes.md ← All 10 bug classes with patterns + real examples 03-grep-arsenal.md ← Master grep patterns for every class 04-poc-and-foundry.md ← Foundry PoC writing, cheatcodes, 18 exploit templates 05-triage-report-examples.md ← 7-Question Gate, report format, 20 real paid examples 06-methodology-research.md ← ToB, SlowMist, ConsenSys, Immunefi, Cyfrin, Lido, Nethermind 07-live-hunt-ern.md ← Completed hunt: Ern protocol (2 findings) 09-live-hunt-zksync.md ← Completed hunt: ZKsync Era (0 findings — defense study) 08-ai-tools.md ← Shannon, LuaN1ao, SmartGuard, CAI Framework, AI code hunting 36-solidity-audit-mcp.md ← MCP server: Slither+Aderyn+SWC in Claude Code
---
1. Read one file fully — every section 2. At the bottom: follow → NEXT 3. **After file 05**: you can hunt independently 4. **Files 06-08**: advanced tools + active work 5. **File 36**: MCP integration for live scanning
---
| Metric | Number | |--------|--------| | Immunefi reports analyzed | 2,749 | | Protocols covered | 51 | | Critical reports | 406 | | High reports | 616 | | Total paid by Immunefi | $100M+ | | Avg critical payout | $50K–$2M | | Nethermind reports analyzed | 166 | | DeFiHackLabs hacks reproduced | 681 |
---
> "Read ALL sibling functions. If `vote()` has a modifier, check `poke()`, `reset()`, `harvest()`. The missing modifier on the sibling IS the bug."
This single rule explains 19% of all Critical findings.
---
→ NEXT: [01-foundation.md](01-foundation.md)
All-round bug bounty skill for Claude Code — parallelized agents for smart contract audits (EVM, Move, Solana, TRON), web/API security, local tooling orchestration, and submission-ready reports for HackerOne, Bugcrowd, Intigriti & Immunefi.
Repo: Gabson0x/bountyforge
The "3rd eye" for pentesting — reminds agent to understand before assuming, validate before…
Complete bug bounty workflow — recon (subdomain enumeration, asset discovery, fingerprinting,…
Analyze EVM smart contracts for storage-safety vulnerabilities that can cause persistent…
Generate Echidna/Medusa-compatible Solidity fuzz suites from Foundry or Hardhat projects.…
Convert English-language properties in PROPERTIES.md (produced by the Fizz skill) into…