web3-start-here

web3-start-here is a skill for Claude Code, Codex from Olaradiallysymmetrical491/web3-bug-bounty-hunting-ai-skills. It costs 36 tokens per session (592 once invoked), scanned A, a copy of web3-start-here, MIT.

An index for navigating a collection of guides about finding and validating security bugs in Web3 smart contracts, which are blockchain programs.

In plain words
What is it for?
Use it to find guidance on target selection, code searches, proof-of-concept exploits, report writing, research methods, AI tools, and Solidity auditing.
Why use it?
It shows the recommended reading order so an auditor can move from basic setup through bug patterns, exploit testing, reporting, and worked hunts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it to find guidance on target selection, code searches, proof-of-concept exploits, report writing, research methods, AI tools, and Solidity auditing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/olaradiallysymmetrical491/web3-bug-bounty-hunting-ai-skills/web3-start-here
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.

Any agent
npx skills add Olaradiallysymmetrical491/web3-bug-bounty-hunting-ai-skills --skill web3-start-here
Clone the repo
git clone --depth 1 https://github.com/Olaradiallysymmetrical491/web3-bug-bounty-hunting-ai-skills

Made for: Claude Code, Codex.

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.

agentmods badge for web3-start-here

README.md
[![agentmods](https://agentmods.dev/badge/skills/olaradiallysymmetrical491/web3-bug-bounty-hunting-ai-skills/web3-start-here/github.svg)](https://agentmods.dev/skills/olaradiallysymmetrical491/web3-bug-bounty-hunting-ai-skills/web3-start-here)
Your own site
<a href="https://agentmods.dev/skills/olaradiallysymmetrical491/web3-bug-bounty-hunting-ai-skills/web3-start-here"><img src="https://agentmods.dev/badge/skills/olaradiallysymmetrical491/web3-bug-bounty-hunting-ai-skills/web3-start-here/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.

agentmods 80×15 button for web3-start-here

Your own site · 80×15
<a href="https://agentmods.dev/skills/olaradiallysymmetrical491/web3-bug-bounty-hunting-ai-skills/web3-start-here"><img src="https://agentmods.dev/badge/skills/olaradiallysymmetrical491/web3-bug-bounty-hunting-ai-skills/web3-start-here.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 592 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 100% copy Near-identical to another mod 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.00592
Opus 5 $0.00018 $0.00296
Sonnet 5 $0.00007 $0.00118
Haiku 4.5 $0.00004 $0.00059

Measured 12d ago against content hash 42f0585e371d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

web3-start-here 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 12d 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.

Origin

This is a copy

100% identical to web3-start-here — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

web3-start-here/SKILL.md · 64 lines

What it actually says

WEB3 SKILLS — MASTER INDEX

Built from: 2,749 Immunefi reports + 100+ paid writeups + DeFiHackLabs (681 hacks) + ConsenSys + SlowMist + Trail of Bits + Foundry + Nethermind + Lido + AI agent research + live hunt experience


THE CHAIN (read in this exact order)

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

HOW TO USE THIS

  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

QUICK STATS

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

THE ONE RULE

"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

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.

  1. 12d ago First seen · 64 lines · 36 tokens per session scan A 42f0585e371d

Subscribe to this mod's changes

web3-start-here is a skill published in the GitHub repository Olaradiallysymmetrical491/web3-bug-bounty-hunting-ai-skills (5 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 592 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to web3-start-here, differing in 0 lines, and is treated as a copy.