smart-contract-auditing

smart-contract-auditing is a skill for Claude Code, Codex from nirholas/three.ws. It costs 114 tokens per session (3,374 once invoked), scanned A, original, Apache-2.0.

A guide to reviewing smart contracts, the programs that run on blockchains, for security weaknesses. It covers manual review, automated scanners, fuzz testing, and common DeFi attack patterns.

In plain words
What is it for?
Use it to audit contract code, test attack scenarios, document findings, and check whether security fixes are complete.
Why use it?
It gives you a structured way to look for flaws that could let attackers steal funds or change the protocol's behaviour.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/nirholas/three.ws/smart-contract-auditing
Any agent
npx skills add nirholas/three.ws --skill smart-contract-auditing
Clone the repo
git clone --depth 1 https://github.com/nirholas/three.ws

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 smart-contract-auditing

README.md
[![agentmods](https://agentmods.dev/badge/skills/nirholas/three.ws/smart-contract-auditing.svg)](https://agentmods.dev/skills/nirholas/three.ws/smart-contract-auditing)
Your own site
<a href="https://agentmods.dev/skills/nirholas/three.ws/smart-contract-auditing"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/smart-contract-auditing.svg" alt="Measured on agentmods" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,374 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00114 $0.03374
Opus 5 $0.00057 $0.01687
Sonnet 5 $0.00023 $0.00675
Haiku 4.5 $0.00011 $0.00337

Measured 2d ago against content hash 8c9861a068c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

smart-contract-auditing 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.

data/skills/security/smart-contract-auditing/SKILL.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Smart Contract Auditing — From Zero to Expert

This skill teaches you to think like a top-tier smart contract auditor. You'll learn to find vulnerabilities that automated tools miss, write clear findings, and reason about protocol-level risks in DeFi systems.

The Auditor's Mindset

"Your job is not to confirm the code works. It's to prove it can break."

An auditor must think adversarially. Every function is a potential attack surface. Every external call is a trust boundary. Every assumption is a vulnerability waiting to happen.

┌─────────────────────────────────────────────────┐
│              AUDITOR'S MENTAL MODEL              │
├─────────────────────────────────────────────────┤
│                                                  │
│   1. UNDERSTAND the protocol's invariants        │
│   2. ENUMERATE every state-changing path         │
│   3. CHALLENGE every assumption                  │
│   4. SIMULATE adversarial scenarios              │
│   5. VERIFY mitigations are complete             │
│                                                  │
│   "What must ALWAYS be true?" ← start here       │
│   "How can I make it false?" ← then ask this     │
│                                                  │
└─────────────────────────────────────────────────┘

Vulnerability Taxonomy

Tier 1 — Critical (Funds at Risk)

Vulnerability What Breaks Classic Example
Reentrancy State updated after external call The DAO hack ($60M)
Flash Loan Attack Price oracle manipulation in single tx bZx ($8M), Cream ($130M)
Access Control Missing onlyOwner / role checks Parity wallet freeze ($280M)
Unchecked Return Values Silent failure on transfer Token transfers returning false
Storage Collision Proxy upgrades overwriting slots Audius governance ($6M)

Tier 2 — High (Protocol Malfunction)

Vulnerability What Breaks How to Spot
Oracle Manipulation Price feeds return stale/wrong data Check updatedAt staleness
Integer Overflow/Underflow Math wraps around (pre-0.8.0) Solidity < 0.8 without SafeMath
Front-running MEV bots sandwich user txs Unprotected swaps, auctions
Denial of Service Unbounded loops, gas griefing Arrays that grow without limit
Signature Replay Same sig reused across chains/contracts Missing nonce or chainId

Read the full file on GitHub · 387 lines

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. 2d ago First seen · 387 lines · 114 tokens per session scan A 8c9861a068c7

Subscribe to this mod's changes

smart-contract-auditing is a skill published in the GitHub repository nirholas/three.ws (110 stars, last pushed today), licensed Apache-2.0. It adds 114 tokens to every session and 3,374 once invoked, about $0.0006 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 2026-09-03.

Related

Other skills, from other repositories

blender-mcp

Drive Blender via the catalog blender MCP, with bpy recipes.

GGbond-bo/MemOmics-Agent · 17 tokens

blender-mcp

Control Blender directly from Gauss via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.

math-inc/OpenGauss · 54 tokens

threejs-docs

Comprehensive Three.js reference covering core API (objects, cameras, lights, materials, geometries, renderers, scenes, textures, math, animation, audio, loaders, helpers, nodes), all addons (controls, postprocessing, loaders, exporters, geometries, shaders, WebXR, physics), TSL (Three.js Shading Language) functions…

pledgeandgrow/pledge-skills · 112 tokens

blender-mcp

Control Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.

raphaelmansuy/edgecrab · 53 tokens

blender-mcp

Control Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.

johnson7788/MultiUserClaw · 53 tokens

3d-website-architect

Expert skill for designing, building, and deploying modern premium websites with advanced animations and 3D interactive experiences using Three.js, React Three Fiber, GSAP, and Framer Motion. Use this skill whenever the user wants to build a website with 3D elements, create an immersive web experience, add interactive…

deveshpunjabi/3d-website-skill · 240 tokens