safe-hunt

safe-hunt is a skill for Claude Code, Codex from forefy/.context. It costs 92 tokens per session (1,323 once invoked), scanned A, original, MIT.

A read-only auditor for Safe multisig wallets, shared crypto wallets that require approval from several owners. It uses live blockchain configuration and transaction history to check governance settings and rank possible weaknesses.

In plain words
What is it for?
Use it to audit one or more Safe addresses, investigate a DeFi protocol’s Safes, or sweep discovered protocol wallets for owner, threshold, transaction, and governance misconfigurations.
Why use it?
It provides evidence for each suspected issue and avoids calling something exploitable without confirming it on-chain. It does not send transactions or change wallet state.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

Good fit Use it to audit one or more Safe addresses, investigate a DeFi protocol’s Safes, or sweep discovered protocol wallets for owner, threshold, transaction, and governance misconfigurations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/forefy/.context/safe-hunt
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 forefy/.context --skill safe-hunt
Clone the repo
git clone --depth 1 https://github.com/forefy/.context

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 safe-hunt

README.md
[![agentmods](https://agentmods.dev/badge/skills/forefy/.context/safe-hunt.svg)](https://agentmods.dev/skills/forefy/.context/safe-hunt)
Your own site
<a href="https://agentmods.dev/skills/forefy/.context/safe-hunt"><img src="https://agentmods.dev/badge/skills/forefy/.context/safe-hunt.svg" alt="Measured on agentmods" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,323 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00092 $0.01323
Opus 5 $0.00046 $0.00661
Sonnet 5 $0.00018 $0.00265
Haiku 4.5 $0.00009 $0.00132

Measured 8d ago against content hash c636b616974c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

safe-hunt 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/sweep.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/blockchain/safe-hunt/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Safe Governance Hunt Skill

Identity

Protocol governance security analyst. Systematically assess Safe multisig configurations across DeFi protocols using live on-chain data via the Safe Transaction Service API. No auth required. Read-only - never send transactions, never modify state. Findings are ranked by severity and formatted as audit-ready report items. Ambiguous findings → document with evidence and flag for manual review. Never conclude "exploitable" without on-chain confirmation.


Reference Files

Load on demand:

File Load When
references/safe-api.md Making any Safe API call - endpoints, base URLs, response shapes
references/finding-patterns.md Scoring any Safe - full criteria, severity thresholds, audit language
references/defillama-discovery.md Mode = sweep or protocol - how to extract Safe addresses from DeFiLlama

Modes

Mode 1: Targeted

Input: one or more Safe addresses + optional network (default: ethereum). → Deep audit of each Safe: config + 50 most recent txs + full finding set.

Mode 2: Protocol

Input: protocol name (e.g. "Aave", "Compound"). → Look up protocol in DeFiLlama treasury adapters → extract Safe addresses → run targeted audit on each.

Mode 3: Sweep

Input: "sweep all" or no address given. → Parse all ~292 DeFiLlama treasury adapters → extract all Safe addresses → run targeted audit on each → output ranked leaderboard by risk score.


Engagement Protocol

Step 0 - Determine mode:

  • Address(es) provided → Mode 1 (Targeted)
  • Protocol name provided → Mode 2 (Protocol) - load references/defillama-discovery.md
  • "sweep", "all protocols", or no input → Mode 3 (Sweep) - load references/defillama-discovery.md
  • If unclear, ask: "Do you want to audit a specific Safe address, a named protocol, or sweep all DeFiLlama protocols?"

Read the full file on GitHub · 133 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 133 lines · 92 tokens per session scan A c636b616974c

Subscribe to this mod's changes

safe-hunt is a skill published in the GitHub repository forefy/.context (144 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 1,323 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

web3-audit

Smart contract security audit — 10 DeFi bug classes (accounting desync, access control, incomplete path, off-by-one, oracle, ERC4626, reentrancy, flash loan, signature replay, proxy), pre-dive kill signals (TVL < $500K etc), Foundry PoC template, grep patterns for each class, and real Immunefi paid examples. Use for…

Awarexone/Agentic-Bug-Hunter · 103 tokens

meme-coin-audit

Meme coin and token security audit — rug pull detection (honeypot, hidden mint, fee manipulation, LP lock bypass), Solana SPL token analysis (freeze authority, mint authority, metadata mutability), Token-2022 extension risks (transfer hooks, permanent delegate), DEX liquidity pool attacks (sandwich amplification, LP…

Awarexone/Agentic-Bug-Hunter · 129 tokens

authoring-godot-prompter-skills

Use when writing or editing a SKILL.md or an agent definition in this repo — required frontmatter, section ordering, and the GDScript-then-C# example convention.

jame581/GodotPrompter · 47 tokens

hr-blockchain

Help HR and recruiting teams hire and screen blockchain and Web3 engineering candidates (smart contracts, protocol engineering, cryptography). Use when asked to write a blockchain engineer job description, create smart contract interview questions, assess a Web3 candidate, build a blockchain role leveling framework…

tuanductran/hr-skills · 65 tokens

defi-trading-systems

Designs DeFi trading systems for perpetual futures, liquidity provision, and automated strategies with risk management and MEV protection.

organvm-iv-taxis/a-i--skills · 31 tokens

clawild-moltbook

Use when autonomous crypto intelligence agent for Moltbook — blockchain analysis, social sentiment tracking, and real-time alpha detection. Use when working with clawild moltbook.

oyi77/1ai-skills · 40 tokens