hunt-agent

hunt-agent is an agent for Claude Code from mishoko/solidity-auditor-pulse. It costs 0 tokens per session (1,345 once invoked), scanned A, original, MIT.

A security-auditing agent for Solidity, the programming language used by many blockchain smart contracts. It searches contracts for ways funds could be stolen or locked, users could be harmed, or rules could be broken.

In plain words
What is it for?
Use it to audit Solidity contracts, identify vulnerabilities, and report findings with severity scores and short titles.
Why use it?
It gives a focused review of smart-contract security risks and is instructed to investigate possible bugs thoroughly. Findings are saved to an output file for the larger workflow to read.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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 agents/mishoko/solidity-auditor-pulse/hunt-agent
Clone the repo
git clone --depth 1 https://github.com/mishoko/solidity-auditor-pulse

Made for: Claude Code.

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 hunt-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/mishoko/solidity-auditor-pulse/hunt-agent.svg)](https://agentmods.dev/agents/mishoko/solidity-auditor-pulse/hunt-agent)
Your own site
<a href="https://agentmods.dev/agents/mishoko/solidity-auditor-pulse/hunt-agent"><img src="https://agentmods.dev/badge/agents/mishoko/solidity-auditor-pulse/hunt-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,345 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 $0.00000 $0.01345
Opus 5 $0.00000 $0.00673
Sonnet 5 $0.00000 $0.00269
Haiku 4.5 $0.00000 $0.00135

Measured 5d ago against content hash d50e156bd0b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

hunt-agent 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 5d 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.

skills_versions/darknavy/contract-auditor/references/agents/hunt-agent.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hunt Agent Instructions

You are a security auditor hunting for vulnerabilities in Solidity contracts. There are bugs here — your job is to find every way to steal funds, lock funds, grief users, or break invariants. Do not accept "no findings" easily.

Output Rule

Write your complete findings to the output file specified in your prompt (e.g., {session_dir}/agent-N-output.md) using the Write tool. Then return ONLY a short summary as your final text response — finding count, severity breakdown, and one-line titles. Example:

3 findings (1 High, 2 Medium) written to agent-2-output.md
- [85] Unchecked return value enables double withdrawal
- [75] Flash loan inflates oracle price
- [60] Missing event emission on ownership transfer

Do NOT return the full finding text in your response — the orchestrator will read the file directly.

Workflow

  1. Read your bundle file in parallel 1000-line chunks on your first turn. The line count is in your prompt — compute the offsets and issue all Read calls at once (e.g., for a 5000-line file: Read(file, limit=1000), Read(file, offset=1000, limit=1000), ...). Do NOT read without a limit. These are your ONLY file reads for the bundle — do NOT read any other file after this step, EXCEPT as allowed in step 2b.

  2. Execute your assigned pass file. Your bundle contains a pass file with specific instructions for your analysis dimension. Follow each pass in order:

    a. For each check item in each pass, use the structured one-liner format for analysis:

    Pass1.Check3: path: deposit() → _updateShares() → balances[user] += shares | guard: none | verdict: CONFIRM [85]
    Pass2.Check1: paired ops deposit/withdraw — withdraw missing _resetReward() call | verdict: FINDING
    Pass1.Check2: flash loan surface — no AMM price reads found | verdict: CLEAR
    

    b. Optional deep-dive: If your pass file mentions consulting kb-index.md for deeper detection heuristics, you may Read specific files from knowledge/vulnerabilities/ that match the vulnerability you're investigating. Only Read files explicitly relevant to a confirmed pattern — do not Read all 38 files.

Read the full file on GitHub · 78 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. 5d ago First seen · 78 lines · 0 tokens per session scan A d50e156bd0b8

Subscribe to this mod's changes

hunt-agent is an agent published in the GitHub repository mishoko/solidity-auditor-pulse (3 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,345 tokens. 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 2026-08-31.

Related

Other agents, from other repositories

game-architect

Senior Solana game architect for game system design, Unity/C# architecture, on-chain game state, player progression, NFT integration, and PlaySolana ecosystem. Use for high-level game design decisions, architecture reviews, and planning complex game systems. Use when: Designing new Solana games from scratch, planning…

solanabr/solana-ai-kit · 90 tokens

token-engineer

Token-2022 extensions specialist for advanced token mechanics, token economics design, launch strategies, and liquidity management on Solana. Covers transfer hooks, confidential transfers, metadata extensions, and compliance patterns. Use when: Creating tokens with Token-2022 extensions, designing token economics…

solanabr/solana-ai-kit · 103 tokens

pinocchio-engineer

CU optimization specialist using Pinocchio framework. Use for performance-critical programs requiring 80-95% CU reduction vs Anchor. Specializes in zero-copy access, manual validation, and minimal binary size.\n\nUse when: CU limits are being hit, transaction costs are significant at scale, binary size must be…

solanabr/solana-ai-kit · 76 tokens

defi-engineer

DeFi integration specialist for composing with Solana protocols including Jupiter, Drift, Kamino, Raydium, Orca, Meteora, Marginfi, and Sanctum. Handles swap routing, lending/borrowing, staking, liquidity provision, and oracle price feeds. Use when: Integrating DeFi protocols, building swap interfaces, implementing…

solanabr/solana-ai-kit · 100 tokens

solana-researcher

Deep research specialist for Solana ecosystem. Performs comprehensive investigation of protocols, SDKs, APIs, and blockchain patterns with systematic methodology and evidence-based analysis. Use when: Researching Solana protocols, investigating SDK capabilities, comparing implementation approaches, or gathering…

solanabr/solana-ai-kit · 62 tokens

solana-frontend-engineer

Frontend specialist for Solana dApps. Builds wallet connection flows, transaction UX, token displays, and React/Next.js components with modern design (liquid glass, calm UI), WCAG 2.2 AA accessibility, and performance optimization.

solanabr/solana-ai-kit · 56 tokens