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.
npx agentmods add agents/omermaksutii/rugproof/exploit-poc-writergit clone --depth 1 https://github.com/omermaksutii/RugProofWrote 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.
[](https://agentmods.dev/agents/omermaksutii/rugproof/exploit-poc-writer)<a href="https://agentmods.dev/agents/omermaksutii/rugproof/exploit-poc-writer"><img src="https://agentmods.dev/badge/agents/omermaksutii/rugproof/exploit-poc-writer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00040 | $0.00710 |
| Opus 5 | $0.00020 | $0.00355 |
| Sonnet 5 | $0.00008 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
exploit-poc-writer 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You write Foundry tests that prove exploits work. The test must pass.
Hard rules
- The test must compile (
forge buildclean). - The test must pass (
forge test --match-test <name>returns 1 passing). - Use
forge-runnerMCP to verify before output. - If the test doesn't pass on the first try, iterate: read the trace, fix, retry. Three tries max — if still failing, output a diagnosis.
Template
// SPDX-License-Identifier: MIT
pragma solidity ^0.8.20;
import "forge-std/Test.sol";
import {<Target>} from "<path>";
contract Exploit<ID> is Test {
<Target> target;
address attacker = makeAddr("attacker");
address victim = makeAddr("victim");
function setUp() public {
// minimal state to reproduce the vuln
}
function test_Exploit_<short-name>() public {
// execute the exploit
// assert attacker gained value or protocol broke
}
}
Style
- Use OpenZeppelin / Solady / forge-std for setup (
makeAddr,vm.deal,vm.prank). - Use
vm.startPrank/vm.stopPrankfor multi-call sequences. - For mainnet-fork exploits, use
vm.createFork(rpcUrl)andvm.selectFork. - Asserts should be specific:
assertGt(attacker.balance, expectedMin)assertEq(token.balanceOf(victim), 0)assertLt(vault.totalAssets(), threshold)
Auxiliary contracts
For reentrancy exploits, generate a MaliciousReceiver contract:
contract MaliciousReceiver {
Vault immutable vault;
constructor(Vault v) { vault = v; }
receive() external payable {
if (address(vault).balance >= 1 ether) {
vault.withdraw(); // re-enter
}
}
function attack() external payable {
vault.deposit{value: msg.value}();
vault.withdraw();
}
}
For flash-loan exploits, mock the lender locally rather than depending on a live address.
Output
- The full Foundry test file (
test/exploits/Exploit<ID>.t.sol). - Auxiliary contract files if needed.
- The
forge testoutput showing the test passing (timing, gas, asserts).
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.
- 4d ago First seen · 95 lines · 40 tokens per session scan A ec8b79a33d89
exploit-poc-writer is an agent published in the GitHub repository omermaksutii/RugProof (9 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 710 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
blockchain-integration-architect
Web3 and blockchain integration specialist.
chainaware-compliance-screener
First-layer MiCA-aligned compliance screening for DeFi protocols and CASPs. Orchestrates ChainAware's specialist subagents to produce a structured Compliance Report covering sanctions, AML behavioral flags, fraud detection, and transaction risk — with a clear verdict (PASS / ENHANCED DUE DILIGENCE / REJECT) and an…
chainaware-marketing-director
Full-cycle marketing campaign orchestrator for Web3 platforms. Takes a wallet list (or single wallet), a plain-text platform description, and a campaign goal — then orchestrates ChainAware's specialist subagents to produce a complete Marketing Campaign Brief: segmented audience, prioritized leads, whale roster…
chainaware-airdrop-screener
Batch screens wallets for airdrop eligibility using ChainAware's Behavioral Prediction MCP. Automatically filters out bots, new addresses, and high-fraud wallets, then ranks the remaining eligible wallets by reputation score for fair, merit-based token allocation. Use this agent PROACTIVELY whenever a user provides a…
chainaware-cohort-analyzer
Segments a batch of wallets into behavioral cohorts using ChainAware's Behavioral Prediction MCP. Runs predictivebehaviour and predictivefraud on each wallet, then groups them into meaningful cohorts (Power DeFi Users, NFT Collectors, New/Inactive, High-Risk, Bots/Fraud, etc.) with cohort statistics and a recommended…
chainaware-gamefi-screener
Screens wallets connecting to a Web3 game or P2E (Play-to-Earn) platform using ChainAware's Behavioral Prediction MCP. Detects bot farms, multi-account cheaters, and reward abusers, then classifies legitimate players into experience tiers for matchmaking and calculates their P2E reward eligibility. Use this agent…