rugcheck-ai AGENTS.md

rugcheck-ai AGENTS.md is an instructions file for Codex, OpenCode from MrWizardlyLoaf/rugcheck-ai. It costs 511 tokens per session, scanned A, original, MIT.

Instructions for a Solana token-safety service. Solana is a blockchain network, and a token-safety check looks for signs that a token may be fraudulent or impossible to sell.

In plain words
What is it for?
Use it to check a token before trading, test whether it can be sold, review its authorities and holders, inspect liquidity, and prepare an unsigned buy transaction routed through Jupiter.
Why use it?
It helps reduce the risk of trading a token with hidden controls, low liquidity, concentrated ownership, or other warning signs.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is 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 instructions/mrwizardlyloaf/rugcheck-ai/agents-md
Clone the repo
git clone --depth 1 https://github.com/MrWizardlyLoaf/rugcheck-ai

Made for: Codex, OpenCode.

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 rugcheck-ai AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mrwizardlyloaf/rugcheck-ai/agents-md.svg)](https://agentmods.dev/instructions/mrwizardlyloaf/rugcheck-ai/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mrwizardlyloaf/rugcheck-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/mrwizardlyloaf/rugcheck-ai/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 511 This file is loaded in full into every session.
When invoked 511 The same file — it is already loaded in full.
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 $0.00511 $0.00511
Opus 5 $0.00255 $0.00255
Sonnet 5 $0.00102 $0.00102
Haiku 4.5 $0.00051 $0.00051

Measured 5d ago against content hash e2edc63727f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

rugcheck-ai AGENTS.md 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.

AGENTS.md · 46 lines

What it actually says

RugCheck AI — agent guide

On-chain token-safety MCP for Solana. Screen a token for rug/honeypot traps before trading, then execute the buy — re-screened, and routed through Jupiter with a small Jito tip for inclusion. The execution tool returns an unsigned transaction; you sign it, the server never holds keys.

Connect (no install)

Remote MCP endpoint (Streamable HTTP):

https://web-production-58d585.up.railway.app/mcp

Listed on the official MCP Registry as io.github.MrWizardlyLoaf/rugcheck-ai.

Tools

  • scan_token(mint) — full safety report in one call (verdict, 0–100 score, all risks)
  • is_safe(mint) — quick yes/no gate: one boolean before trading
  • verify_token_safety(mint) — on-chain audit: mint/freeze authority + Token-2022 traps
  • check_authorities(mint) — authority + extension detection
  • simulate_sell(mint) — can the token be sold? (honeypot check)
  • simulate_trade(mint, amount_usd) — round-trip buy→sell: real entry/exit cost & loss %
  • check_liquidity(mint) — DEX liquidity, 24h volume, pair age
  • holders_breakdown(mint) — top-holder concentration (dump risk)
  • token_age(mint) — freshness + real trading activity
  • rug_forecast(mint) — heuristic rug probability + urgency window
  • scammer_dna(mint) — intent score (0–100) from structural scam signals
  • check_deployer(mint) — the wallets holding power over the token
  • compare_tokens(mints) — rank a basket of tokens safest-first
  • batch_scan(mints) — scan up to 10 tokens at once, one report each
  • execute_safe_swap(mint, wallet, amount_usd) — re-screens, returns an unsigned USDC→token swap to sign

Source & stack

Built with Python (FastMCP). Entry point: server.py. The screening tools are read-only — they call Solana getAccountInfo and never touch your keys.

Self-host

pip install -r requirements.txt
SOLANA_RPC=<your-rpc-url> python server.py
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 · 46 lines · 511 tokens per session scan A e2edc63727f9

Subscribe to this mod's changes

rugcheck-ai AGENTS.md is an instructions file published in the GitHub repository MrWizardlyLoaf/rugcheck-ai (1 stars, last pushed 2mo ago), licensed MIT. It adds 511 tokens to every session, about $0.0026 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.