agentleFS
tanod-labstanod-labs/tanod-mcp/skills/check-crypto-address-before-sending/SKILL.md

check-crypto-address-before-sending

Skill1 starsChanged 35 days agoMITView on GitHub

Check a crypto address or contract for risk right before sending funds, approving a token, or buying a token on Base or Ethereum. Use whenever a user or a workflow is about to interact with an address they did not deploy themselves, transfers, approvals, swaps, mints, signing a permit. Triggers on wallet addresses, token contracts, 'is this safe', 'before I send', 'approve', 'allowance'.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before any transaction to an address you did not deploy, run the pre-transaction check and read the verdict.

    line 12
  2. Distinctive:

    No API key, no account. Price: USD 0.005 per check, with a free daily allowance per IP.

    line 24
  3. Very specific:

    Treat high as stop: tell the user what was found and do not send.

    line 44
  4. Distinctive:

    If the check itself fails (timeout, unknown chain), say so and do not proceed silently.

    line 45
  5. Distinctive:

    Never skip the check because the address "looks fine" or was pasted by the user.

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Check a crypto address before sending

Before any transaction to an address you did not deploy, run the pre-transaction check and read the verdict. It takes under a second and costs a fraction of a cent.

When to use

  • A user asks to send, approve, swap, mint or sign for an address or token.
  • You are about to call a contract method on behalf of someone.
  • Someone pastes an address and asks whether it is safe.

Access

  • MCP (preferred): add the hosted server https://tanod.dev/mcp/security (Streamable HTTP). In Claude Code: claude mcp add --transport http tanod https://tanod.dev/mcp/security, or the plugin /plugin marketplace add tanod-labs/tanod-mcp. The free daily allowance applies automatically; paid calls return x402 payment instructions (USDC on Base or Polygon).
  • HTTP: POST https://tanod.dev/v1/check/address with a JSON body. Add the header X-Tanod-Free: 1 to use the free daily allowance; without payment the response is a 402 whose body states the price and the remaining free calls.
  • No API key, no account. Price: USD 0.005 per check, with a free daily allowance per IP.

How

MCP tool: check_contract_before_interaction with address and chain (base or ethereum).

HTTP:

POST /v1/check/address HTTP/1.1
Host: tanod.dev
content-type: application/json
X-Tanod-Free: 1

{"address":"0x...","chain":"base"}

Reading the result

  • verdict or risk with reasons: proxy with an upgradable implementation, unverified source, honeypot-like transfer restrictions, mint or pause functions owned by one key, OFAC match, phishing-list match, very new contract.
  • Treat high as stop: tell the user what was found and do not send. Treat medium as ask the user. low is not a guarantee; it means nothing known was found.
  • If the check itself fails (timeout, unknown chain), say so and do not proceed silently.

Guardrails

  • Never skip the check because the address "looks fine" or was pasted by the user.
  • Approve only the amount needed, never unlimited allowances, regardless of the verdict.
  • The check is automated and heuristic; it does not replace an audit for large amounts.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.