guardian-check

guardian-check is a skill for Claude Code, Codex from rudimentall1/agentic-wallet-guardian-v3. It costs 121 tokens per session (966 once invoked), scanned A, original, MIT.

A safety check for MetaMask Agent Wallet commands that transfer funds or change blockchain state. It sends the proposed action to a separate Guardian service, which returns a decision but does not sign or execute the transaction.

In plain words
What is it for?
Use it before commands that send, swap, bridge, lend, borrow, repay, trade, or otherwise change on-chain positions through the MetaMask Agent Wallet CLI.
Why use it?
It adds an independent review of the intended action, its actual transaction details, and the agent's history before the wallet is allowed to proceed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it before commands that send, swap, bridge, lend, borrow, repay, trade, or otherwise change on-chain positions through the MetaMask Agent Wallet CLI.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rudimentall1/agentic-wallet-guardian-v3/guardian-check
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.

Any agent
npx skills add rudimentall1/agentic-wallet-guardian-v3 --skill guardian-check
Clone the repo
git clone --depth 1 https://github.com/rudimentall1/agentic-wallet-guardian-v3

Made for: Claude Code, Codex.

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 guardian-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/rudimentall1/agentic-wallet-guardian-v3/guardian-check/github.svg)](https://agentmods.dev/skills/rudimentall1/agentic-wallet-guardian-v3/guardian-check)
Your own site
<a href="https://agentmods.dev/skills/rudimentall1/agentic-wallet-guardian-v3/guardian-check"><img src="https://agentmods.dev/badge/skills/rudimentall1/agentic-wallet-guardian-v3/guardian-check/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.

agentmods 80×15 button for guardian-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/rudimentall1/agentic-wallet-guardian-v3/guardian-check"><img src="https://agentmods.dev/badge/skills/rudimentall1/agentic-wallet-guardian-v3/guardian-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 966 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00121 $0.00966
Opus 5 $0.00060 $0.00483
Sonnet 5 $0.00024 $0.00193
Haiku 4.5 $0.00012 $0.00097

Measured 12d ago against content hash a068d84353ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

guardian-check 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/guardian-check/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

guardian-check

MetaMask Agent Wallet's own Guard Mode / Beast Mode settings (spend limits, allowlists, threat scanning) apply the same static rules to every agent. Guardian adds a second, independent check: does this specific action look right for this agent, right now — comparing declared intent against actual calldata, this agent's own history, and an explainable policy engine — before the mm command is allowed to run at all.

Guardian has no access to private keys and never executes anything itself. It only returns a decision. MetaMask Agent Wallet remains the only thing that ever signs or broadcasts a transaction.

When to use this

Before running any mm command that moves funds or changes on-chain state. Map the command to the fields Guardian needs:

mm command action_type notes
mm send transfer target = recipient address
mm swap swap from_token/to_token from the swap args
mm bridge bridge
mm perps open/modify/close contract_call treat as a contract call against the perps protocol
mm predict trade contract_call
mm earn supply/withdraw contract_call
mm aave borrow/repay contract_call
mm pay (x402) transfer or contract_call depending on the resource being paid for

Do not run this check for read-only commands (mm balance, mm history, mm address, mm portfolio) — nothing to evaluate, they never move funds.

How to use this

  1. Build the intent from what the user/agent is about to do with mm: agent_id, wallet (the mm address), chain, action_type (from the table above), target, amount, from_token/to_token if relevant.

  2. Run:

    python scripts/check.py \
      --agent-id "<your agent's stable id>" \
      --wallet "<mm wallet address>" \
      --chain "<chain>" \
      --action-type "<mapped action_type>" \
      --amount <amount> \
      --target "<recipient or contract address>"
    

Read the full file on GitHub · 86 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 86 lines · 121 tokens per session scan A a068d84353ae

Subscribe to this mod's changes

guardian-check is a skill published in the GitHub repository rudimentall1/agentic-wallet-guardian-v3 (1 stars, last pushed 13d ago), licensed MIT. It adds 121 tokens to every session and 966 once invoked, about $0.0006 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.