due-diligence

due-diligence is a skill for Claude Code from metis-rwa/mcp. It costs 41 tokens per session (599 once invoked), scanned A, original, MIT.

A step-by-step review of a tokenized real-world asset, such as a digital token representing an asset outside the blockchain. It examines issuer controls, supply, ownership concentration, trading liquidity, price differences, and existing research.

In plain words
What is it for?
Investigating a named token’s minting, freezing, supply, major holders, market depth, exit costs, premium or discount, and published research.
Why use it?
It organizes the checks needed to understand who controls the token, how much exists, who holds it, and how easily it may be traded. It also explains what those findings mean for a holder.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the metis plugin — 3 skills, 1 MCP server shipped together

Good fit Investigating a named token’s minting, freezing, supply, major holders, market depth, exit costs, premium or discount, and published research.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/metis-rwa/mcp/due-diligence
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 metis-rwa/mcp --skill due-diligence
Clone the repo
git clone --depth 1 https://github.com/metis-rwa/mcp

Made for: Claude Code.

Or install metis, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

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 due-diligence

README.md
[![agentmods](https://agentmods.dev/badge/skills/metis-rwa/mcp/due-diligence/github.svg)](https://agentmods.dev/skills/metis-rwa/mcp/due-diligence)
Your own site
<a href="https://agentmods.dev/skills/metis-rwa/mcp/due-diligence"><img src="https://agentmods.dev/badge/skills/metis-rwa/mcp/due-diligence/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 due-diligence

Your own site · 80×15
<a href="https://agentmods.dev/skills/metis-rwa/mcp/due-diligence"><img src="https://agentmods.dev/badge/skills/metis-rwa/mcp/due-diligence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 599 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 $0.00041 $0.00599
Opus 5 $0.00020 $0.00300
Sonnet 5 $0.00008 $0.00120
Haiku 4.5 $0.00004 $0.00060

Measured 10d ago against content hash b9da8ce943be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

due-diligence 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 10d 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.

plugin/skills/due-diligence/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Due diligence on $ARGUMENTS

Work the asset named in $ARGUMENTS through every step below, in order, and report what you find at each one. If no asset was named, call list_rwa_assets and ask which one.

Run the steps as you go rather than collecting everything and summarizing at the end. Each answer should be readable on its own.

1. Who controls it

get_token_controls. State plainly whether the issuer can mint, freeze, seize, pause, or gate transfers, and what each of those means for a holder. Do not editorialize: a backed asset needs most of these powers.

2. What exists

get_token_supply. Is supply capped or open? For a backed asset, this is the number the reserves have to cover.

3. Who holds it

get_holder_concentration. Report the top-5 and top-10 share and the holder wallet count. Then say which of the top accounts look like pools, bridges, or custodians rather than investors, because concentration among venues means something very different from concentration among holders.

4. Could you get out

get_token_market. Compare pooled liquidity against the size someone might actually hold. Say what a meaningful exit would cost in slippage terms, and whether volume suggests anyone is trading it at all. If the tool returns the partial view, say which numbers are missing rather than working around it.

5. What is it worth right now

get_reference_premium. Is the token trading away from the security it tracks? Before calling a gap an opportunity, check whether it is explainable: the reference price is republished by a third party and goes stale outside market hours, which alone produces a premium nobody can capture.

6. What has already been observed

observe_asset for the current cycle against stored history, then list_research filtered to this asset for anything the research agent has published on it. get_research on the most relevant object gives you its claims with the evidence each one rests on.

Finish with conditions, not a verdict

Read the full file on GitHub · 64 lines

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. 10d ago First seen · 64 lines · 0 tokens per session scan A b9da8ce943be

Subscribe to this mod's changes

due-diligence is a skill published in the GitHub repository metis-rwa/mcp (0 stars, last pushed 29d ago), licensed MIT. It adds 41 tokens to every session and 599 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.