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 metis-rwa/mcp --skill due-diligencegit clone --depth 1 https://github.com/metis-rwa/mcpWrote 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/metis-rwa/mcp/due-diligence)<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.
<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>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 | $0.00041 | $0.00599 |
| Opus 5 | $0.00020 | $0.00300 |
| Sonnet 5 | $0.00008 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
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.
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
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.
- 10d ago First seen · 64 lines · 0 tokens per session scan A b9da8ce943be
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.
Other skills, from other repositories
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
bridge
Cross-chain token transfers using Wormhole and CCTP.
hyperliquid
Hyperliquid L1 perps DEX (69% market share).
marginfi
MarginFi — Solana lending and borrowing.
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…
trading-signal
Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for…