What is vault-due-diligence?

A read-only research workflow for checking one DeFi vault, its manager, or its address before putting money into it. DeFi means financial services run on blockchain networks.

Use it to resolve a vault, review its risk evidence, and write due-diligence, underwriting, or incident notes before allocating funds.

It helps produce a risk report using only figures and identifiers returned by the connected Philidor data service, without guessing missing information or preparing a transaction.

vault-due-diligence — Skill for Cursor by Philidor-Labs/philidor-mcp

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 Philidor-Labs/philidor-mcp --skill vault-due-diligence

Clone the repo

git clone --depth 1 https://github.com/Philidor-Labs/philidor-mcp

Made for: Cursor.

Or install philidor, the plugin that ships this one along with the rest of its 6 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/philidor-labs/philidor-mcp/vault-due-diligence/github.svg)](https://agentmods.dev/skills/philidor-labs/philidor-mcp/vault-due-diligence)

Your own site

<a href="https://agentmods.dev/skills/philidor-labs/philidor-mcp/vault-due-diligence"><img src="https://agentmods.dev/badge/skills/philidor-labs/philidor-mcp/vault-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/philidor-labs/philidor-mcp/vault-due-diligence"><img src="https://agentmods.dev/badge/skills/philidor-labs/philidor-mcp/vault-due-diligence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 724 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.

Model	Per session	Once invoked
Fable 5.1	$0.00050	$0.00724
Opus 5.5	$0.00020	$0.00290
Sonnet 5.5	$0.00010	$0.00145
Haiku 4.5	$0.00005	$0.00072

Measured 19d ago against content hash e2ee7747a072, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vault-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 19d 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.

skills/vault-due-diligence/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vault due diligence

Philidor is read-only. It does not hold a wallet, compute a health factor, or prepare a transaction. Every score, tier, APR, TVL, and incident in the answer must come from a tool result in this turn. If a field is absent, say it was not returned. Never invent a risk number, address, or id.

The hosted server is https://mcp.philidor.io/api/mcp. If these tools are not connected, stop and say the Philidor MCP server is unavailable.

Resolve the vault first

If the user gave a vault id, or a network slug plus address, call get_vault with that pair. Lookup is id, or both network and address. EVM addresses are 0x hex. Solana addresses are case-sensitive base58.
If they gave only a name, curator, asset, or chain, call search_vaults (query, plus chain, protocol, asset, or riskTier when they named them). Pick a row only when the returned name, chain, and asset match the request. If several rows match, list the returned ids and ask which one. Do not guess an address.
Aave V4 vaults are protocol=aave and protocolVersion=v4. aave-v4 is an accepted alias. It is not a separate protocol id.

Then read the evidence

Call get_vault_risk_breakdown with the network and address from the get_vault result. The breakdown is four vectors: Asset Composition, Platform and Strategy, Control and Governance, and History.
When the vault payload includes a protocol id, call get_protocol_info with that id. When it includes a curator id, call get_curator_info with that id. Use the id string the tool returned.
To interpret a score the tools already returned, call explain_risk_score with that exact number (0–10). Read philidor://methodology before explaining how the score is built. Do not recite weights, caps, or tier cutoffs from memory.
If the client exposes MCP prompts, vault_due_diligence takes network and address and covers the same report.

What the report must contain

Vault id, network slug, and address, copied from the tool result.
Composite score, tier (Prime, Core, or Edge), and the four vector scores that were returned.
TVL, APR fields as labeled (keep base yield and rewards separate when both are present), audit or review status, and deposit status (open, closed, or unknown).
Recent events returned on the vault, plus protocol incidents returned by get_protocol_info.
A one-line limit: a higher Philidor score means lower assessed risk under the current methodology. It is not a safety guarantee, a return guarantee, or an allocation instruction.

Read the full file on GitHub · 37 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.

19d ago First seen · 37 lines · 50 tokens per session scan A e2ee7747a072

Subscribe to this mod's changes

vault-due-diligence is a skill published in the GitHub repository Philidor-Labs/philidor-mcp (5 stars, last pushed 19d ago), licensed MIT. It adds 50 tokens to every session and 724 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-01.

Finance and fintech Web3 and blockchain aave ai-tools claude crypto defi ethereum

vault-due-diligence

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Vault due diligence

Resolve the vault first

Then read the evidence

What the report must contain

What this file has done since we first saw it

Other skills, from other repositories

pump-swarm

trading-solana

copy-trading

trading-evm

whale-tracking

acp