What is pre-deposit-safety-check?

A read-only safety check for a planned deposit into a DeFi vault or a collateral-and-debt loop. DeFi uses blockchain-based financial services, and a loop repeatedly borrows and supplies assets to increase exposure.

Use it to find depositable vaults, inspect their risk breakdown and incidents, explain a reported score, or review a loop venue.

It helps inspect the venue's reported risk and deposit status before funds are committed, without calculating unsupported figures or creating a transaction.

pre-deposit-safety-check — Skill for Cursor by Philidor-Labs

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 pre-deposit-safety-check

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/pre-deposit-safety-check/github.svg)](https://agentmods.dev/skills/philidor-labs/philidor-mcp/pre-deposit-safety-check)

Your own site

<a href="https://agentmods.dev/skills/philidor-labs/philidor-mcp/pre-deposit-safety-check"><img src="https://agentmods.dev/badge/skills/philidor-labs/philidor-mcp/pre-deposit-safety-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.

Your own site · 80×15

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

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 828 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	$0.00052	$0.00828
Opus 5.5	$0.00021	$0.00331
Sonnet 5.5	$0.00010	$0.00166
Haiku 4.5	$0.00005	$0.00083

Measured 16d ago against content hash 869fa4fc3ed1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pre-deposit-safety-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 16d 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/pre-deposit-safety-check/SKILL.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-deposit safety check

Use this before a deposit into a vault or a collateral/debt loop. Philidor underwrites the venue. It does not compute health factor and it does not prepare transactions. Quote only figures and ids returned in this turn. Never invent a risk number.

The hosted server is https://mcp.philidor.io/api/mcp.

Vault deposit

Call search_vaults with the asset, chain, and protocol the user named. Set depositable to true when they need a vault that can still take deposits. riskTier is Prime, Core, or Edge. limit defaults to 10 and caps at 50. Say so when the list is a sample.
Read the deposit line on each row. closed means maxDeposit is zero. unknown means on-chain status was not probed. When depositable is true, vaults whose depositability is not yet indexed can still appear. Do not treat unknown or an unindexed row as open.
For the chosen row, call get_vault and get_vault_risk_breakdown with the returned network and address (or get_vault by returned id).
Call explain_risk_score with the returned composite score. Read philidor://methodology if you explain vectors.
Check events on get_vault. list_vaults_with_incidents is a separate global list of critical incidents in the last 365 days. Absence from that list is not proof of a clean history. Say which call you made.
find_safest_vaults returns at most 10 audited vaults sorted by score (higher means lower assessed risk). It is a screen, not the full market, and not a safety guarantee.

Report the vault id, network, address, score, tier, TVL, APR labels, and deposit status from those results. Stop if the user asked you to send a transaction.

Loop (collateral posted, debt borrowed)

If the user did not give a market id, call list_markets first. Aave V4 is protocol=aave and version=v4 (aave-v4 is an accepted alias). Vault search uses protocolVersion; this tool uses version. Chain is an integer id (1, 8453) or a slug (ethereum, solana).
Call check_loop_venue with the marketId from that list plus the collateral and debt symbols the user named (weETH, USDC, and so on). Required arguments are marketId, collateral, and debt.
Report, from that result only: score, tier, utilization, borrow APR, deposit status, and recent incidents for both legs. Also report whether both reserves exist. Closed or unknown deposits are not executable. Headline APR alone is not a venue choice.
Philidor stops there. For wallet health factor, preview_action, or prepare_action, hand off to the protocol MCP (Aave is https://mcp.aave.com). Do not invent those figures here.
If the client exposes MCP prompts, review_loop_venue takes the same marketId, collateral, and debt.

Read the full file on GitHub · 35 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.

16d ago First seen · 35 lines · 52 tokens per session scan A 869fa4fc3ed1

Subscribe to this mod's changes

pre-deposit-safety-check is a skill published in the GitHub repository Philidor-Labs/philidor-mcp (5 stars, last pushed 16d ago), licensed MIT. It adds 52 tokens to every session and 828 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

pre-deposit-safety-check

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

Pre-deposit safety check

Vault deposit

Loop (collateral posted, debt borrowed)

What this file has done since we first saw it

Other skills, from other repositories

trading-solana

pump-swarm

copy-trading

trading-evm

whale-tracking

acp