What is risk-adjusted-yield?

A read-only workflow for comparing the yield and reported risk information of DeFi vaults. APR is the stated annual percentage return, while TVL means the total value held in a vault.

Use it to search and filter vaults, compare finalists, and identify whether deposits are currently available using Philidor results.

It keeps yield beside the risk score, risk tier, TVL, and deposit status, rather than inventing a combined risk-adjusted number or treating unknown deposit status as open.

risk-adjusted-yield — 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 risk-adjusted-yield

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/risk-adjusted-yield/github.svg)](https://agentmods.dev/skills/philidor-labs/philidor-mcp/risk-adjusted-yield)

Your own site

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

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 664 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	$0.00053	$0.00664
Opus 5.5	$0.00021	$0.00266
Sonnet 5.5	$0.00011	$0.00133
Haiku 4.5	$0.00005	$0.00066

Measured 16d ago against content hash 0ffc3d5871d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

risk-adjusted-yield 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/risk-adjusted-yield/SKILL.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Risk-adjusted yield comparison

Compare yield only beside the risk evidence Philidor returns. Do not invent a risk-adjusted APY, a Sharpe-style ratio, or any score the tools did not return. If you rank vaults, say whether the list is a sample (a capped search_vaults page) or the top-10 audited screen from find_safest_vaults.

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

Steps

Call search_vaults with the filters the user named: asset, chain, protocol, protocolVersion, riskTier (Prime, Core, or Edge). Set depositable to true when they want vaults that can still be entered. Sort with sortBy apr_net or tvl_usd and sortOrder asc or desc. limit defaults to 10 and maxes at 50.
Aave V4 is protocol=aave and protocolVersion=v4. aave-v4 is an accepted alias, not its own protocol id.
Keep base yield and reward APR as separate fields when the payload splits them. Do not add them into a number Philidor did not label.
Drop or flag rows the user cannot enter: deposit status closed. Keep unknown visible and label it unknown. Do not call an unknown row open.
For two or three finalists, call compare_vaults. vaults is an array of 2–3 objects, each with network and address copied from search_vaults or get_vault. Never type an address that no tool returned.
Call get_vault_risk_breakdown on a finalist when the user wants vector detail. Call explain_risk_score with a score that was returned. Read philidor://methodology before explaining the four vectors.
Call find_safest_vaults only for “safest” or “highest score” questions. It returns the top 10 audited vaults for the optional asset, chain, and minTvl. It does not rank by APR. A high score is lower assessed risk, not a guarantee.
If the client exposes MCP prompts, defi_yield_comparison takes optional asset, chain, and riskTier.

Done when

Every row shows the returned vault id, network, address, tier, score, TVL, and the APR labels the tool used.
The answer states the filter and the cap (limit or top 10), so “highest APR” is not presented as the whole market.
No risk figure appears that was not in a tool result from this turn.

Read the full file on GitHub · 31 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 · 31 lines · 53 tokens per session scan A 0ffc3d5871d9

Subscribe to this mod's changes

risk-adjusted-yield is a skill published in the GitHub repository Philidor-Labs/philidor-mcp (5 stars, last pushed 16d ago), licensed MIT. It adds 53 tokens to every session and 664 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

risk-adjusted-yield

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

Risk-adjusted yield comparison

Steps

Done when

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