A read-only assistant for finding and reviewing DeFi holdings across multiple blockchains and wallets. DeFi means financial services built on blockchain networks rather than traditional banks.

Use it to discover wallet positions, review yield and rebalancing options, maintain portfolio history, and create unsigned NEAR Intent bundles for wallet-based signing.

It brings positions into one project and prepares proposed moves without holding private keys or signing transactions.

portfolio — Skill for Claude Code and Codex by suyoumo: A read-only assistant for finding and reviewing DeFi holdings…

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.

agentmods

npx agentmods add skills/suyoumo/clawprobench/portfolio

Any agent

npx skills add suyoumo/ClawProBench --skill portfolio

Clone the repo

git clone --depth 1 https://github.com/suyoumo/ClawProBench

Made for: Claude Code, Codex.

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/suyoumo/clawprobench/portfolio.svg)](https://agentmods.dev/skills/suyoumo/clawprobench/portfolio)

Your own site

<a href="https://agentmods.dev/skills/suyoumo/clawprobench/portfolio"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/portfolio.svg" alt="Measured on agentmods" height="20"></a>

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,492 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00069	$0.03492
Opus 5	$0.00034	$0.01746
Sonnet 5	$0.00014	$0.00698
Haiku 4.5	$0.00007	$0.00349

Measured 5d ago against content hash 82235cca5dd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

portfolio 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 5d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/alert_if_health_below.py, scripts/backtest_strategy.py, scripts/concentration_warning.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

ironclaw/skills/portfolio/SKILL.md · 324 lines

How it starts

The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Portfolio Keeper

You help the user discover, analyze, and rebalance their cross-chain DeFi portfolio. You build and maintain a per-user portfolio project that aggregates all of their wallets in one place, runs a recurring keeper mission, and produces unsigned NEAR Intent bundles for any move the user accepts.

You never hold private keys. Every execution path produces unsigned intents only. Signing happens in the user's wallet, never here.

Core principles

One default project per user. Multiple wallets live inside a single portfolio project by default. Only create an additional project (e.g. portfolio-treasury) when the user explicitly asks for one.
Read-only and unsigned. All portfolio.* operations are read-only or produce unsigned artifacts. The agent must not request signing.
Project-scoped state. Every file you write goes under projects/<id>/... in the workspace. Never write portfolio data outside the project.
Strategies and protocols are data, not code. Strategy docs are Markdown files with YAML frontmatter; protocols are JSON entries inside the portfolio tool. Adding either is a data change.
History is sacred. Never overwrite or delete entries under state/history/ or suggestions/. They are the local time series that powers backtests and the learner.

Procedure (every activation)

1. Project bootstrap

If no portfolio project exists for this user, call project_create with name="portfolio" and a short description. Only create additional projects (portfolio-treasury, portfolio-dao, …) when the user explicitly asks ("create a separate treasury portfolio").
After creation, copy the default strategy doc into projects/<id>/strategies/stablecoin-yield-floor.md via memory_write. The default lives in the portfolio tool's strategies/ directory; if you can't read it, write the same frontmatter from memory.
Write projects/<id>/config.json if it doesn't exist:

Read the full file on GitHub · 324 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

5d ago First seen · 324 lines · 69 tokens per session scan A 82235cca5dd9

Subscribe to this mod's changes

portfolio is a skill published in the GitHub repository suyoumo/ClawProBench (823 stars, last pushed 10d ago), licensed Apache-2.0. It adds 69 tokens to every session and 3,492 once invoked, about $0.0003 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 2026-08-30.

Evaluation Finance and fintech LLM Web3 and blockchain agent benchmark harness leaderboard

Evaluation

Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.

agentic-in/elephant-agent · 25 tokens

evm

Read-only EVM client: wallets, tokens, gas across 8 chains.

NousResearch/hermes-agent · 19 tokens

hyperliquid

Hyperliquid market data, account history, trade review.

NousResearch/hermes-agent · 16 tokens

solana

Query Solana wallets, tokens, txs, and NFTs in USD.

NousResearch/hermes-agent · 18 tokens

building-pydantic-ai-agents

Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…

pydantic/pydantic-ai · 85 tokens

harness-creator

Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…

walkinglabs/learn-harness-engineering · 142 tokens