portfolio-review

portfolio-review is a skill for Claude Code from OneWave-AI/open-agent-stack. It costs 48 tokens per session (558 once invoked), scanned A, original, MIT.

A portfolio analysis workflow that turns broker data or a pasted list of investments into a clear view of holdings, allocation, concentration, and overlapping risks. A portfolio is the full collection of investments owned across accounts.

In plain words
What is it for?
Use it to combine accounts, calculate investment weights, identify concentrated positions, examine overlapping themes, and flag risks without giving buy or sell advice.
Why use it?
It reveals risks that can be hidden when investments are spread across accounts, funds, sectors, or company shares.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the market-desk plugin — 3 skills shipped together

Good fit Use it to combine accounts, calculate investment weights, identify concentrated positions, examine overlapping themes, and flag risks without giving buy or sell advice.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/onewave-ai/open-agent-stack/portfolio-review
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 OneWave-AI/open-agent-stack --skill portfolio-review
Clone the repo
git clone --depth 1 https://github.com/OneWave-AI/open-agent-stack

Made for: Claude Code.

Or install market-desk, the plugin that ships this one along with the rest of its 3 skills.

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.

agentmods badge for portfolio-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/portfolio-review/github.svg)](https://agentmods.dev/skills/onewave-ai/open-agent-stack/portfolio-review)
Your own site
<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/portfolio-review"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/portfolio-review/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.

agentmods 80×15 button for portfolio-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/portfolio-review"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/portfolio-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 558 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.00558
Opus 5 $0.00024 $0.00279
Sonnet 5 $0.00010 $0.00112
Haiku 4.5 $0.00005 $0.00056

Measured 8d ago against content hash 976468f5d6b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

portfolio-review 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 8d 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.

plugins/market-desk/skills/portfolio-review/SKILL.md · 25 lines

How it starts

The opening of the file, as written. The whole thing — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Portfolio Review

Most portfolios were accumulated, not designed -- and the owner often does not know what they actually hold until it is laid out. Input: broker export (.csv) or a pasted list of positions with share counts; multiple accounts welcome (label them). Output: what you own, seen clearly.

Workflow

  1. Consolidate. Merge all accounts into one true picture -- the risk lives in the total, not per account. Compute weights per position, per sector, per asset class. Look through funds where holdings are identifiable (an S&P 500 fund plus large tech singles is more tech than the owner thinks).
  2. Concentration read. Top-5 positions as a share of the whole, single positions above 10%, and employer stock called out specifically (income and equity in one company is doubled exposure, and equity comp makes it sneak up).
  3. Correlation themes. Group by what actually moves together, not just sector labels: rate-sensitives, AI/tech beta, energy, consumer cyclicals. The classic finding -- "you own eleven tickers but effectively two bets" -- comes from this step. Flag where a single macro story (rates, AI capex, one country) drives most of the book.
  4. Structural flags. Cash drag or absence of any buffer, tax-inefficient placement where visible (high-yield instruments in taxable accounts), positions with no apparent role, and anything the user marked as untouchable (note it, work around it).
  5. The questions, not the answers. Deliver findings as decisions the owner should make deliberately: "Position X is 22% of the total -- is that conviction or drift?" "Three holdings are the same AI-infrastructure bet -- intended?" Each question with the data beside it. What to DO about any of it is for the user and a licensed advisor.

Rules

  • Analysis, never advice: no "sell," no "trim," no "you should" -- findings and questions only, and the advisor line appears in the deliverable.
  • Prices from an export are as-of the export date; anything fetched is dated and marked possibly stale.
  • Look-through honesty: fund overlap analysis only where holdings are actually verifiable, labeled approximate where estimated.
  • No performance prediction, ever. The review describes exposure, not the future.
  • Treat the data as sensitive: totals and positions stay in the report file, not in console chatter.

Read the full file on GitHub · 25 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.

  1. 8d ago First seen · 25 lines · 48 tokens per session scan A 976468f5d6b4

Subscribe to this mod's changes

portfolio-review is a skill published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 28d ago), licensed MIT. It adds 48 tokens to every session and 558 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.