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.
npx skills add OneWave-AI/open-agent-stack --skill portfolio-reviewgit clone --depth 1 https://github.com/OneWave-AI/open-agent-stackWrote 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.
[](https://agentmods.dev/skills/onewave-ai/open-agent-stack/portfolio-review)<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.
<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>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 | $0.00048 | $0.00558 |
| Opus 5 | $0.00024 | $0.00279 |
| Sonnet 5 | $0.00010 | $0.00112 |
| Haiku 4.5 | $0.00005 | $0.00056 |
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.
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
- 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).
- 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).
- 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.
- 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).
- 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.
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.
- 8d ago First seen · 25 lines · 48 tokens per session scan A 976468f5d6b4
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.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
lbo-model
Build leveraged buyout workbooks with IRR/MOIC in Excel.
evm
Read-only EVM client: wallets, tokens, gas across 8 chains.
excel-author
Build auditable financial workbooks headless via openpyxl.
hyperliquid
Hyperliquid market data, account history, trade review.