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 seonglae/openportfolio --skill openportfolio-bookgit clone --depth 1 https://github.com/seonglae/openportfolioWrote 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/seonglae/openportfolio/openportfolio-book)<a href="https://agentmods.dev/skills/seonglae/openportfolio/openportfolio-book"><img src="https://agentmods.dev/badge/skills/seonglae/openportfolio/openportfolio-book/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/seonglae/openportfolio/openportfolio-book"><img src="https://agentmods.dev/badge/skills/seonglae/openportfolio/openportfolio-book.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 | $0.00073 | $0.00664 |
| Opus 5.5 | $0.00029 | $0.00266 |
| Sonnet 5.5 | $0.00015 | $0.00133 |
| Haiku 4.5 | $0.00007 | $0.00066 |
Grade A, and why
openportfolio-book scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reading the book
openportfolio holds every account as one book in one base currency. This skill reads it. It never writes, and nothing in openportfolio places an order: there is no tool for it because the backend has no function that does.
Setup
The tools come from the stdio MCP server in the openportfolio repo. Register it once with your agent CLI, from the repo root:
claude mcp add openportfolio -- node "$PWD/mcp/portfolio-server.mjs"
It reads CONVEX_DEPLOYMENT, OPENPORTFOLIO_SERVICE_KEY and, optionally, OPENPORTFOLIO_TENANT from the environment or from .env.local beside it. A service key belongs to exactly one book, so the server cannot see any other. Run whoami first when a call is refused: it says which book and which role the key resolved to.
Order of reading
whoamifor the book and its base currency. Every value below is in that currency unless a row says otherwise.net_worthfor the total, split by venue and by asset class.list_accounts, thenlist_balances(optionally withaccountKey) for positions.symbol_exposurewith asymbolwhen a name appears in more than one account. The summed figure is the one that matters for concentration, not the per-account one.net_worth_historyfor recorded snapshots, oldest first. A snapshot is never recomputed, so it shows what the book was worth then at that day's rates.list_venuesto see what each adapter can actually do. A venue that cannot read balances is priced from rows someone entered.
Flows and the calendar
flow_by_investorwith amarket(and optionaldays) answers who has been absorbing the supply over a window.list_flowsgives the per-session rows. Check thecurrencyandsourceon each: positioning data may be in contracts rather than money.upcoming_catalysts(optionalwindowDays,asset) lists dated forward events: lockups, rebalances, unlocks, prints.
How to report
- Quote figures with their currency and the date they were recorded. A missing price is a missing number, not a zero: say which row is unpriced rather than summing around it.
- Concentration is a share of the total from
net_worth, computed fromsymbol_exposure, not from one account. - Observations and probabilities only. Never recommend a quantity, a price or an order. If a view is worth having, register it with the
openportfolio-forecastskill so it gets scored.
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 · 40 lines · 73 tokens per session scan A e8a7fa642749
openportfolio-book is a skill published in the GitHub repository seonglae/openportfolio (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 73 tokens to every session and 664 once invoked, about $0.0003 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 2026-09-30.
Other skills, from other repositories
research-stocks
Read current stock research, technical backtests, saved analyses or saved backtests. Use for a named ticker or watchlist research history; preserve source dates, model limitations and risk factors.
track-tariff-trends
Retrieve a country's average applied tariff over time — the MFN rate on all products, or the rate it applies on goods from one partner and/or in one product group — plus the optional US effective tariff rate. Use when the user asks how a country's tariffs have changed, or what it charges another country on average.…
get-prediction-markets
Retrieve active prediction-market contracts (Polymarket) with live yes-price probabilities, volume, and close dates, filterable by category or keyword. Use when the user asks what the market odds are on a geopolitical, economic, or election outcome.
tvchart
Drive a live TradingView Lightweight Charts widget end-to-end via PyWry MCP tools — symbol, interval, indicators, markers, price lines, layouts, state.
tbank-messenger
A chat connection for T-Bank, a Russian bank, that lets an agent read conversations, download attachments, and contact bank support. It works with chats inside the bank app, not SMS codes or push notifications.
aifi-daily-report
A tool for producing a Chinese end-of-day report on United States stock markets as a self-contained HTML file. HTML is the standard format used to display web pages.