Orkas is a desktop application for commanding a team of AI agents through one chat, with a commander model assigning work to specialist agents in parallel or in sequence. People use it to coordinate research, writing, presentations, and software tasks while keeping files on their computer. The catalogue includes skills for extending the agents available to Orkas.
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 Orkas-AI/Orkas --skill market-datagit clone --depth 1 https://github.com/Orkas-AI/OrkasWrote 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/orkas-ai/orkas/market-data)<a href="https://agentmods.dev/skills/orkas-ai/orkas/market-data"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/market-data/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/orkas-ai/orkas/market-data"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/market-data.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 | $0.00002 | $0.01035 |
| Opus 5.5 | $0.00001 | $0.00414 |
| Sonnet 5.5 | $0.00000 | $0.00207 |
| Haiku 4.5 | $0.00000 | $0.00103 |
Grade A, and why
market-data 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 24d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Market Data
Read for every substantive StockAnalyser route. It owns the shared input and evidence contract; the other Skills own interpretation.
API-first source order
- Use supplied CSV/JSON when the user explicitly asks to analyze it.
- Any question about the current/latest price, whether a stock is worth buying,
or an entry range must call
market quotebefore any web search. Tencent is the free primary quote API and Sina is the automatic fallback. - Use
history fetchfor free A/HK/US daily bars. Its pinned AKShare dependency is installed automatically in the Skill runner's isolated cache; never run a manual package install or package-presence preflight. - Use a connected broker only for broker-grade corroboration, account state, security rules, or orders. Keep credentials inside the connector boundary.
- Use targeted exchange, filing, and issuer pages for company facts or events missing from providers. Web search snippets never substitute for a quote or history API response.
Do not begin web research while a required quote call is still pending. If all
quote providers fail, say that the current price is unverified and do not issue
an exact valuation, entry band, stop, or buy/sell conclusion. A prior close or
auction indication must retain its quote_kind, provider time, session, age,
and quality flags.
Never silently mix vendors, currencies, raw and adjusted prices, intraday and daily bars, or price and total returns.
Canonical contract
CSV columns: date,open,high,low,close,volume; amount and adjusted_close
are optional. JSON may be the same row array or { "bars": [...], "meta": {} }.
Dates use ISO-8601. Numbers are raw numeric values, not comma/percent strings.
Attach symbol, market, currency, timezone, adjustment, source, and
as_of when known. The core sorts dates, rejects duplicates or impossible OHLC,
and emits freshness and coverage flags.
For a screen, use:
{"securities":[{"symbol":"600519.SH","bars":[...],"fundamentals":{"roe":0.31,"pe":24.2}}],"filters":{},"weights":{}}
What ships with it
4 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.
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.
- 24d ago First seen · 85 lines · 2 tokens per session scan A b1a65408f2e0
market-data is a skill published in the GitHub repository Orkas-AI/Orkas (2,192 stars, last pushed today), licensed MIT. It adds 2 tokens to every session and 1,035 once invoked, about $0.0000 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 2026-09-23.
Other skills, from other repositories
compound-interest-calculator
Calculate compound interest given principal, rate, time, and compounding frequency.
behavioral-economics
Systematic departures from rational choice theory and their implications for economic analysis and policy. Covers cognitive heuristics (anchoring, availability, representativeness), biases (loss aversion, status quo, overconfidence), prospect theory (reference dependence, probability weighting, diminishing…
development-economics
Economics of low-income countries and the structural transformation from agrarian poverty to industrial prosperity. Covers growth models (Solow, endogenous growth, unified growth theory), the role of institutions (inclusive vs. extractive), inequality measurement and dynamics (Gini, Lorenz curve, Kuznets), poverty…
international-trade
Theory and policy of international economic exchange. Covers comparative advantage (Ricardo, Heckscher-Ohlin), gains from trade, trade policy instruments (tariffs, quotas, subsidies), exchange rate determination, balance of payments, globalization dynamics, trade agreements, and the political economy of protectionism.…
public-policy
Economic analysis of government intervention -- taxation (incidence, efficiency, optimal design), regulation (cost-benefit, market failure correction), externalities (Pigouvian taxation, cap-and-trade, Coasian bargaining), and public goods provision (non-rivalry, non-excludability, free-rider problem). Covers welfare…
macroeconomics
Analysis of aggregate economic phenomena -- GDP measurement, inflation dynamics, unemployment theory, monetary policy (central banks, interest rates, money supply), fiscal policy (government spending, taxation, debt), and the business cycle. Covers Keynesian, monetarist, and new classical perspectives. Use when…