LangAlpha is an agent workspace for researching financial markets and supporting investment decisions through persistent research, news analysis, and parallel subagents. It is for investors who want to develop and update trading theses over time, including generating long-short pair-trade ideas. The catalogue entries provide the skills, instructions, MCP servers, and plugin that make up its agent workflow.
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 ginlix-ai/LangAlpha --skill market-watchgit clone --depth 1 https://github.com/ginlix-ai/LangAlphaWrote 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/ginlix-ai/langalpha/market-watch)<a href="https://agentmods.dev/skills/ginlix-ai/langalpha/market-watch"><img src="https://agentmods.dev/badge/skills/ginlix-ai/langalpha/market-watch/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/ginlix-ai/langalpha/market-watch"><img src="https://agentmods.dev/badge/skills/ginlix-ai/langalpha/market-watch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00045 | $0.00594 |
| Opus 5 | $0.00023 | $0.00297 |
| Sonnet 5 | $0.00009 | $0.00119 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
market-watch 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 13d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Market Watch
Keep intraday analysis anchored to live prices. When a task turns on current price — a level check, an intraday move, a "where is it trading now" — register the central tickers so fresh quotes arrive automatically and your numbers never go stale mid-task.
When to use
Intraday or live-price analysis where the price may move while you work: "is NVDA above 205 right now", "how's TSLA trading into the print", sizing a level off the current quote. Skip it for purely historical or end-of-day work where a single snapshot is enough.
Workflow
- At the start of the task, identify the ticker(s) central to the
request and register them immediately with
watch_market. - While they matter, read the ambient feed (below) for the current price rather than re-quoting on every step.
- When live tracking is no longer relevant, call
watch_marketwithaction="unwatch"to stop watching some or all symbols (omitsymbolsto clear the whole list).
How the feed works
Once a symbol is watched, fresh prices arrive on their own as
<market-watch> price blocks attached to conversation messages and tool
results. This is ambient data — not user text, and not tool output
you requested. Each block is a snapshot at a moment in time; the newest
<market-watch> entry in the conversation is the current price, and any
earlier entry (including numbers in your own earlier statements) may be
stale.
Rules
- Treat the newest
<market-watch>entry as the live price. Prefer it — or a freshget_quote— over any older number in the thread. - If the price moves materially mid-analysis, acknowledge it and adapt your read rather than silently carrying the older figure.
- Before you state a price in a final answer: if the newest feed entry is
more than a minute old, make one
get_quotecall to re-check first.
Mechanics to know
- Stamps only flow while the market session is open — expect no feed outside trading hours.
- Updates are throttled: roughly one stamp per ~25s across the turn, not a tick-by-tick stream.
- The watch list is per-thread, capped at 10 symbols, and expires
after ~6h of inactivity. On a long task, if the feed goes quiet, just call
watch_marketagain to re-register.
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.
- 13d ago First seen · 58 lines · 45 tokens per session scan A 0172496e8edd
market-watch is a skill published in the GitHub repository ginlix-ai/LangAlpha (1,736 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 594 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 2026-08-30.
Other skills, from other repositories
creating-financial-models
This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions.
dividend-analysis
Comprehensive capital allocation analysis: dividends, buybacks, M&A, debt management, and FCF deployment.
position-ladder
Plan a staged position — entry ladder, share-count floor/ceiling, and the trim/re-add cycle that lowers average cost — with lot accounting, wash-sale checks, total-return honesty, and a thesis-break exit gate.
report-generator
Generate professional HTML/PDF investment reports with interactive visualizations.
stock-eval
Evaluate US stocks with comprehensive fundamental and valuation analysis.
stock-valuation
Multi-method stock valuation using DCF, comparable company analysis, EV multiples, and residual income models.