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 impact-analysisgit 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/impact-analysis)<a href="https://agentmods.dev/skills/ginlix-ai/langalpha/impact-analysis"><img src="https://agentmods.dev/badge/skills/ginlix-ai/langalpha/impact-analysis/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/impact-analysis"><img src="https://agentmods.dev/badge/skills/ginlix-ai/langalpha/impact-analysis.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 | $0.00056 | $0.03210 |
| Opus 5.5 | $0.00022 | $0.01284 |
| Sonnet 5.5 | $0.00011 | $0.00642 |
| Haiku 4.5 | $0.00006 | $0.00321 |
Grade A, and why
impact-analysis 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 25d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Impact Analysis
One object carries this skill: the transmission chain, written as event, channel, driver, line item, action. A shock reaches a share price only by reaching a named landing, a financial line item or the valuation input a discount rate moves directly, so a claim that cannot name where it lands is a mood about a theme and does not ship. This is the work between .agents/skills/morning-note/SKILL.md, which says something happened, and the models, which say what a company is worth.
Evidence labels, source tiers, staleness, the readiness posture and the intake limits: .agents/skills/research-conventions/SKILL.md, read before the first deliverable.
The exposure map is the default output. Absent a position list the user supplied, the report names candidates in research-queue language and says in one sentence what would convert the screen into an action. Every name in it is a research candidate until the user says otherwise.
Step 1: Frame the shock and freeze the as-of
Write the event in one sentence carrying four things: what changed, who decided it, the date it takes effect, and what was expected before it. The last one is the whole analysis in miniature: a fully anticipated shock reaches the line item and never reaches the price.
Timing bucket. Every claim in the report carries one of four, and the headline claim carries its bucket in the first two sentences:
| Bucket | Window | What lands here |
|---|---|---|
immediate |
days | the multiple, sentiment, anything that reprices before a number moves |
this quarter |
the current reporting period | a line item that moves before the next print |
this year |
the next four quarters | contract resets, hedge roll-offs, inventory turning over |
structural |
beyond four quarters | capacity siting, supply-chain relocation, a changed cost curve |
Freeze the as-of. Record one moment for the whole set of time-sensitive inputs (prices, consensus, the macro series, the policy text as published) and state it at the top. An input with no as-of is a gap rather than an estimate.
What ships with it
1 file 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.
- 25d ago Changed e2699bb1fcdd
- 1mo ago First seen · 140 lines · 56 tokens per session scan A 36311c1ba88b
impact-analysis is a skill published in the GitHub repository ginlix-ai/LangAlpha (1,820 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 3,210 once invoked, about $0.0002 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 2026-09-16.
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.
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.
technical-analysis
Technical analysis of US stocks using charts and indicators.
dividend-analysis
Comprehensive capital allocation analysis: dividends, buybacks, M&A, debt management, and FCF deployment.