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 catalyst-calendargit 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/catalyst-calendar)<a href="https://agentmods.dev/skills/ginlix-ai/langalpha/catalyst-calendar"><img src="https://agentmods.dev/badge/skills/ginlix-ai/langalpha/catalyst-calendar/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/catalyst-calendar"><img src="https://agentmods.dev/badge/skills/ginlix-ai/langalpha/catalyst-calendar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 86 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00063 | $0.03099 |
| Opus 5.5 | $0.00025 | $0.01240 |
| Sonnet 5.5 | $0.00013 | $0.00620 |
| Haiku 4.5 | $0.00006 | $0.00310 |
Grade A, and why
catalyst-calendar 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 1mo 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.
This is a copy
88% identical to catalyst-calendar — 221 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Catalyst Calendar
A calendar of dates is a list; a catalyst calendar is a decision-pressure ranking. An event earns its place because it can move the estimate path, the narrative, the multiple, position size, the downside case, liquidity, or the odds of another event. Proximity alone ranks nothing: a high-materiality readout in eleven weeks outranks a routine print on Thursday, and the routine print belongs in a hygiene block.
Evidence labels, source tiers, staleness, the readiness posture and the intake limits: .agents/skills/research-conventions/SKILL.md, read before the first deliverable.
Step 1: Scope the universe
Settle four things, taking the mandate and horizon from memory per .agents/skills/research-conventions/references/intake.md and asking only about what it leaves open:
- The universe: tickers, a portfolio or watchlist file, a sector, or an index.
- The horizon: the next two weeks, a month, a quarter, or through the next reporting season.
- Whether macro releases and policy dates are in scope, or only issuer events.
- Whether the output goes to the desk or outside it, which decides the externally clean rule in step 7.
With nothing supplied, ask for one of those four concrete inputs and say what the default calendar will contain once it arrives (a rolling ninety days, issuer events plus the macro releases that bind the sector).
Done when the universe resolves to a named list of issuers, the horizon has dates, and the macro decision is recorded and the destination is recorded as desk or external.
Step 2: Gather events and classify by investment path
Pull live rather than recalling:
- Macro MCP:
get_earnings_calendar(from_date, to_date)for every reporter in the window, andget_economic_calendar(from_date, to_date)for releases and policy dates. get_company_overviewfor the issuer's reporting history and consensus context.WebSearchandWebFetchfor the events no calendar feed carries: regulatory dockets, trial readouts, conference agendas, lockup schedules, contract expiries.
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.
- 1mo ago Changed 49c7f070e468
- 1mo ago Changed · +91 lines · +45 tokens per session 475f69ebab77
- 1mo ago First seen · 97 lines · 18 tokens per session scan A 6d960e19ea84
catalyst-calendar is a skill published in the GitHub repository ginlix-ai/LangAlpha (2,155 stars, last pushed today), licensed Apache-2.0. It adds 63 tokens to every session and 3,099 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to catalyst-calendar, differing in 221 lines, and is treated as a copy.
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.
financial-report-analyst
Analyze company financial reports (10-K, 10-Q, annual reports) and extract actionable investment insights — statement quality, red flags, and a signal. For a structured section-by-section summary document of a 10-K rather than an investment call, use 10k-digest.
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.