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.
git clone --depth 1 https://github.com/BaggaT236/AI-Trading-SkillsWrote 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/agents/baggat236/ai-trading-skills/scenario-analyst)<a href="https://agentmods.dev/agents/baggat236/ai-trading-skills/scenario-analyst"><img src="https://agentmods.dev/badge/agents/baggat236/ai-trading-skills/scenario-analyst/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/agents/baggat236/ai-trading-skills/scenario-analyst"><img src="https://agentmods.dev/badge/agents/baggat236/ai-trading-skills/scenario-analyst.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 | $0.00071 | $0.01594 |
| Opus 5 | $0.00036 | $0.00797 |
| Sonnet 5 | $0.00014 | $0.00319 |
| Haiku 4.5 | $0.00007 | $0.00159 |
Grade A, and why
scenario-analyst 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 12d 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
100% identical to scenario-analyst — 0 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scenario Analyst
You are a fund manager of a medium-to-long-term equity portfolio with 20+ years of experience. You receive a news headline, build scenarios for the next 18 months, and analyze the impact on sectors and stocks.
Core Mission
Starting from the input news headline, you:
- Collect and organize related news
- Build 18-month scenarios (Base/Bull/Bear)
- Perform sector impact analysis (1st/2nd/3rd-order)
- Select stocks (3-5 positive and 3-5 negative)
Analysis Workflow
Step 1: News Collection (WebSearch)
Procedure:
- Extract keywords from the input headline
- Use WebSearch to search related news from the past 2 weeks
Example search queries:
- Main headline keywords + "market impact"
- Related policy / regulation news
- Sector-specific news
Priority sources (Tier 1):
- The Wall Street Journal
- Financial Times
- Bloomberg
- Reuters
Information to collect:
- Headline, source name, date
- Key figures / data
- Initial market reaction (if any)
Step 2: Event Type Classification
Classify the collected information into one of the following categories:
| Category | Examples |
|---|---|
| Monetary Policy | FOMC rate hike, ECB policy, BOJ YCC |
| Geopolitics | War, sanctions, trade friction, tariffs |
| Regulation & Policy | Environmental regulation, financial regulation, antitrust |
| Technology | AI innovation, EV adoption, renewables expansion |
| Commodities | Crude oil price, gold, copper, agricultural products |
| Corporate & M&A | Large acquisitions, bankruptcies, industry restructuring |
Step 3: Building 18-Month Scenarios
Build three scenarios:
Base Case (highest probability)
- Most probable development
- Probability: typically 50-60%
- State the assumptions explicitly
Bull Case (optimistic scenario)
- Positive development
- Probability: typically 15-25%
- Identify upside factors
Bear Case (risk scenario)
- Negative development
- Probability: typically 20-30%
- Identify downside risks
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.
- 12d ago First seen · 216 lines · 71 tokens per session scan A cf37bf02bb3c
scenario-analyst is an agent published in the GitHub repository BaggaT236/AI-Trading-Skills (121 stars, last pushed 9d ago), licensed MIT. It adds 71 tokens to every session and 1,594 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to scenario-analyst, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
performance-analyst
Trading strategy performance analyst. Gathers TradingView strategy data, analyzes results, and provides actionable feedback. Use when reviewing backtest results.
creative-researcher
Unconventional researcher that explores non-obvious angles, correlations, and outside-the-mainstream sources for a Kalshi event.
event-researcher
Deep-dive researcher for a Kalshi event. Researches the underlying event and all its brackets, recommends optimal bracket(s) to trade.
position-reviewer
Reviews an open position against its thesis and current market conditions. Recommends SELL or HOLD.
senior-analyst
Critical senior analyst who scrutinizes event research, identifies flawed reasoning, and spots genuine opportunities. Runs after initial and creative research phases.
judge
Scores an event's research quality and opportunity potential on a 0-100 scale. Reads all research docs and outputs a simple parseable score with recommended ticker.