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 agentmods add commands/lucemia/trading-agents-plugin/trading-analysisgit clone --depth 1 https://github.com/lucemia/trading-agents-pluginWrote 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/commands/lucemia/trading-agents-plugin/trading-analysis)<a href="https://agentmods.dev/commands/lucemia/trading-agents-plugin/trading-analysis"><img src="https://agentmods.dev/badge/commands/lucemia/trading-agents-plugin/trading-analysis.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.02524 |
| Opus 5 | $0.00031 | $0.01262 |
| Sonnet 5 | $0.00012 | $0.00505 |
| Haiku 4.5 | $0.00006 | $0.00252 |
Grade A, and why
trading-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 4d 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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extract the ticker symbol from $ARGUMENTS (e.g. "NVDA"). If no ticker is provided, ask the user for one before proceeding.
Set TODAY to the current date in YYYY-MM-DD format.
Phase 1 — Parallel Data Analysis
Spawn these 4 subagents IN PARALLEL using the Agent tool (all at once, do not wait for one before starting the others). Each subagent has Bash access to fetch data.
Subagent 1 — Technical Analyst:
You are a technical analyst for $TICKER as of $TODAY.
Fetch data:
```bash
uv run --project /Users/davidchen/repo/TradingAgents python /Users/davidchen/repo/TradingAgents/scripts/fetch_market_data.py --ticker $TICKER --type technical --date $TODAY
Write a technical analysis report (150-200 words) covering:
- Trend: price vs EMA10, SMA50, SMA200 — bullish/bearish structure
- Momentum: RSI level, MACD direction and histogram
- Volatility: ATR relative to price, Bollinger band position
- Key levels: nearest support and resistance based on recent closes
End with exactly: TECHNICAL SIGNAL: BULLISH, BEARISH, or NEUTRAL
**Subagent 2 — News & Sentiment Analyst:**
You are a news and sentiment analyst for $TICKER as of $TODAY.
Fetch data:
uv run --project /Users/davidchen/repo/TradingAgents python /Users/davidchen/repo/TradingAgents/scripts/fetch_market_data.py --ticker $TICKER --type news --date $TODAY
Write a sentiment report (150-200 words) covering:
- Top 3 most impactful headlines and their market implications
- Overall sentiment: positive, negative, or mixed
- Any sector tailwinds/headwinds visible in the news
- Any earnings, guidance, or analyst signals
End with exactly: SENTIMENT SIGNAL: POSITIVE, NEGATIVE, or NEUTRAL
**Subagent 3 — Fundamentals Analyst:**
You are a fundamentals analyst for $TICKER as of $TODAY.
Fetch data:
uv run --project /Users/davidchen/repo/claude-trading-agents python /Users/davidchen/repo/claude-trading-agents/scripts/fetch_market_data.py --ticker $TICKER --type fundamentals --date $TODAY
Write a fundamentals report (200-250 words) covering:
- Valuation: trailing P/E, forward P/E, PEG ratio (forward PE / earnings growth), P/B vs sector norms
- Growth: revenue growth, earnings growth trajectory
- Quality: gross/operating margins, ROE, free cash flow
- Balance sheet: total debt, total cash, D/E ratio (totalDebt / (totalDebt + stockholders equity)), current ratio
- Risk metrics: beta, short ratio
- Quarterly financials: cite 1-2 key line items from quarterly_income_stmt and quarterly_balance_sheet (e.g. quarterly revenue, net income, total assets)
- Analyst consensus: mean recommendation (1=Strong Buy, 5=Sell), price target vs current price
End with exactly: FUNDAMENTAL SIGNAL: STRONG, FAIR, or WEAK
**Subagent 4 — Macro Analyst:**
You are a macro analyst providing global market context as of $TODAY.
Fetch data:
uv run --project /Users/davidchen/repo/claude-trading-agents python /Users/davidchen/repo/claude-trading-agents/scripts/fetch_market_data.py --ticker MACRO --type macro --date $TODAY
Write a macro context report (100-150 words) covering:
- Key macro themes visible in S&P 500, Treasury yield, oil, and gold news
- Any geopolitical, monetary policy, or economic signals that could affect equities
- Overall macro environment: risk-on, risk-off, or neutral
End with exactly: MACRO SIGNAL: RISK-ON, RISK-OFF, or NEUTRAL
Wait for all 4 subagents to complete. Collect their full reports.
---
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.
- 4d ago First seen · 303 lines · 62 tokens per session scan A 80e5fdd2f0f1
trading-analysis is a command published in the GitHub repository lucemia/trading-agents-plugin (14 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 2,524 once invoked, about $0.0003 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 commands, from other repositories
config
Command "config" from sdebruyn/fabric-dw-mcp-cli, covering configuration & defaults, http retry budget, sql retry budget, mcp workspace allowlist {#mcp-workspace-allowlist} and mcp server log level.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
valuation-methods
Valuation methods analysis — multiples, DCF inputs, PEG integration, valuation assumption extraction.
scan
Scan AWS account for cost optimization.
audit-checklist
Perform an internal audit, review controls, or prepare for an external financial audit.
finops-status
Orientation — say where an opportunity or assignment sits in the five-step FinOps lifecycle and what unlocks next. Useful when a record has no active stage: an opportunity while its assignments do the work, an assignment whose plan has not been approved yet, or a rejected or archived assignment. Read-only; mutates…