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 romaco-labs/romaco-mcp --skill romaco-chart-analysisgit clone --depth 1 https://github.com/romaco-labs/romaco-mcpWrote 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/romaco-labs/romaco-mcp/romaco-chart-analysis)<a href="https://agentmods.dev/skills/romaco-labs/romaco-mcp/romaco-chart-analysis"><img src="https://agentmods.dev/badge/skills/romaco-labs/romaco-mcp/romaco-chart-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/romaco-labs/romaco-mcp/romaco-chart-analysis"><img src="https://agentmods.dev/badge/skills/romaco-labs/romaco-mcp/romaco-chart-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 | $0.00098 | $0.01241 |
| Opus 5 | $0.00049 | $0.00620 |
| Sonnet 5 | $0.00020 | $0.00248 |
| Haiku 4.5 | $0.00010 | $0.00124 |
Grade A, and why
romaco-chart-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 9d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Romaco chart analysis
Build a real romaco-charts chart, connect it to the romaco MCP bridge, analyze a
ticker with the MCP's deterministic tools, and draw the result on the live chart.
Critical gotchas — these break cold runs, do not skip
- Fetch market data SERVER-SIDE only. A browser
fetchto Yahoo fails with CORS, and a hand-rolled proxy gets429. Use theyahoo-finance2library (v3) inside a Vite dev-server middleware — it handles Yahoo's cookie/crumb handshake and retries (it is the same library the MCP uses internally). - No
<StrictMode>. Its dev-only double mount/unmount tears down theMcpBridgeWebSocket ("WebSocket is closed before the connection is established"). Render the app without it. - Apply each indicator exactly once. Call
romaco_setup_chartwithpreset: "clean"(no indicators), then add indicators once during annotation. A preset that pre-loads indicators plus a manual add = duplicated rows in the legend (double EMA/RSI, a flood of VOL). - One MCP owns port 7399. The browser bridge connects to whichever MCP holds
7399. If two agents (e.g. Claude and Codex) both run the romaco MCP, they fight for the port. Run only one.
Workflow
1. Scaffold the chart app
- Vite + React + TypeScript project (wherever the user asks).
- Install:
romaco-charts,react,react-dom,yahoo-finance2@^3. vite.config.ts— a plugin exposingGET /api/<symbol>-daily, server-side:import YahooFinance from 'yahoo-finance2' const yf = new YahooFinance() // period1 ≈ 1–3y back, enough for EMA200 / volume profile / structure const result = await yf.chart(SYMBOL, { period1, interval: '1d' }) // map each quote → { time, open, high, low, close, volume } // time = Math.floor(new Date(q.date).getTime() / 1000) // UNIX seconds // skip rows with null OHLC; cache in memory; respond { candles }src/App.tsx— fetch the candles from the proxy (same-origin, no CORS), passdata={candles}to<TradingTerminal ref={ref} symbol={SYMBOL} data={candles} />, and mount<McpBridge chartRef={ref} />below it.src/main.tsx— render WITHOUT<StrictMode>.npm install→npm run dev→ open the dev URL in the browser.
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.
- 9d ago First seen · 88 lines · 98 tokens per session scan A efc2199209cf
romaco-chart-analysis is a skill published in the GitHub repository romaco-labs/romaco-mcp (1 stars, last pushed 11d ago), licensed Apache-2.0. It adds 98 tokens to every session and 1,241 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.