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 etbars/vibetrader-mcp --skill clawhubgit clone --depth 1 https://github.com/etbars/vibetrader-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/etbars/vibetrader-mcp/clawhub)<a href="https://agentmods.dev/skills/etbars/vibetrader-mcp/clawhub"><img src="https://agentmods.dev/badge/skills/etbars/vibetrader-mcp/clawhub/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/etbars/vibetrader-mcp/clawhub"><img src="https://agentmods.dev/badge/skills/etbars/vibetrader-mcp/clawhub.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 | $0.00059 | $0.00916 |
| Opus 5.5 | $0.00024 | $0.00366 |
| Sonnet 5.5 | $0.00012 | $0.00183 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
vibetrader 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 15d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VibeTrader
Build trading bots by describing them, backtest them, and run them around the clock, from your agent.
Setup
-
Create a key at https://vibetrader.markets/settings → API keys. Choose what it may do:
- See: your bots, portfolio, trades, signals and backtests. Always included.
- Manage bots and signals: create, edit, start, pause and delete paper bots and signal bots, and record trades you made for a signal.
- Place orders and run live bots: buy and sell at your connected brokerage, and create or start bots that trade real money.
-
Put the key in your OpenClaw config (
~/.openclaw/openclaw.json). The skill reads it from the environment:{ "skills": { "entries": { "vibetrader": { "env": { "VIBETRADER_API_KEY": "vt_your_key_here" } } } } } -
Add the VibeTrader MCP server. It sends the key as a header on every request:
{ "mcp": { "servers": { "vibetrader": { "url": "https://mcp.vibetrader.markets/mcp", "transport": "streamable-http", "headers": { "Authorization": "Bearer ${VIBETRADER_API_KEY}" } } } } }Or sign in instead of using a key: set
"auth": "oauth"on the server (and dropheaders), then runopenclaw mcp login vibetrader. You sign in to VibeTrader in the browser and choose the permissions there.
The key always goes in the request header. Never paste it into chat: the hosted server no longer has an authenticate tool.
What it can do
- Bots: create from plain English, list, inspect, start, pause, update, delete, and preview how often a bot would trigger.
- Backtests: run them, list them, open results, and run a quick covered-call backtest.
- Portfolio: account summary, positions, trade history, and per-bot trades and daily stats.
- Market: quotes, market status, and the indicator catalog.
- Orders:
place_orderandclose_positionat your VibeTrader-connected Alpaca account. Needs Place orders and run live bots. - Signal mode: a bot that watches and decides but sends you each entry and exit instead of trading, so you can trade wherever you hold the account:
set_signal_modeturns it on;list_open_signalsshows what to do now;report_signalrecords the trade you made so the bot tracks your position and sends the exits.
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.
- 15d ago First seen · 77 lines · 59 tokens per session scan A 91e7377bc1e5
vibetrader is a skill published in the GitHub repository etbars/vibetrader-mcp (4 stars, last pushed 11d ago), licensed MIT. It adds 59 tokens to every session and 916 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 2026-10-22.
vibetrader compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vibetraderetbars/vibetrader-mcp | Skill | 4 | 11d ago | MIT | A | 59 | Claude Code, Codex |
| sector-rotationHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 39 | Claude Code, Codex |
| twitter-readerhimself65/finance-skills | Skill | 3.5k | 3d ago | MIT | A | 110 | Claude Code |
| strategy-pivot-designertradermonty/claude-trading-skills | Skill | 3.7k | 2d ago | MIT | A | 28 | Claude Code, Codex |
| energy-procurementhashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 93 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 269 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |
| multi-expert-analyzerdigoal/blog | Skill | 8.6k | 2d ago | GPL-2.0 | A | 292 | Codex |