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 INo-xious/stockbit-mcp --skill trade-with-guardrailsgit clone --depth 1 https://github.com/INo-xious/stockbit-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/ino-xious/stockbit-mcp/trade-with-guardrails)<a href="https://agentmods.dev/skills/ino-xious/stockbit-mcp/trade-with-guardrails"><img src="https://agentmods.dev/badge/skills/ino-xious/stockbit-mcp/trade-with-guardrails/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/ino-xious/stockbit-mcp/trade-with-guardrails"><img src="https://agentmods.dev/badge/skills/ino-xious/stockbit-mcp/trade-with-guardrails.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Excessive Agency · line 52 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 57 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00042 | $0.00591 |
| Opus 5.5 | $0.00017 | $0.00236 |
| Sonnet 5.5 | $0.00008 | $0.00118 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
trade-with-guardrails 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.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simulated trading with guardrails
This server cannot execute real-money trades. Distinguish three accounts before selecting tools:
- Brokerage portfolio:
portfolio,position,cash_balance,ordersandorder_historyread the real account. Simulation mode does not redirect these tools. - Stockbit website virtual account:
virtual_portfolio,virtual_positionandvirtual_orders. - Local paper ledger:
paper_portfolio,paper_positionandpaper_orders.
If a request leaves the simulation account unclear, clarify which of the last two the user means. Never present simulated holdings or fills as real money. A request for a real-money trade cannot be fulfilled by silently substituting a simulation.
Website virtual trading
Read virtual_portfolio and virtual_orders first. Use virtual_config for the website's fee
settings. Activate with virtual_activate only when the user intends to start the virtual account.
For a simulated order, state the account, symbol, side, limit price and lots before calling
virtual_order. Use virtual_order_amend or virtual_order_cancel with an order identifier read
from that virtual account. Every virtual write requires authorization for that specific change;
confirm: true conveys that authorization. These tools support day limit orders and do not publish
trades to the social stream.
Local paper ledger
Read trading_status. When paper is off, the user can enable it at their terminal with
stockbit-auth trading-enable --paper; this cannot enable real trading.
Call paper_order_preview with the requested action, symbol, price and lots (or the existing paper
order identifier). Read the ticket's checks and relay its summary verbatim, including the PAPER
ACCOUNT label. After agreement, use the corresponding paper_order_buy, paper_order_sell,
paper_order_amend or paper_order_cancel with the ticket identifier. Tickets expire after two
minutes. Local simulated fill rules do not match exchange execution or Stockbit's virtual engine.
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 · -28 lines · -25 tokens per session 114b0440cc2f
- 2mo ago First seen · 77 lines · 67 tokens per session scan A 7bb69c06f10a
trade-with-guardrails is a skill published in the GitHub repository INo-xious/stockbit-mcp (56 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 591 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 2026-08-30.
Other skills, from other repositories
tradingview-mcp
AI Trading Intelligence — live prices, 30+ technical indicators, backtesting (6 strategies), walk-forward overfitting detection, trade logs, equity curves, licensed news sentiment (Marketaux), and multi-market screener. Supports stocks, crypto, ETFs, indices, Turkish (BIST), and Egyptian (EGX) markets.
escalation
Escalate a disputed refund to the billing lead.
refunds
Process customer refunds.
error-handling
Read the error codes these tools raise and decide whether to retry, fix the call, or stop.
issue-management
Create, update, list and search GitHub issues and PRs, list a repository's labels, run milestones, and check for duplicates.
release-management
Tag a commit, publish a GitHub release, and read, correct or withdraw the tags and releases already there.