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 cha2hyun/tossinvest-mcp --skill tossinvest-tradinggit clone --depth 1 https://github.com/cha2hyun/tossinvest-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/cha2hyun/tossinvest-mcp/tossinvest-trading)<a href="https://agentmods.dev/skills/cha2hyun/tossinvest-mcp/tossinvest-trading"><img src="https://agentmods.dev/badge/skills/cha2hyun/tossinvest-mcp/tossinvest-trading/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/cha2hyun/tossinvest-mcp/tossinvest-trading"><img src="https://agentmods.dev/badge/skills/cha2hyun/tossinvest-mcp/tossinvest-trading.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 | $0.00055 | $0.00996 |
| Opus 5 | $0.00028 | $0.00498 |
| Sonnet 5 | $0.00011 | $0.00199 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
tossinvest-trading 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TossInvest Trading
Use this workflow only for an explicit user-requested order action. Hermes may prefix tool names
with mcp_tossinvest_; names below omit that prefix.
Non-negotiable rules
- Never infer an order from research, analysis, portfolio discussion, or a price target.
- Never request, read, transmit, log, or store the human approval token or its hash.
- Never split an order to evade configured limits or the KRW 100 million hard block.
- Never call a write tool before a matching preview has been approved outside MCP.
- Never call a write tool more than once for the same preview.
- Never automatically retry any create, modify, or cancel request.
- If the result is
order-state-unknown, inspect order history before any further write. - Treat a missing trading tool as trading disabled; do not seek another route around it.
- Conditional-order creation, modification, and cancellation are unsupported; never substitute a regular-order write tool or another route.
Establish exact intent
For a new order, require:
- side:
BUYorSELL - symbol
- order type:
LIMITorMARKET - exactly one of whole-share
quantityor supported USDorder_amount pricefor a limit order- time in force when it differs from
DAY
For a modification, require the existing order ID and every proposed replacement field.
For a cancellation, require the existing order ID and an explicit request to cancel it. Do not require creation-only fields such as side or amount.
If any required intent is ambiguous, ask the user before calling a preview tool.
Create
- Confirm symbol identity and currency when ambiguous.
- Check stock warnings and the relevant market calendar.
- Check buying power for a buy or sellable quantity for a sell.
- Call
preview_orderexactly once with the user's stated intent. - Present symbol, side, order type, quantity or amount, limit price when present, currency,
estimated value, estimated KRW value, warnings, expiry, and
approval_url. - Explain that market-order execution price may move and that a new preview is required after expiry or material changes.
- Ask the user to open
approval_urland approve the exact preview with the separate credential. - Only after the user reports that external approval is complete, call
place_orderonce with the preview ID. - Report the returned order ID, detailed status, execution data, timestamp, and any warning.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 100 lines · 55 tokens per session scan A 1e5637ff6deb
tossinvest-trading is a skill published in the GitHub repository cha2hyun/tossinvest-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 996 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 2026-08-31.
Other skills, from other repositories
finance-news-analysis
Analyze current financial news for sentiment, market or sector impact, affected instruments, uncertainty, and risk scenarios without giving trade advice.
finance-skills
Route finance requests to capabilities available in the active runtime and report missing market data, tools, credentials, or verification explicitly.
trip-planner
Plan a trip step by step: an itinerary plus a running budget that converts every currency into your preferred one, printed as two tables after each change — and a final summary with the budget broken down by category, the average spend per day, and checks for accommodation gaps and missing daily food/misc estimates.
document-exports
Generate and TEST downloadable document exports (PDF/CSV) from a Node/Express backend — pdfkit streaming, CSV BOM, cents formatting, and the supertest/pdfkit pitfalls that silently break tests.
money-path-safety
Use when the user wants to: pay/buy/subscribe, receive or spend a bonus/promo code/referral, check a balance or limit, get a refund, or when any logic for deducting/crediting/quotas changes — even if the request does not name money explicitly («give me more minutes», «why was I charged twice», «enter a promo code»).…
portfolio-github-pages
Build and deploy a personal/academic PORTFOLIO as a single-page STATIC site (no build step) to GitHub Pages via the gh CLI. Use when the user asks for a portfolio, landing page, "pagina de portfólio", professional site, or "site estatico pro GitHub Pages", especially with a theme (astronomy/space is a known good…