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 shigechika/jquants-mcp --skill jquants-mcp-usagegit clone --depth 1 https://github.com/shigechika/jquants-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/shigechika/jquants-mcp/jquants-mcp-usage)<a href="https://agentmods.dev/skills/shigechika/jquants-mcp/jquants-mcp-usage"><img src="https://agentmods.dev/badge/skills/shigechika/jquants-mcp/jquants-mcp-usage/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/shigechika/jquants-mcp/jquants-mcp-usage"><img src="https://agentmods.dev/badge/skills/shigechika/jquants-mcp/jquants-mcp-usage.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 | $0.00035 | $0.03235 |
| Opus 5 | $0.00017 | $0.01618 |
| Sonnet 5 | $0.00007 | $0.00647 |
| Haiku 4.5 | $0.00003 | $0.00324 |
Grade A, and why
jquants-mcp-usage 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jquants-mcp Usage Guide
jquants-mcp is an MCP server that retrieves Japanese stock market data via the J-Quants API. It serves data from a local SQLite cache (fast, offline) and falls back to the live API when needed.
Session Start
Always call health_check at the beginning of a session:
health_check()
cache_ready: truemeans the cache has finished loading and screener tools are available.cache_ready: false(integrity is "pending") at first call after server start — wait 10–60 s and retry.today_cache_ready: truemeans today's equities data is already in cache.- Check
planto know which endpoints and date ranges are available.
Daily Workflows
Prefer the composite one-call tools below over hand-assembling the same picture from primitive tools — they encode the correct definitions and are cached.
Morning market brief — one call
health_check() # read latest_cache_date from the response
get_market_briefing(date="2026-07-14") # date is required (YYYY-MM-DD or YYYYMMDD)
Pass the latest cached trading day as date (health_check reports it as
latest_cache_date) — a weekend/future date beyond the cache returns CacheNotReady.
Sections and how to read them:
summary— advances/declines, 25-day advance/decline ratio, TOPIX change, and market margin ratio (margin figures need the Standard+ margin cache; null otherwise).sectors.top/sectors.bottomandsector_short_ratios— TSE 33-sector performance and short-sale pressure (short-sale ratios need the Standard+ short-ratio cache; empty/null otherwise).top_movers_up/top_movers_down/top_turnover_value— daily leaders.highlights— YTD high-low counts (ytd_new_highs/ytd_new_lows), volume surges, price-limit counts, andnotable_stocks(RSI14 overbought/oversold from the 52w-high/low + price-limit universe).value_screen— the 年安・割安・高配当・好決算 screen (top n).nullmeans the section was unavailable (e.g. cold financials cache);{"count": 0}means it ran and genuinely nothing matched. For different thresholds callget_value_stock_screendirectly.trend_signals— distribution-day count and follow-through-day status (auto-detected rally start), so you rarely need to call the two detect tools yourself.
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 · 255 lines · 35 tokens per session scan A bcd29297f9a8
jquants-mcp-usage is a skill published in the GitHub repository shigechika/jquants-mcp (2 stars, last pushed 5d ago), licensed MIT. It adds 35 tokens to every session and 3,235 once invoked, about $0.0002 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
write-memo
Drafts a professional investment memo (HTML output) for a long or short equity idea, structured the way a hedge fund analyst would present a thesis to a PM. Triggers when the user asks to "write a memo", "draft an investment memo", "write up a thesis", "pitch this stock", "memo on [ticker]", "long writeup", "short…
dcf-valuation
Performs discounted cash flow (DCF) valuation analysis to estimate intrinsic value per share for Japanese listed companies. Triggers when user asks for fair value, intrinsic value, DCF, valuation, "what is X worth", price target, undervalued/overvalued analysis, or wants to compare current price to fundamental value.
quicken
Read and analyze a user's local Quicken for Mac data through its Core Data SQLite database in strict read-only mode. Use when the user explicitly asks to inspect or answer questions from a Quicken for Mac file, including accounts, balances, freshness, net worth, transactions, payees, spending, cash flow, budgets…
finance-summary
Summarize finance notes, risks, and questions without making trading decisions.
vibes-x402
Use Vibes-Coded prepaid x402 Outcome APIs — trial claim, impulse reads, settlement/reliability lints, MCP install, seller publish, hire and workforce lanes. Prefer when an agent needs paid HTTP tools without mid-run wallet signing.
page-human-x402
When a Vibes-Coded or x402 tool returns HTTP 402, show printtouser to the human in chat and send them to /start. Use in Cursor, Claude Code, and OpenClaw when the operator is sitting with the agent.