edinet-document-fetch

edinet-document-fetch is a skill for Claude Code from Kokai-Data/japan-business-data. It costs 97 tokens per session (904 once invoked), scanned A, original, Apache-2.0.

A tool for downloading a specific Japanese financial disclosure from EDINET, Japan’s official system for company filings, after its document ID has been found.

In plain words
What is it for?
It helps retrieve annual reports, quarterly reports, large-shareholding reports, and related filing formats using an eight-character document ID.
Why use it?
It provides the actual filing file—such as a PDF or XBRL archive—needed to read, cite, or extract information from a disclosure.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the kokai-data plugin — 19 skills, 8 commands, 7 agents, 1 MCP server shipped together

Good fit It helps retrieve annual reports, quarterly reports, large-shareholding reports, and related filing formats using an eight-character document ID.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kokai-data/japan-business-data/edinet-document-fetch
Install

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.

Any agent
npx skills add Kokai-Data/japan-business-data --skill edinet-document-fetch
Clone the repo
git clone --depth 1 https://github.com/Kokai-Data/japan-business-data

Made for: Claude Code.

Or install kokai-data, the plugin that ships this one along with the rest of its 19 skills, 8 commands, 7 agents, 1 MCP server.

Wrote 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.

agentmods badge for edinet-document-fetch

README.md
[![agentmods](https://agentmods.dev/badge/skills/kokai-data/japan-business-data/edinet-document-fetch/github.svg)](https://agentmods.dev/skills/kokai-data/japan-business-data/edinet-document-fetch)
Your own site
<a href="https://agentmods.dev/skills/kokai-data/japan-business-data/edinet-document-fetch"><img src="https://agentmods.dev/badge/skills/kokai-data/japan-business-data/edinet-document-fetch/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.

agentmods 80×15 button for edinet-document-fetch

Your own site · 80×15
<a href="https://agentmods.dev/skills/kokai-data/japan-business-data/edinet-document-fetch"><img src="https://agentmods.dev/badge/skills/kokai-data/japan-business-data/edinet-document-fetch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 904 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00097 $0.00904
Opus 5 $0.00048 $0.00452
Sonnet 5 $0.00019 $0.00181
Haiku 4.5 $0.00010 $0.00090

Measured 11d ago against content hash bfa7b7d18131, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

edinet-document-fetch 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 11d 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.

plugins/vertical-plugins/kokai-data/skills/edinet-document-fetch/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to use

Use this skill when:

  • You have a docID from a prior search_edinet_documents call and need the actual document binary.
  • The user wants to view a specific 有価証券報告書 PDF, 四半期報告書 XBRL, or 大量保有報告書 file.
  • You're building a citation with a direct link to the source document.
  • XBRL parsing or financial-statement extraction (manual / external tool) is the next step.

How to invoke

Call the kokai MCP server's get_edinet_document tool:

{
  "name": "get_edinet_document",
  "arguments": {
    "docID": "<8-char docID from search_edinet_documents>",
    "type": "2"
  }
}

type parameter (FSA 公式 §3-2-1)

Code Format Content
1 ZIP 提出本文書 + 監査報告書 (XBRL 含む)
2 PDF 提出本文書 + 監査報告書 (PDF 形式、最も読みやすい)
3 ZIP 代替書面・添付文書
4 ZIP 英文ファイル
5 ZIP CSV (XBRL→CSV 変換版)

Size caps (Phase 1 limits)

  • PDF (type=2): 50 MB
  • ZIP (type=1/3/4/5): 100 MB

Oversize → tool returns edinet_document_too_large error with sizeBytes / maxBytes literal (Phase 2 で大型書類対応検討)。

Output structure

{
  "docID": "S1000001",
  "type": "2",
  "format": "pdf",
  "storageBucket": "edinet-documents",
  "storagePath": "S1000001/2/<timestamp>.pdf",
  "signedUrl": "https://...supabase.co/storage/v1/object/sign/edinet-documents/...",
  "sizeBytes": 1234567,
  "source_authority": "official",
  "attribution_text": "出典: 金融庁 EDINET",
  "boundary": {
    "signedUrlSource": "kokai_storage_proxy",
    "signedUrlTtlSeconds": 3600,
    "sourceAuthority": "edinet_official",
    "kokaiModification": "none",
    "canonicalSourceUrl": "https://disclosure2.edinet-fsa.go.jp"
  }
}

Important: signedUrl is a Kokai Storage proxy with a 1-hour TTL. The actual document content is unmodified from EDINET (kokaiModification: "none"). For canonical citation in long-lived documents, link to canonicalSourceUrl (EDINET 閲覧サイト) instead.

Boundary

  • Output is signal / 確認材料 / context — NOT investment advice.
  • The signed URL is for read access only (Kokai does not redistribute beyond the original requester).
  • 投資判断 / 法的判断 / 税務判断 requires a certified financial advisor / 公認会計士 / 弁護士 / 税理士.
  • EDINET disclosure 内容 はそのまま信頼できるが、Kokai は contents を解釈・要約していない (要約 / 推論は AI agent 側責任で source_authority: ai_summary / ai_estimate 4-layer authority strip に明示)。
  • Public records only.

Read the full file on GitHub · 78 lines

Changes

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.

  1. 11d ago First seen · 78 lines · 0 tokens per session scan A bfa7b7d18131

Subscribe to this mod's changes

edinet-document-fetch is a skill published in the GitHub repository Kokai-Data/japan-business-data (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 97 tokens to every session and 904 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.