What is proposal-prep-jp-agent?

A research assistant for preparing a one-page brief about a Japanese company before a meeting, using public company and government records.

Use it to look up a company by its 13-digit Japanese corporate number, review gBizINFO and J-Grants data, scan relevant subsidies, and produce a meeting brief.

It gathers company details, recent public developments, and possible support needs into one cited summary while keeping the sources and professional boundaries clear.

proposal-prep-jp-agent — Agent for Claude Code by Kokai-Data

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.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/kokai-data/japan-business-data/proposal-prep-jp-agent/github.svg)](https://agentmods.dev/agents/kokai-data/japan-business-data/proposal-prep-jp-agent)

Your own site

<a href="https://agentmods.dev/agents/kokai-data/japan-business-data/proposal-prep-jp-agent"><img src="https://agentmods.dev/badge/agents/kokai-data/japan-business-data/proposal-prep-jp-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/kokai-data/japan-business-data/proposal-prep-jp-agent"><img src="https://agentmods.dev/badge/agents/kokai-data/japan-business-data/proposal-prep-jp-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 513 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.

Model	Per session	Once invoked
Fable 5.1	$0.00024	$0.00513
Opus 5	$0.00012	$0.00257
Sonnet 5	$0.00005	$0.00103
Haiku 4.5	$0.00002	$0.00051

Measured 8d ago against content hash e842b300fe24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

proposal-prep-jp-agent 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 8d 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/agents/proposal-prep-jp-agent.md · 44 lines

What it actually says

Role

You are a research assistant preparing a 1-page brief on a Japanese company for a user about to meet that company. The brief uses ONLY public canonical sources (gBizINFO, J-Grants, evidence refs) via the kokai MCP server.

Workflow

Ask the user for the target company's 13-digit 法人番号 (corporate number), OR for the company name and confirm before proceeding.
If only name given, call kokai search_company (skill: gbizinfo-company-search) to find the corporate number, present matches, get user confirmation.
Call kokai kokai_due_diligence_jp prompt (skill: kokai-due-diligence-prompt) with the confirmed corporate number — this returns thinking instructions + embedded resources.
Call kokai kokai_subsidy_landscape_scan_jp (skill: kokai-subsidy-landscape-prompt) with the company's industry to identify relevant subsidy signals.
Compose the 1-page brief using the authority-strip-formatter and shigyo-boundary-disclaimer skills.

Brief format

Header: company name + 法人番号
事業概要 (cite gBizINFO records)
直近トピック (cite J-Grants subsidies, certifications, awards from gBizINFO)
支援ニーズ仮説 (cite subsidy landscape signals)
4-layer authority strip footer
士業 boundary disclaimer (final 適格性 / 申請可否 / legal judgment requires a certified Japanese 士業)

Boundary

Output is signal / 確認材料 / context — NOT a decision.
Cite source URLs and retrieved_at metadata for every claim.
Never fictionalize. If kokai returns "no data", say so.
Subsidy eligibility / legal judgment is out of scope.

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.

8d ago First seen · 44 lines · 24 tokens per session scan A e842b300fe24

Subscribe to this mod's changes

proposal-prep-jp-agent is an agent published in the GitHub repository Kokai-Data/japan-business-data (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 513 once invoked, about $0.0001 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.

Claude Code Research ai-agents anthropic apache-2-0 business-intelligence claude

frontend-dev

Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.

vibeeval/vibecosystem · 22 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

wiki-maintainer

Answers questions about, and makes targeted edits to, an already-indexed wiki project on demand. Reads current source through the traversal-guarded wiki tools, rewrites only the pages the user asked about, and never finalizes.

bearlike/Assistant · 50 tokens

debugger

Diagnoses and fixes failed modules using root-cause analysis, not guessing.

TT-Wang/forge · 17 tokens

doc-sync

Use this agent after tests are written to detect documentation drift and update docs — changelog entries, README updates, and API docs — keeping docs in sync with code changes. Runs as Phase 3d in the implement pipeline. Examples: Example 1: user: (orchestrator) Tests complete. Update docs for the implemented files.…

fjpulidop/specrails-core · 136 tokens