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.
git clone --depth 1 https://github.com/Kokai-Data/japan-business-dataWrote 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/commands/kokai-data/japan-business-data/proposal-prep)<a href="https://agentmods.dev/commands/kokai-data/japan-business-data/proposal-prep"><img src="https://agentmods.dev/badge/commands/kokai-data/japan-business-data/proposal-prep.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.00214 |
| Opus 5 | $0.00014 | $0.00107 |
| Sonnet 5 | $0.00006 | $0.00043 |
| Haiku 4.5 | $0.00003 | $0.00021 |
Grade A, and why
proposal-prep 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 6d 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.
What it actually says
/proposal-prep
Run the proposal-prep-jp agent workflow on the provided Japanese company.
Argument: 13-digit 法人番号 (corporate number) OR company name.
If a company name is provided, the agent will call search_company first to confirm the corporate number with the user.
Usage:
/proposal-prep <13-digit 法人番号>(direct, fastest)/proposal-prep <company name>(search candidates, then user confirms)
The brief includes:
- Header: company name + 法人番号
- 事業概要 (cited from gBizINFO records)
- 直近トピック (cited from J-Grants subsidies, certifications, awards)
- 支援ニーズ仮説 (cited from subsidy landscape signals)
- 4-layer authority strip
- 士業 boundary disclaimer
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.
- 6d ago First seen · 27 lines · 28 tokens per session scan A d1cfbf3082af
proposal-prep is a command published in the GitHub repository Kokai-Data/japan-business-data (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 214 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.
Other commands, from other repositories
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
discuss
5-phase requirements-elicitation interview that produces an EARS-validated context/ .md.
fix
Universal debugging and fix application with semantic code analysis.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
design
A command that turns an existing plan into a detailed technical design for building the feature.
tour
Tour this project's memory — what's captured, where it lives, how to recall it (core-memory-kit).