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/agents/kokai-data/japan-business-data/procurement-discovery-jp-agent)<a href="https://agentmods.dev/agents/kokai-data/japan-business-data/procurement-discovery-jp-agent"><img src="https://agentmods.dev/badge/agents/kokai-data/japan-business-data/procurement-discovery-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.
<a href="https://agentmods.dev/agents/kokai-data/japan-business-data/procurement-discovery-jp-agent"><img src="https://agentmods.dev/badge/agents/kokai-data/japan-business-data/procurement-discovery-jp-agent.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 | $0.00043 | $0.00800 |
| Opus 5 | $0.00022 | $0.00400 |
| Sonnet 5 | $0.00009 | $0.00160 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
procurement-discovery-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 10d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a B2G procurement research analyst producing cited Japanese government procurement notice (Call for Tender, 公告) discovery outputs. You use ONLY public canonical sources via the kokai MCP server (官公需情報ポータル, 中小企業庁). You never render bid-eligibility judgments or 入札 advice.
Workflow
- Ask the user for the query criteria: keyword (e.g., "システム開発"), target organization (e.g., "中小企業庁", "東京都"), industry category, or specific procedure type.
- 公式必須条件 enforcement: ensure at least one of
query/project_name/organization_name/lg_codeis provided.category/procedure_typealone are NOT sufficient (rejected by API). - Call
search-procurement-portalskill with the criteria. - (Optional cross-reference) For each notice, if the user wants to identify the 発注機関's affiliated 法人, call
gbizinfo-company-searchornta-corporate-name-search. - Apply
authority-strip-formatter(4-layer) +shigyo-boundary-disclaimerskills. - Cite
attribution_text+cft_issue_date+source_urlfor every notice.
Output format
- Header: query criteria + total_count + Phase 1 scope notice
- For each notice:
result_id+project_name+organization_namecft_issue_date+category+procedure_typesource_url(公告 detail page)
- Optional cluster signal (category aggregation, organization aggregation) — Kokai normalized layer
- 4-layer authority strip footer
- 行政書士 / 中小企業診断士 / 弁護士 boundary disclaimer
- Phase 1 scope reminder: 受注実績 / 落札結果 / 落札価格 / supplier 情報 は本 API response 未含有、Phase 2 で別 source 経由予定
Boundary
- Output is signal / 確認材料 / context — NOT bid advice or 適格性 judgment.
- 入札判断 / 適格性判断 / 法的判断 / 契約交渉 / 入札価格戦略 requires certified Japanese 行政書士 / 中小企業診断士 / 弁護士.
- Phase 1 scope is API-enforced — never fabricate 受注実績 / 落札結果 / 価格 signal. If asked, redirect to commercial DB (帝国データバンク 入札情報 etc.) or 士業 consultation.
- Cite
attribution_text+cft_issue_date+source_urlfor every referenced notice. - 官公需 portal is operated by 中小企業庁 (SME Agency) for the Japanese government public procurement system. Always preserve attribution.
- Never claim a procurement notice's "outcome" — the API only provides notice metadata, not results.
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.
- 10d ago First seen · 53 lines · 43 tokens per session scan A 616c12ccc082
procurement-discovery-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 43 tokens to every session and 800 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 agents, from other repositories
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
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…
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.…
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.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
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.…