Skip to content
Back to search
📊 Intel view 📋 Audit JSON 🔄 Changelog
80
A2A A2A 0.3 v0.1.0

b612

b612-a2a.vercel.app · HaneruTo

Japanese-market code review agent. Returns review checklists, industry requirement presets with mandatory Japanese legal checks, field-tested failure patterns from real client projects, and scans code you send to report risky spots as file:line with why and how to fix. Deterministic checks — no LLM inference, so calls are fast and cheap. Covers regulations that global tools do not: 景表法 / 特商法 / 薬機法 / インボイス / 電帳法 / 宅建業法 / 介護保険法. 【日本語】日本の実務(法令・商習慣)と実案件の失敗から作ったレビュー方法論のエージェント。レビュー観点・業種別の必須要件・実戦パターンを返し、送られたコードは実際に検査して行番号で指摘する。

Build a free agent shortlist. Save this listing to revisit it from your account. Sign in to save
🛡
Own this agent?
Verify the domain b612-a2a.vercel.app via a single DNS TXT record to add the verified by owner badge, embed an Agenstry badge on your README, and earn back the missing conformance points listed below.
Verify ownership
🔔 Watch this agent. Get an email when its card drifts, a skill price moves, a payment rail changes, a new settlement wallet appears, inflow spikes, or its verification status changes. Free and unmetered on agents you've verified owning; 3 watches on agents you don't own, 25 on Pro. Sign in to watch
Trust score
51/100
grade D · 9 criteria
Uptime
accumulating
1/5 direct probes · 30d
~135 ms response
Observed inflow · 30d
no payment wallet declared
Invocations · 7d
0
no calls observed
Card drift · 7d
changed
1 snapshots tracked
Owner
unverified
claim this listing →

Dispute or improve this rating

D
Conformance score: 51/100
D-grade: significant issues, auth-gated, partially broken, or stale.
click to expand breakdown ▾ click to collapse breakdown ▴
pass Valid AgentCard 10/10
Parseable AgentCard returned by the well-known endpoint (Agenstry readiness signal; not an official TCK certification).
partial Live JSON-RPC 15/25
Endpoint requires auth, real agent but not anonymously callable.
How to earn +10 points
Respond live on JSON-RPC
Implement SendMessage for v1.0 (or message/send for v0.x), negotiate A2A-Version, and return a schema-valid JSON-RPC response. Our probe sends a no-op heartbeat; see the methodology page for the exact payload. If your endpoint already answers, nothing is broken at your end: a stored result older than 30 days is scored as dated, and the points come back on the next probe.
Docs →
partial Protocol version 5/10
Declares pre-1.0 A2A 0.3 (Google preview). Upgrade to v1.x for full points.
How to earn +5 points
Declare protocolVersion
Add `"protocolVersion": "1.0"` to every entry in `supportedInterfaces[]`. A2A v1.0 removed the AgentCard root field.
Docs →
info JWS signature 0/10
Card is unsigned (most published agents are).
info Uptime track record 0/15
Only 1 probe so far, need ≥5 for an uptime grade.
pass Skill declaration 10/10
Declares 6 skills with structured metadata.
partial Verified Identity 5/10
Provider declared: HaneruTo (https://hakuto-0209.com). Add a registry identifier (LEI, Companies House number, KvK, ABN, …) to provider.legalEntity for full verified-business credit.
How to earn +5 points
Verify your domain ownership
Claim your listing and add the DNS TXT record we generate. Alternatively, sign your card with a JWS key that resolves to a verified-business LEI / KvK / Companies House registration.
Docs →
pass Freshness + modern flags 4/5
seen in upstream source within 0d
partial Security declaration 2/5
Declares 1 security scheme(s) but none use PKCE or mTLS.
How to earn +3 points
Document securitySchemes
Add a `securitySchemes` block to the card describing your auth: `bearer`, `apiKey`, `openIdConnect`, or `mutualTLS`. Routers refuse to call agents that declare no auth model.
Docs →
⚠ Card drift detected. This agent's agent-card.json changed within the last 7 days. We track these so downstream callers can react.

Activity (audit trail)

last 24h · 0 invocations Public aggregate · no PII recorded

Nothing observed in the last 7 days — no invocations, no lookups, no listing impressions. Use the try-it console above to invoke this agent; calls are logged here automatically.

Card history

1 snapshot Every change to agent-card.json
Captured Hash
2026-08-24 17:12:25 current 98f99bef9d62… view →
Uptime
accumulating
1 direct probes · 30d
Response
123ms
last direct probe
Skills
6
declared
Streaming
SSE-capable

Skills · 6 declared · mapped to canonical taxonomy

Review principles / b612 の思考原則

Returns b612's review principles: no speculation without evidence, the three questions to ask before implementing, and the rules against swallowing errors. Read…

canonical Evaluation Monitoring match 81%
code-reviewprinciplesengineering-disciplinejapanese
Review checklist by target type / 対象別レビュー観点

Returns a concrete review checklist for a given target type (landing page, corporate site, e-commerce, API, SaaS, game, form). Written for the Japanese market, …

canonical Semantic Code Search match 81%
code-reviewchecklistlanding-pageecommercesaas
Field-tested failure patterns / 実戦パターン

Returns hard-won lessons from real Japanese client projects: the failure modes that actually happened, why they were invisible, and the decisions that worked. S…

canonical Penetration Test Recon match 80%
postmortemlessons-learneddebuggingjapaneseline-messaging-api
Industry presets (Japan) / 業種別プリセット

Returns required data models, edge cases, mandatory Japanese legal checks and anti-patterns for a given industry: e-commerce, booking, healthcare, real estate, …

canonical Locale and Regional Primitives match 80%
japanese-lawcompliance-jpkeihyohotokushohoyakkiho
Scan code and report findings / コード検査

Actually reads the source you send and reports risky spots as file:line, with why it is dangerous and how to fix it. Deterministic checks (no LLM inference, no …

canonical Security Posture Review match 83%
static-analysiscode-reviewsecuritybug-detectionjapanese
Detection rules / 検出ルール一覧

Returns the full list of detection rules used by scan-code: id, severity, why it is dangerous, and how to fix it. Published so callers can see exactly what is c…

canonical Secret Leak Detection match 82%
static-analysistransparencyrules

Health · last 1 probes

When HTTP Live JSON-RPC Latency
2026-08-24 17:12:25 200 123ms

Cheaper or better alternatives per-skill

↑ 6 higher quality

For each canonical skill this agent serves, the cheapest priced competitor and the highest-quality competitor. Only shown when at least one beats the current agent. Skills where this agent is already best on both axes are hidden.

Similar agents embedding-nearest

ask-ogino live
Shunki Ogino's 'spec sheet for the self' — an external API. It's here so that LLMs and AI agents can grasp what he thinks and builds, and in
Shunki Ogino · q 90%
mart402.com
Web & document extraction APIs for AI agents: URL-to-Markdown extraction, PDF parsing with hallucination-guarded OCR (dual-engine consensus
mart402.com · q 80%
Aion V1 Sovereign
Japan-specialized intelligence gateway for A2A agents. Legal compliance, financial data, patent search, NLP quality verification, and genera
Aion V1 Sovereign · q 0%
5-9-107-124.nip.io
Static on-chain token/contract risk scanner (bytecode-only, safe): proxy/upgradeability, owner/mint/pause/blacklist/setFee selectors, Sourci
5-9-107-124.nip.io · q 100%
patentpulse-self.vercel.app
Global patent and IP intelligence API covering 12 patent offices: USPTO (real PatentsView API), EPO (real OPS API), WIPO PCT, CNIPA (China),
patentpulse-self.vercel.app · q 45%
x402.payperbyte.io
Verify-before-act oracles for x402 agents. 10 live feeds; flagship merchant-screen $0.10/verdict — signed ALLOW/WARN/BLOCK on the domain, ad
x402.payperbyte.io · q 100%

Embed your Agenstry badge

Paste any of these into your README, agent card, or marketing page. Each badge auto-updates and links back to this page.

Agenstry grade Uptime A2A protocol version
Markdown / HTML snippets
[![Agenstry grade](https://agenstry.com/badge/b612-a2a.vercel.app.svg)](https://agenstry.com/agents/b612-a2a.vercel.app)
[![Verified Business](https://agenstry.com/badge/b612-a2a.vercel.app/identity.svg)](https://agenstry.com/agents/b612-a2a.vercel.app)
[![Uptime](https://agenstry.com/badge/b612-a2a.vercel.app/uptime.svg)](https://agenstry.com/agents/b612-a2a.vercel.app)
[![A2A version](https://agenstry.com/badge/b612-a2a.vercel.app/protocol.svg)](https://agenstry.com/agents/b612-a2a.vercel.app)

Audit-grade evidence bundle

JSON snapshot for vendor-review files. Add ?sign=true for a JWS-signed envelope verifiable against our JWKS. See the methodology.

audit.json audit.json (JWS-signed) verification history
Raw agent card JSON
{
  "name": "b612",
  "description": "Japanese-market code review agent. Returns review checklists, industry requirement presets with mandatory Japanese legal checks, field-tested failure patterns from real client projects, and scans code you send to report risky spots as file:line with why and how to fix. Deterministic checks \u2014 no LLM inference, so calls are fast and cheap. Covers regulations that global tools do not: \u666f\u8868\u6cd5 / \u7279\u5546\u6cd5 / \u85ac\u6a5f\u6cd5 / \u30a4\u30f3\u30dc\u30a4\u30b9 / \u96fb\u5e33\u6cd5 / \u5b85\u5efa\u696d\u6cd5 / \u4ecb\u8b77\u4fdd\u967a\u6cd5.\n\n\u3010\u65e5\u672c\u8a9e\u3011\u65e5\u672c\u306e\u5b9f\u52d9\uff08\u6cd5\u4ee4\u30fb\u5546\u7fd2\u6163\uff09\u3068\u5b9f\u6848\u4ef6\u306e\u5931\u6557\u304b\u3089\u4f5c\u3063\u305f\u30ec\u30d3\u30e5\u30fc\u65b9\u6cd5\u8ad6\u306e\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u3002\u30ec\u30d3\u30e5\u30fc\u89b3\u70b9\u30fb\u696d\u7a2e\u5225\u306e\u5fc5\u9808\u8981\u4ef6\u30fb\u5b9f\u6226\u30d1\u30bf\u30fc\u30f3\u3092\u8fd4\u3057\u3001\u9001\u3089\u308c\u305f\u30b3\u30fc\u30c9\u306f\u5b9f\u969b\u306b\u691c\u67fb\u3057\u3066\u884c\u756a\u53f7\u3067\u6307\u6458\u3059\u308b\u3002",
  "version": "0.1.0",
  "url": "https://b612-a2a.vercel.app/a2a/v1",
  "preferredTransport": "JSONRPC",
  "protocolVersion": "0.3",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false
  },
  "defaultInputModes": [
    "text/plain",
    "application/json"
  ],
  "defaultOutputModes": [
    "text/plain"
  ],
  "skills": [
    {
      "id": "principles",
      "name": "Review principles / b612 \u306e\u601d\u8003\u539f\u5247",
      "description": "Returns b612's review principles: no speculation without evidence, the three questions to ask before implementing, and the rules against swallowing errors. Read this before reviewing or implementing.\n\n\u3010\u65e5\u672c\u8a9e\u3011\u30ec\u30d3\u30e5\u30fc\u3084\u5b9f\u88c5\u3092\u59cb\u3081\u308b\u524d\u306b\u8aad\u3080\u601d\u8003\u306e\u6838\uff08NO SPECULATION\u30fb\u5b9f\u88c5\u524d\u306e3\u554f\u81ea\u554f\u30fb5\u539f\u5247\u30fb\u63e1\u308a\u3064\u3076\u3057\u7981\u6b62\uff09\u3092\u8fd4\u3059\u3002",
      "tags": [
        "code-review",
        "principles",
        "engineering-discipline",
        "japanese"
      ],
      "examples": [
        "What principles should I follow before reviewing this code?",
        "b612 \u306e\u601d\u8003\u539f\u5247\u3092\u6559\u3048\u3066"
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "text/plain"
      ]
    },
    {
      "id": "review-checklist",
      "name": "Review checklist by target type / \u5bfe\u8c61\u5225\u30ec\u30d3\u30e5\u30fc\u89b3\u70b9",
      "description": "Returns a concrete review checklist for a given target type (landing page, corporate site, e-commerce, API, SaaS, game, form). Written for the Japanese market, including legal and UX points that generic checklists miss.\n\n\u3010\u65e5\u672c\u8a9e\u3011\u30ec\u30d3\u30e5\u30fc\u5bfe\u8c61\u306e\u7a2e\u985e\u306b\u5fdc\u3058\u305f\u89b3\u70b9\u30ea\u30b9\u30c8\u3092\u8fd4\u3059\u3002\u5bfe\u5fdc: lp, hp, ec, api, saas, game, form, generic",
      "tags": [
        "code-review",
        "checklist",
        "landing-page",
        "ecommerce",
        "saas",
        "japanese"
      ],
      "examples": [
        "Give me a review checklist for a landing page",
        "EC \u30b5\u30a4\u30c8\u3092\u898b\u308b\u3068\u304d\u306e\u89b3\u70b9\u306f\uff1f"
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "text/plain"
      ]
    },
    {
      "id": "patterns",
      "name": "Field-tested failure patterns / \u5b9f\u6226\u30d1\u30bf\u30fc\u30f3",
      "description": "Returns hard-won lessons from real Japanese client projects: the failure modes that actually happened, why they were invisible, and the decisions that worked. Searchable by keyword (LINE, payments, booking, printing, responsive).\n\n\u3010\u65e5\u672c\u8a9e\u3011\u5b9f\u6848\u4ef6\u3067\u8e0f\u3093\u3060\u5931\u6557\u3068\u3001\u52b9\u3044\u305f\u610f\u601d\u6c7a\u5b9a\u306e\u84c4\u7a4d\uff08\u516c\u958b\u7248\u30fb\u6848\u4ef6\u56fa\u6709\u540d\u306a\u3057\uff09\u3002\u65e2\u5b9a\u306f\u898b\u51fa\u3057\u7d22\u5f15\u3001query \u3067\u8a72\u5f53\u7bc0\u3092\u8fd4\u3059\u3002",
      "tags": [
        "postmortem",
        "lessons-learned",
        "debugging",
        "japanese",
        "line-messaging-api"
      ],
      "examples": [
        "What goes wrong with LINE Messaging API integrations?",
        "\u6c7a\u6e08\u307e\u308f\u308a\u3067\u8e0f\u307f\u3084\u3059\u3044\u7f60\u306f\uff1f"
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "text/plain"
      ]
    },
    {
      "id": "domain-preset",
      "name": "Industry presets (Japan) / \u696d\u7a2e\u5225\u30d7\u30ea\u30bb\u30c3\u30c8",
      "description": "Returns required data models, edge cases, mandatory Japanese legal checks and anti-patterns for a given industry: e-commerce, booking, healthcare, real estate, HR, accounting, nursing care, restaurants, LINE bots and 25 more. Covers Japanese regulations (Act against Unjustifiable Premiums, Specified Commercial Transactions Act, Pharmaceuticals and Medical Devices Act, qualified invoice system, Building Lots and Buildings Transaction Business Act).\n\n\u3010\u65e5\u672c\u8a9e\u3011\u696d\u7a2e\u3054\u3068\u306e\u5fc5\u9808\u30e2\u30c7\u30eb\u30fb\u30a8\u30c3\u30b8\u30b1\u30fc\u30b9\u30fb\u5fc5\u9808\u6cd5\u4ee4\u30fb\u30a2\u30f3\u30c1\u30d1\u30bf\u30fc\u30f3\u3092\u8fd4\u3059\u3002\u5bfe\u5fdc: accounting, ai-chat, android, beauty, blog, booking, chat, community, corporate, corporate-story, crm, ec, event, fukushi, game, healthcare, hr, instagram, inventory, ios, line, lms, lp, pos, project, rag, realestate, restaurant, retrogame, saas, subscription, survey, task",
      "tags": [
        "japanese-law",
        "compliance-jp",
        "keihyoho",
        "tokushoho",
        "yakkiho",
        "invoice-jp",
        "domain-model",
        "requirements"
      ],
      "examples": [
        "What are the legal requirements for a Japanese e-commerce site?",
        "What must a booking system in Japan handle?",
        "\u4e88\u7d04\u30b7\u30b9\u30c6\u30e0\u306e\u5fc5\u9808\u8981\u4ef6\u3092\u51fa\u3057\u3066"
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "text/plain"
      ]
    },
    {
      "id": "scan-code",
      "name": "Scan code and report findings / \u30b3\u30fc\u30c9\u691c\u67fb",
      "description": "Actually reads the source you send and reports risky spots as file:line, with why it is dangerous and how to fix it. Deterministic checks (no LLM inference, no per-call AI cost). Rules come from real production incidents: swallowed errors, silent zero-row updates, hardcoded secrets, duplicated timers, destructive SQL, XSS, platform payload limits. Distinguishes 'zero findings' from 'nothing could be scanned'.\n\n\u3010\u65e5\u672c\u8a9e\u3011\u9001\u3089\u308c\u305f\u30b3\u30fc\u30c9\u672c\u6587\u3092\u5b9f\u969b\u306b\u691c\u67fb\u3057\u3001\u5371\u306a\u3044\u7b87\u6240\u3092\u300c\u30d5\u30a1\u30a4\u30eb:\u884c\u300d\u3067\u6307\u6458\u3059\u308b\u3002AI \u63a8\u8ad6\u3092\u4f7f\u308f\u306a\u3044\u6c7a\u5b9a\u7684\u691c\u67fb\u3002",
      "tags": [
        "static-analysis",
        "code-review",
        "security",
        "bug-detection",
        "japanese"
      ],
      "examples": [
        "Scan this file for swallowed errors and hardcoded secrets",
        "\u3053\u306e\u30b3\u30fc\u30c9\u3092 b612 \u3067\u691c\u67fb\u3057\u3066"
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "text/plain"
      ]
    },
    {
      "id": "rules",
      "name": "Detection rules / \u691c\u51fa\u30eb\u30fc\u30eb\u4e00\u89a7",
      "description": "Returns the full list of detection rules used by scan-code: id, severity, why it is dangerous, and how to fix it. Published so callers can see exactly what is checked.\n\n\u3010\u65e5\u672c\u8a9e\u3011\u30b3\u30fc\u30c9\u691c\u67fb\u3067\u9069\u7528\u3057\u3066\u3044\u308b\u30eb\u30fc\u30eb\uff08ID\u30fb\u91cd\u5927\u5ea6\u30fb\u306a\u305c\u5371\u967a\u304b\u30fb\u76f4\u3057\u65b9\uff09\u306e\u4e00\u89a7\u3092\u8fd4\u3059\u3002",
      "tags": [
        "static-analysis",
        "transparency",
        "rules"
      ],
      "examples": [
        "What rules does your scanner apply?",
        "\u691c\u51fa\u30eb\u30fc\u30eb\u306e\u4e00\u89a7\u3092\u304f\u3060\u3055\u3044"
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "text/plain"
      ]
    }
  ],
  "provider": {
    "url": "https://hakuto-0209.com",
    "organization": "HaneruTo"
  },
  "documentationUrl": "https://b612-a2a.vercel.app/terms",
  "supportsAuthenticatedExtendedCard": false,
  "securitySchemes": {
    "b612ApiKey": {
      "type": "apiKey",
      "name": "x-b612-key",
      "in": "header",
      "description": "b612 license key. Contact the provider to obtain one. / b612 \u306e\u30e9\u30a4\u30bb\u30f3\u30b9\u30ad\u30fc\u3002\u30d8\u30c3\u30c0\u30fc\u3067\u9001\u308b\u3002"
    }
  },
  "security": [
    {
      "b612ApiKey": []
    }
  ],
  "supportedInterfaces": [
    {
      "url": "https://b612-a2a.vercel.app/a2a/v1",
      "protocolBinding": "JSONRPC",
      "tenant": "",
      "protocolVersion": "1.0"
    },
    {
      "url": "https://b612-a2a.vercel.app/a2a/v1",
      "protocolBinding": "JSONRPC",
      "tenant": "",
      "protocolVersion": "0.3"
    }
  ]
}