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.
npx agentmods add instructions/sou0327/knowmint/claude-mdgit clone --depth 1 https://github.com/Sou0327/knowmintWrote 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/instructions/sou0327/knowmint/claude-md)<a href="https://agentmods.dev/instructions/sou0327/knowmint/claude-md"><img src="https://agentmods.dev/badge/instructions/sou0327/knowmint/claude-md.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 | $0.01623 | $0.01623 |
| Opus 5 | $0.00812 | $0.00812 |
| Sonnet 5 | $0.00325 | $0.00325 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
knowmint CLAUDE.md 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 3d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Info
- GitHub:
Sou0327/knowmint— リポジトリ URL を使う際は必ずこれを使用すること - 本番: https://knowmint.shop
Project Overview
KnowMint — AIエージェントが x402 プロトコルで SOL を直接自律支払いできる、初のナレッジマーケットプレイス。
人間が体験知・暗黙知を出品 → エージェントが自律発見・直接支払い（秘密鍵は運営非保有）。
AIエージェントを活用した知識調達にも対応（エージェント提案 → 人間承認 → 作業再開）。
仮想通貨 (Solana / x402) で決済。3つのアクセスレイヤー: Web UI / CLI (km) / REST API+MCP。
Commands
npm run dev # 開発サーバー (localhost:3000)
npm run build # プロダクションビルド
npm run lint # ESLint
npm run km -- <command> # CLI ツール (cli/bin/km.mjs)
npm run km-mcp # MCP サーバー (stdio) ※ Node.js 22.6+ 必須
npm run build:cf # Cloudflare Workers ビルド
npm run deploy:cf # Cloudflare Workers デプロイ
npm run test:unit # Unit テスト (202件)
npm run test:staging # Staging 統合テスト
npm run test:e2e:cli-flow # CLI E2E テスト
npm run test:e2e:fake-tx # 偽トランザクション拒否テスト
npm run test:e2e:x402-flow # HTTP 402 ペイメントゲートテスト
npm run test:e2e:devnet # devnet 実送金テスト
npm run test:e2e:ui # Maestro UI E2E (18フロー)
Architecture
Next.js 16 App Router + Supabase + Solana 決済。詳細は @docs/architecture.md 参照。
Supabase クライアント使い分け (重要)
| クライアント | ファイル | 用途 | RLS |
|---|---|---|---|
| Browser | lib/supabase/client.ts |
クライアントコンポーネント | 適用 |
| Server | lib/supabase/server.ts |
RSC, Server Actions | 適用 |
| Admin | lib/supabase/admin.ts |
API routes のみ | バイパス |
API routes は Admin クライアントで RLS をバイパスし、withApiAuth 内で手動認可する。
API Route パターン
ほとんどの route は withApiAuth HOC + getAdminClient() + apiSuccess()/apiError() を使用。
/api/v1/keys は例外 (独自認証)。認証フロー: IP rate limit → APIキー(SHA-256) → パーミッション → キー別 rate limit
コンテンツ分離 (セキュリティ)
knowledge_items— 公開情報 +preview_contentknowledge_item_contents— 購入者のみアクセス可 (RLS で保護)
Environment Variables
必須: NEXT_PUBLIC_SUPABASE_URL / NEXT_PUBLIC_SUPABASE_ANON_KEY / SUPABASE_SERVICE_ROLE_KEY
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.
- 3d ago First seen · 106 lines · 1,623 tokens per session scan A 3121b163cad2
knowmint CLAUDE.md is an instructions file published in the GitHub repository Sou0327/knowmint (3 stars, last pushed 4mo ago), licensed MIT. It adds 1,623 tokens to every session, about $0.0081 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 instructions, from other repositories
spree CLAUDE.md
Claude Code instructions for spree/spree, covering spree commerce — development rules, plans & architecture decisions, monorepo structure, development server (worktrees) and general rules.
pumpfun-bonkfun-bot CLAUDE.md
Instructions for chainstacklabs/pumpfun-bonkfun-bot, covering agent guide, ground rules, layout, naming inside learning-examples/ and commands.
agent-wallet-sdk AGENTS.md
Instructions for up2itnow0822/agent-wallet-sdk, covering agents.md -- agent wallet sdk, purpose, ownership, local contracts and work guidance.
tiny.place CLAUDE.md
Claude Code instructions for tinyhumansai/tiny.place, covering claude.md, what this repo is, repo layout, getting started and commands.
marketplace-mcp AGENTS.md
AGENTS.md instructions for YegorMy/marketplace-mcp, covering agent notes, rules and verification.
dexter-mcp AGENTS.md
AGENTS.md instructions for Dexter-DAO/dexter-mcp, covering dexter mcp agents, current mcp architecture (wip), apps sdk build & deploy, build commands and architecture.