What is knowmint AGENTS.md?

Project instructions for developing the KnowMint codebase with Claude Code. They define which project documents take priority, how tasks move from planned to completed, and which checks to run.

Use them when working on KnowMint to follow its documentation order, update task markers, run lint and build checks, and perform the relevant end-to-end tests.

They give agents a consistent process for planning, implementing, verifying, reviewing, and recording work. They also make task status and required evidence explicit.

knowmint AGENTS.md — Instructions file by Sou0327

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.

agentmods

npx agentmods add instructions/sou0327/knowmint/agents-md

Clone the repo

git clone --depth 1 https://github.com/Sou0327/knowmint

Made for: Codex, OpenCode.

Per session 1,087 This file is loaded in full into every session.

When invoked 1,087 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.01087	$0.01087
Opus 5	$0.00544	$0.00544
Sonnet 5	$0.00217	$0.00217
Haiku 4.5	$0.00109	$0.00109

Measured 2d ago against content hash 7a77c06071df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowmint AGENTS.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 2d 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.

AGENTS.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - 開発運用ガイド

プロジェクト: KnowMint
モード: Solo (Claude Code 単体開発)
更新日: 2026-02-16

このファイルは、日々の開発を迷わず進めるための最小運用ルールです。

1. 参照ドキュメントと優先順位

優先	ファイル	役割
1	`CLAUDE.md`	Claude Code 固有ルール・開発原則
2	`Plans.md`	タスク一覧・進捗・受け入れ基準
3	`AGENTS.md`	開発フロー（このファイル）

運用上の判断に迷ったら、上から順に解釈する。

2. 標準ワークフロー (Solo)

1. /plan-with-agent  : Plans.md にタスクと受け入れ基準を定義
2. /work             : 実装 (必要に応じて設計更新)
3. /verify           : lint/build/test で検証
4. /harness-review   : Codex レビューで指摘を解消
5. git commit        : 完了記録

各ステップで「何を満たせば次へ進むか」を明確にすること。

3. タスク管理ルール (Plans.md)

3.1 マーカー

マーカー	意味
`cc:TODO`	未着手
`cc:WIP`	作業中
`cc:完了`	完了
`cc:DONE`	完了（旧表記。新規は `cc:完了` を推奨）
`blocked`	ブロック中

3.2 状態遷移

cc:TODO -> cc:WIP -> cc:完了

3.3 更新ルール

着手時: 対象タスクを cc:WIP に変更
完了時: 受け入れ基準を満たした証跡を残し cc:完了 に変更
ブロック時: blocked を明記し、原因と解除条件を1行で追記

4. 実装時の必須チェック

4.1 最低限の検証コマンド

npm run lint
npm run build

4.2 変更内容に応じた追加検証

# 購入検証の退行防止
npm run test:e2e:fake-tx

# CLI 空環境フロー (login -> search -> install -> publish -> deploy)
npm run test:e2e:cli-flow

関連箇所を変更した場合は、対応する検証を必ず実行する。

5. レビューと品質ゲート

実装完了後は /harness-review を実施
指摘は「再現確認 -> 修正 -> 再検証」の順で解消
レビュー未実施のまま完了扱いにしない

参照ルール

.claude/rules/test-quality.md
テストを通すための改ざん（skip/緩和/削除）を禁止
.claude/rules/implementation-quality.md
形骸化実装（ハードコード、スタブ、握り潰し）を禁止

6. コミットメッセージ規約

feat: 新機能
fix: バグ修正
docs: ドキュメント
refactor: リファクタリング
test: テスト
chore: その他

例:

feat: CLI の dataset publish フローを追加
fix: purchase API の tx_hash 検証不備を修正
docs: Plans.md の Phase 5 進捗を更新

7. Definition of Done (DoD)

タスク完了は、以下をすべて満たした時点とする。

Plans.md の対象タスクが cc:完了
受け入れ基準に対する実行証跡がある
必要な lint/build/test が通過
/harness-review 指摘が解消済み
変更内容に対応するドキュメント更新済み（必要時）

Solo モードでは、Claude Code が Plan -> Work -> Verify -> Review を一貫して実行する。

Read the full file on GitHub · 135 lines

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.

2d ago First seen · 135 lines · 1,087 tokens per session scan A 7a77c06071df

Subscribe to this mod's changes

knowmint AGENTS.md is an instructions file published in the GitHub repository Sou0327/knowmint (3 stars, last pushed 4mo ago), licensed MIT. It adds 1,087 tokens to every session, about $0.0054 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.

ai-agent knowledge marketplace mcp solana x402

knowmint AGENTS.md