kmt-doc-rules

kmt-doc-rules is a skill for Claude Code, Codex from tkumata/AGENTS.md. It costs 26 tokens per session (1,108 once invoked), scanned A, original, MIT.

A documentation guide that turns an informal brain dump into an implementation-ready software document while preserving the user's intent. It defines when to update requirements, specifications, design, product documents, architecture decisions, or plans, then stops for approval.

In plain words
What is it for?
Structuring product and engineering notes into requirements, specifications, designs, architecture decisions, or implementation plans.
Why use it?
It separates confirmed requirements from assumptions and open questions without changing source code during documentation.

Skill for Claude CodeCodex

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 skills/tkumata/agents.md/kmt-doc-rules
Any agent
npx skills add tkumata/AGENTS.md --skill kmt-doc-rules
Clone the repo
git clone --depth 1 https://github.com/tkumata/AGENTS.md

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for kmt-doc-rules

README.md
[![agentmods](https://agentmods.dev/badge/skills/tkumata/agents.md/kmt-doc-rules.svg)](https://agentmods.dev/skills/tkumata/agents.md/kmt-doc-rules)
Your own site
<a href="https://agentmods.dev/skills/tkumata/agents.md/kmt-doc-rules"><img src="https://agentmods.dev/badge/skills/tkumata/agents.md/kmt-doc-rules.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,108 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.01108
Opus 5 $0.00013 $0.00554
Sonnet 5 $0.00005 $0.00222
Haiku 4.5 $0.00003 $0.00111

Measured today against content hash d248405567b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

kmt-doc-rules 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 today.

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.

codex-skills/kmt-doc-rules/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kmt Doc Rules

ユーザの brain dump から意図を保ったまま実装可能な文書へ一度の整理する。文書化後は承認待ちで停止し、実装後の再計画や Finalization はこのスキルで行わない。

Rules

  • KISS の原則に従い、要件を満たす最も単純な設計・実装を選び、不要な複雑化・抽象化・間接層を追加しないこと。
  • YAGNI の原則に従い、現在の要件で明示的に必要とされていない機能、抽象化、汎用化、拡張ポイント、将来対応のためのコードを追加しないこと。
  • 未決定事項、例、候補を要求や決定として扱わない。
  • 仮定を置く場合は仮定として明示し、実装結果を左右する不明点は Open Questions に残す。
  • 実装に直接関係する既存文書とコードだけを確認する。
  • リポジトリ全体、無関係な履歴、過去の計画を網羅的に調査しない。
  • 内容が変わる文書だけを作成または更新する。
  • 同じ説明を複数の文書へ重複して記載しない。
  • 文書化中はソースコードを変更しない。
  • 一回の bounded pass で成果物を作成し、追加の自動調査、再計画、整合性ループを開始しない。

Artifact

  • docs/current/REQUIREMENTS.md: 機能要求、非機能要求、制約、受け入れ条件が変わる場合
  • docs/current/SPECIFICATIONS.md: 外部動作、入出力、状態遷移、エラー、境界条件が変わる場合
  • docs/current/DESIGN.md: 責務分割、依存方向、外部境界、データ構造が変わる場合
  • docs/current/PRD.md: 製品背景、対象ユーザ、ゴール、スコープ、成功指標が変わる場合
  • docs/adr/NNNN-short-title.md: 長期的な変更コストを持つ設計判断がある場合
  • docs/plans/active/YYYY-MM-DD-short-name.md: 複数ファイル、複数フェーズ、別セッションでの継続、またはユーザが計画を求めた場合
  • docs/plans/completed/YYYY-MM-DD-short-name.md: active plan が完了した場合

単一ファイルの明白な小変更や、計画を必要としない清書では active plan を作成しない。ADR の判断内容は上書きせず、判断を変更する場合は新しい ADR を作成する。

Workflow

  1. Goal / Scope / Non-goals / Requirements / Open Questions を抽出する。
  2. 実装に直接関係する既存文書とコードだけを確認する。
  3. 要件定義書、仕様書、設計書、PRD、ADR、active plan を成果物とする。
  4. 実装担当が判断できない未決定事項を Open Questions に残す。
  5. 成果物、未決定事項、対象外、次の承認対象を短く報告して停止する。

Active Plan Template

active plan を作成する場合は、次の最小構成を使う。不要な節は省略する。

# <title>

## Status

- Phase: awaiting_approval
- Approval: pending

## Goal

## Scope

## Non-goals

## Required Behavior

## Tasks

### Task 1: <name>

- Objective:
- Scope:
- Acceptance Criteria:
- Verification:

### Task NN: <name>

- Objective:
- Scope:
- Acceptance Criteria:
- Verification:

## Open Questions

## References

各 Task は目的が 1 つで、主要な変更が 1 つであり、独立して検証可能でなければならない。Acceptance Criteria と Verification は観測可能な内容にする。

Done

以下を満たしたら文書化を終了する。

  • brain dump が重複なく清書されている
  • Scope と Non-goals が明確である
  • 未決定事項が Open Questions に残っている
  • 成果物だけが作成または更新されている
  • Acceptance Criteria と Verification が検証可能である
  • active plan を作成した場合は Phase: awaiting_approvalApproval: pending である
  • ソースコードを変更していない

Read the full file on GitHub · 96 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.

  1. today Changed · -22 lines · -13 tokens per session d248405567b1
  2. 5d ago First seen · 118 lines · 39 tokens per session scan A f048f0bfef91

Subscribe to this mod's changes

kmt-doc-rules is a skill published in the GitHub repository tkumata/AGENTS.md (1 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 1,108 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.

Related

Other skills, from other repositories

git-workflow

This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…

Galaxy-Dawn/claude-scholar · 64 tokens

daily-paper-generator

Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.

Galaxy-Dawn/claude-scholar · 47 tokens

codex-autoresearch

Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…

leo-lilinxiao/codex-autoresearch · 80 tokens

map-wayfind

Decision-frontier wayfinding: build and work a durable map of open design decisions BEFORE planning, for large or foggy efforts where /map-plan would force premature decomposition. Use when a task is too big or too vague to decompose — many unknowns, tangled decisions, or "I'm not even sure what to build yet" — and…

azalio/map-framework · 182 tokens

map-fast

Minimal workflow for small, low-risk changes — no planning, no learning.

azalio/map-framework · 17 tokens

clipboard

Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".

CodeAlive-AI/ai-driven-development · 36 tokens