A Japanese-language workflow for planning and carrying out software work with steering documents. It uses requirement, design, and task-list files to guide implementation and record a review afterward.

Use it to plan a feature, create detailed implementation tasks, track those tasks while coding, and record lessons after verification.

It keeps plans, implementation steps, and progress in one documented place, which reduces the chance of skipping work or losing project decisions.

How sogawa-yk/mcp-gauge configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sogawa-yk/mcp-gauge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/sogawa-yk/mcp-gauge/main/.claude/skills/steering/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/sogawa-yk/mcp-gauge

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sogawa-yk/mcp-gauge/steering/github.svg)](https://agentmods.dev/skills/sogawa-yk/mcp-gauge/steering)

Your own site

<a href="https://agentmods.dev/skills/sogawa-yk/mcp-gauge/steering"><img src="https://agentmods.dev/badge/skills/sogawa-yk/mcp-gauge/steering/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sogawa-yk/mcp-gauge/steering"><img src="https://agentmods.dev/badge/skills/sogawa-yk/mcp-gauge/steering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,978 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 100% copy Near-identical to another mod 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 5.1	$0.00064	$0.03978
Opus 5	$0.00032	$0.01989
Sonnet 5	$0.00013	$0.00796
Haiku 4.5	$0.00006	$0.00398

Measured 10d ago against content hash 68b00d9b7cea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

steering 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.

Origin

This is a copy

100% identical to steering — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/steering/SKILL.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Steering スキル

ステアリングファイル（.steering/）に基づいた実装を支援し、tasklist.mdの進捗管理を確実に行うスキルです。

スキルの目的

ステアリングファイル（requirements.md, design.md, tasklist.md）の作成支援
tasklist.mdに基づいた段階的な実装管理
進捗の自動追跡とtasklist.md更新の強制
実装完了後の振り返り記録

使用タイミング

このスキルは以下のタイミングで使用してください：

作業計画時: ステアリングファイルを作成する時
実装時: tasklist.mdに従って実装する時
検証時: 実装完了後の振り返りを記録する時

モード1: ステアリングファイル作成

目的

新しい機能や変更のためのステアリングファイルを作成します。

手順

ステアリングディレクトリの確認

現在の日付を取得し、`.steering/[YYYYMMDD]-[機能名]/` の形式でディレクトリを作成

永続ドキュメントの確認
- docs/product-requirements.md
- docs/functional-design.md
- docs/architecture.md
- docs/repository-structure.md
- docs/development-guidelines.md
これらを読んで、プロジェクトの方針を理解する
テンプレートからファイル作成

以下のテンプレートを読み込み、プレースホルダーを具体的な内容に置き換えてファイルを作成:
- .claude/skills/steering/templates/requirements.md → .steering/[日付]-[機能名]/requirements.md
- .claude/skills/steering/templates/design.md → .steering/[日付]-[機能名]/design.md
- .claude/skills/steering/templates/tasklist.md → .steering/[日付]-[機能名]/tasklist.md
tasklist.mdの詳細化

requirements.mdとdesign.mdに基づいて、tasklist.mdを詳細化:
- 各フェーズのタスクを具体的に記述
- サブタスクも明確に
- 実装の順序を明記

モード2: 実装（最重要）

目的

tasklist.mdに従って実装を進め、進捗を確実にドキュメントに記録します。

🚨 重要な原則

MUST（必須）:

tasklist.mdを常に開いた状態で実装
タスク開始時に必ずEditツールで[ ]→[x]に更新
タスク完了時に必ずEditツールで完了を記録
tasklist.mdの全タスクが完了するまで作業を継続する
NEVER: tasklist.mdを更新せずに次のタスクに進まない

NEVER（禁止）:

tasklist.mdを見ずに実装を進める
TodoWriteツールだけで進捗管理する（TodoWriteは補助、tasklist.mdが正式）
複数タスクをまとめて更新する（リアルタイムに更新する）
「時間の都合により」「別タスクとして実施予定」などの理由でタスクをスキップする
未完了タスク（[ ]）を残したまま作業を終了する

🚨 タスク完全完了の原則

絶対に守るべきルール:

tasklist.mdの全タスクが完了するまで作業を継続すること
- 全てのタスクが[x]になるまで実装を継続
- 「時間がかかりすぎる」「難しい」などの理由でスキップしない
- 未完了タスクがある状態で振り返りを書かない
タスクスキップは原則禁止
- 「時間の都合により別タスクとして実施予定」は禁止
- 「実装が複雑すぎるため後回し」は禁止
- 「難しいから後で」「テストが面倒」などの理由は禁止
- スキップが許可されるのは技術的な理由のみ（下記参照）
タスクが大きすぎる場合の対処法
- タスクを小さなサブタスクに分割する
- 分割したサブタスクをtasklist.mdに追加
- サブタスクを1つずつ完了させる

Read the full file on GitHub · 387 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

10d ago First seen · 387 lines · 64 tokens per session scan A 68b00d9b7cea

Subscribe to this mod's changes

steering is a skill published in the GitHub repository sogawa-yk/mcp-gauge (0 stars, last pushed 6mo ago), licensed MIT. It adds 64 tokens to every session and 3,978 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to steering, differing in 0 lines, and is treated as a copy.

Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

mcp-gauge: Skill for Claude Code