steering

A project-memory system that analyzes a codebase and keeps notes about its structure, technologies, purpose, decisions, workflows, commands, and lessons. The supplied instructions require both English and Japanese documentation.

In plain words
What is it for?
Use it to create or maintain architecture, technology, product, workflow, and domain-knowledge documents, record architectural decisions, and detect differences between the code and its documentation.
Why use it?
It gives coding agents persistent project context and can reveal when the notes no longer match the code.

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/nahisaho/codegraphmcpserver/steering
Any agent
npx skills add nahisaho/CodeGraphMCPServer --skill steering
Clone the repo
git clone --depth 1 https://github.com/nahisaho/CodeGraphMCPServer

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,877 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 $0.00052 $0.06877
Opus 5 $0.00026 $0.03438
Sonnet 5 $0.00010 $0.01375
Haiku 4.5 $0.00005 $0.00688

Measured 2d ago against content hash 2de6bc0a1b57, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

.claude/skills/steering/SKILL.md · 851 lines

How it starts

The opening of the file, as written. The whole thing — 851 lines — stays where its author put it; the contents beside it link to each section on GitHub.

役割

あなたは、プロジェクトのコードベースを分析し、プロジェクトメモリ(steeringコンテキスト)を生成・維持する専門家です。アーキテクチャパターン、技術スタック、ビジネスコンテキストを文書化し、すべてのエージェントが参照できる「プロジェクトの記憶」を作成します。

専門領域

コードベース分析

  • アーキテクチャパターン検出: ディレクトリ構造、命名規則、コード組織の分析
  • 技術スタック抽出: 使用言語、フレームワーク、ライブラリ、ツールの特定
  • ビジネスコンテキスト理解: README、ドキュメント、コードコメントからの目的把握

Steeringドキュメント管理

  • structure.md: アーキテクチャパターン、ディレクトリ構造、命名規則
  • tech.md: 技術スタック、フレームワーク、開発ツール、技術制約
  • product.md: ビジネスコンテキスト、製品目的、ユーザー、コア機能
  • project.yml: プロジェクト設定(機械可読形式、エージェント動作のカスタマイズ)

Memory System Management

  • memories/architecture_decisions.md: ADR-style architectural decision records
  • memories/development_workflow.md: Build, test, deployment processes
  • memories/domain_knowledge.md: Business logic, terminology, core concepts
  • memories/suggested_commands.md: Frequently used CLI commands
  • memories/lessons_learned.md: Insights, challenges, best practices

Purpose: Persistent knowledge across conversations, continuous learning, agent collaboration

乖離検出と推奨事項

  • コードとsteeringドキュメントの不一致検出
  • アーキテクチャ改善の提案
  • 技術スタック更新の検出

3. Documentation Language Policy

CRITICAL: 英語版と日本語版の両方を必ず作成

Document Creation

  1. Primary Language: Create all documentation in English first
  2. Translation: REQUIRED - After completing the English version, ALWAYS create a Japanese translation
  3. Both versions are MANDATORY - Never skip the Japanese version
  4. File Naming Convention:
    • English version: filename.md
    • Japanese version: filename.ja.md
    • Example: structure.md (English), structure.ja.md (Japanese)

Document Reference

CRITICAL: 他のエージェントの成果物を参照する際の必須ルール

  1. Always reference English documentation when reading or analyzing existing documents
  2. 他のエージェントが作成した成果物を読み込む場合は、必ず英語版(.md)を参照する
  3. If only a Japanese version exists, use it but note that an English version should be created
  4. When citing documentation in your deliverables, reference the English version
  5. ファイルパスを指定する際は、常に .md を使用(.ja.md は使用しない)

Read the full file on GitHub · 851 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. 2d ago First seen · 851 lines · 52 tokens per session scan A 2de6bc0a1b57

Subscribe to this mod's changes

steering is a skill published in the GitHub repository nahisaho/CodeGraphMCPServer (12 stars, last pushed 8mo ago), licensed MIT. It adds 52 tokens to every session and 6,877 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

ljg-learn

Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or…

lijigang/ljg-skills · 113 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.

nexu-io/html-anything · 25 tokens

pedagogy-review

Holistic pedagogical review of a lecture deck (.qmd or .tex). Checks narrative arc, prerequisite assumptions, worked examples, notation clarity, and deck-level pacing. Use when user says "pedagogy review", "does this teach well?", "is the flow right?", "will students follow?", "review the narrative", or before…

pedrohcgs/claude-code-my-workflow · 90 tokens

master-yinguang

Use when user asks about 印光大师, 净土, 念佛, 持名念佛, 十念法, 摄耳谛听, 老实念佛, 信愿行, 带业往生, 仗佛慈力, 自力他力, 竖出横超, 往生, 极乐, 阿弥陀佛, 净土三经, 敦伦尽分, 闲邪存诚, 因果报应, 文钞, 一函遍复, or wants teaching in 印光大师 Yinguang's voice. Triggers include "印光"、"文钞"、"老实念佛"、"信愿行"、"带业往生"、"仗佛慈力"、"横超竖出"、"都摄六根"、"净念相继"、"敦伦尽分"、"闲邪存诚"、"因果"、"十念法"、"摄耳谛听"、"一函遍复"、"净土三经"、"往生" — invoke…

xr843/Master-skill · 274 tokens