prompt-engineer

prompt-engineer is a skill for Claude Code, Codex from MH4GF/claude-code. It costs 32 tokens per session (1,336 once invoked), scanned A, original, MIT.

A guide for improving prompt files used by Claude Code, including CLAUDE.md, SKILL.md, and custom slash commands. It checks whether instructions are clear, structured, specific, and concise.

In plain words
What is it for?
Use it when creating or editing agent instructions, reusable skills, or slash commands, then review whether the revised prompt preserves the original intent.
Why use it?
It helps prevent coding agents from misunderstanding vague, conflicting, or overly long instructions.

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/mh4gf/claude-code/prompt-engineer
Any agent
npx skills add MH4GF/claude-code --skill prompt-engineer
Clone the repo
git clone --depth 1 https://github.com/MH4GF/claude-code

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 prompt-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/mh4gf/claude-code/prompt-engineer.svg)](https://agentmods.dev/skills/mh4gf/claude-code/prompt-engineer)
Your own site
<a href="https://agentmods.dev/skills/mh4gf/claude-code/prompt-engineer"><img src="https://agentmods.dev/badge/skills/mh4gf/claude-code/prompt-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,336 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 $0.00032 $0.01336
Opus 5 $0.00016 $0.00668
Sonnet 5 $0.00006 $0.00267
Haiku 4.5 $0.00003 $0.00134

Measured 3d ago against content hash 1f6d3f2fdc65, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prompt-engineer 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.

user-scope-backup-2026-07-04/skills/prompt-engineer/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Engineer Skill

Claude Code向けプロンプト文書(CLAUDE.md、SKILL.md、カスタムスラッシュコマンド)の作成・改善を支援する。

対象ファイル

ファイル種別 用途 配置場所
CLAUDE.md プロジェクト固有のコンテキスト・ルール リポジトリルート、~/.claude/
SKILL.md 再利用可能なスキル定義 スキルディレクトリ
カスタムコマンド 繰り返しワークフローのテンプレート .claude/commands/*.md

改善ワークフロー

1. 分析フェーズ

対象プロンプトを以下の観点で評価:

構造面

  • 論理的なセクション分け
  • XMLタグの適切な使用(<instructions>, <context>, <example>等)
  • 情報の優先順位付け

内容面

  • 目的の明確さ
  • 指示の具体性(曖昧な表現の排除)
  • 必要十分な情報量(過不足なし)

Claude特性への適合

  • 命令形・直接的な表現
  • 重要事項の強調(IMPORTANT:, MUST等)
  • 出力形式の明示

2. 改善フェーズ

優先順位

  1. 致命的問題(目的不明確、矛盾する指示)
  2. 効果に直結(具体性不足、構造の混乱)
  3. 品質向上(表現の洗練、エッジケース対応)

主要テクニック

  • 曖昧な指示 → 具体的な行動指示に変換
  • 長文の説明 → 簡潔な箇条書き or 例示
  • 暗黙の期待 → 明示的な制約・条件

3. 検証フェーズ

改善後、以下をチェック:

  • 元の意図が保持されているか
  • Claudeが誤解しうる表現がないか
  • 不要な情報が削除されているか
  • 重要な情報が強調されているか

コア原則

簡潔さが最優先

コンテキストウィンドウは共有資源。すべてのトークンが他の情報と競合する。

前提: Claudeは既に非常に賢い

Claudeが既に知っていることは書かない。各情報に対して以下を問う:

  • 「Claudeは本当にこの説明が必要か?」
  • 「Claudeは既にこれを知っていると仮定できるか?」
  • 「この文はトークンコストに見合う価値があるか?」
# Bad(約150トークン)
PDF(Portable Document Format)はテキスト、画像、その他のコンテンツを含む
一般的なファイル形式です。PDFからテキストを抽出するにはライブラリが必要です。
pdfplumberは使いやすく、ほとんどのケースに対応できるのでお勧めです...

# Good(約50トークン)
PDFテキスト抽出にはpdfplumberを使用:

\`\`\`python
import pdfplumber
with pdfplumber.open("file.pdf") as pdf:
    text = pdf.pages[0].extract_text()
\`\`\`

Good版はClaudeがPDFとライブラリの概念を知っていることを前提としている。

具体性で曖昧さを排除

# Bad
テストを書いてください

# Good
`tests/`に新規テストファイルを作成。edgeケース(null入力、空配列)を含むこと。mockは使用禁止。

構造で意図を伝える

XMLタグで情報を分離。Claudeはタグ構造を強く認識する。

<task>PRをレビューしてコメントを残す</task>

<constraints>
- セキュリティ上の問題は最優先で指摘
- スタイルの指摘は控えめに
- 必ず改善案を提示
</constraints>

<output_format>
各指摘を以下の形式で出力:
- ファイル: 行番号
- 重要度: high/medium/low
- 内容: 指摘事項
- 提案: 改善案
</output_format>

スキル構造変更チェックリスト

ファイル分割・ルーティング追加など、スキルのアーキテクチャを変更する際に確認:

  • SKILL.mdのdescriptionが発動条件を正確に反映しているか
  • 分割先ファイルへのパス参照が正しいか(相対パス)
  • 分割後も単一SKILL.mdから全体の構造が把握できるか
  • 既存の発動トリガー(キーワード・ファイルパターン)が壊れていないか
  • settings.jsonの許可設定に新規ファイルパスの追加が必要か

Read the full file on GitHub · 136 lines

Files

What ships with it

2 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.

  1. 3d ago First seen · 136 lines · 32 tokens per session scan A 1f6d3f2fdc65

Subscribe to this mod's changes

prompt-engineer is a skill published in the GitHub repository MH4GF/claude-code (2 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 1,336 once invoked, about $0.0002 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

systematic-debugging

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

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens