xp-harness: Skill for Claude Code

.claude/skills/skill-design-style/SKILL.md

skill-design-style is a skill for Claude Code from sei-newbear/xp-harness. It costs 70 tokens per session (7,189 once invoked), scanned A, original, MIT.

A set of rules for creating and changing skills, agents, and instruction files in the xp-harness project. It explains how to keep each instruction focused and help the coding agent work more independently.

In plain words
What is it for?
Use it when designing or revising harness instructions, deciding whether guidance belongs to users or maintainers, and reviewing changes to skills, agents, or related files.
Why use it?
It keeps guidance from becoming duplicated, oversized, or scattered, which can make changes harder to understand and maintain. It also clarifies when to involve another agent as a review partner.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is sei-newbear/xp-harness's own configuration. It tells Claude Code how to work on xp-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything xp-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sei-newbear/xp-harness. 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/sei-newbear/xp-harness/main/.claude/skills/skill-design-style/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sei-newbear/xp-harness

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.

agentmods badge for skill-design-style

README.md
[![agentmods](https://agentmods.dev/badge/skills/sei-newbear/xp-harness/skill-design-style.svg)](https://agentmods.dev/skills/sei-newbear/xp-harness/skill-design-style)
Your own site
<a href="https://agentmods.dev/skills/sei-newbear/xp-harness/skill-design-style"><img src="https://agentmods.dev/badge/skills/sei-newbear/xp-harness/skill-design-style.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,189 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 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 $0.00070 $0.07189
Opus 5 $0.00035 $0.03594
Sonnet 5 $0.00014 $0.01438
Haiku 4.5 $0.00007 $0.00719

Measured 8d ago against content hash 3e3599894882, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

skill-design-style 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 8d 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/skill-design-style/SKILL.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skill 設計の流儀 — skill / agent の新規作成・改修時の流儀

なぜこの skill があるか

xp-harness の harness 機構 (= skill / agent / CLAUDE.md) を改修者が改修するとき、規律 / 判断軸 / 改修フローが散在していると、改修者 (main session) が機械的処理に流れて失敗する。本 skill は改修者向けの規律 / 判断軸 / 改修フローを単一の出典 (= single source) として集約する。

中核哲学 (= 改修者の方向性)

依頼者の真のゴール: 自走

改修者が「やりたいこと」を伝えたら、main session (コーディング Agent) が harness 機構に適切に落とし込めるよう、ある程度自走して任せられる状態を実現する。本 skill はその自走を支える規律集。

「依頼者から都度説明を受けないと整理できない」状態を解消し、.apm/ 配下 (= 利用者向け本題) の改修を進められる状態にする。

xp-harness の中核思想

  • 規律装置最小注入: 規律は最小限の文書で注入する。重複させない、肥大化させない
  • ペアプロ哲学: 機械的なチェックよりも subagent / 改修者によるペアプロでの捕捉が筋
  • 単一責任 (= SRP): 各 skill / agent / instruction は単一の責任を持つ

harness 機構の E2E テスト枠組みは未確立

skill / CLAUDE.md / subagent の harness 機構には E2E テスト枠組みが未確立。改修の Done は事前縛りを最小化し、事後評価を許容する。投資フェーズの仕組み作りでは、運用コスト最適化より価値命題の充実を優先する。

subagent はペアプロ的な第三者として 3 用途

reviewer 系の subagent (code-reviewer / e2e-reviewer / pre-implementation-reviewer / done-verifier / skill-reviewer) は、強制 gate ではなくペアプロの相手としての第三者:

  • 改修後の最終レビュー (= 必須)
  • 設計中の壁打ち / 議論 (= 任意・対話的、何度でも)
  • 判断に迷ったときの第三者視点 (= 任意、依頼者に確認する前のステップとして気軽に呼ぶ)

スコープ境界の判別 (= 利用者向け vs 改修者向け)

xp-harness は OSS として skill / agent / instruction を配布する harness。改修対象が「利用者向け」か「改修者向け」かを必ず判別する。

カテゴリ パス 配布 改修方針
利用者向け .apm/skills/* / .apm/agents/* / .apm/instructions/* および .claude/ 配下の対応 symlink (= .apm/ と同じ実体) APM 経由で配布 慎重に、scope 外なら触らない
改修者向け CLAUDE.md (project root) / .claude/skills/philosophy/ / .claude/skills/release/ / .claude/skills/skill-design-style/ / .claude/agents/skill-reviewer.md (それぞれ git tracked、symlink でない) 非配布 philosophy skill と同じパターン、.claude/ 配下に直接コミット

判別法: ls -la で symlink でないことを確認。symlink なら .apm/ 配下と同じものなので利用者向け、symlink でなく直接コミットされていれば改修者向け。

新規 skill / agent を改修者向けで作るときは、必ず .claude/ 配下に直接コミット (= .apm/ には置かない)。

skill 改修フロー (= 改修者が読んで自走する手順)

skill / agent を新規作成・改修するときは、以下の手順を順に通す。

手順 1: 何を / どこに書くか判断 (= 4 軸で位置づける)

skill / description / 本文 / 要件定義.md / 他 skill / CLAUDE.md のどこに書くべきか、以下 4 軸で位置づける:

Read the full file on GitHub · 250 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. 8d ago First seen · 250 lines · 70 tokens per session scan A 3e3599894882

Subscribe to this mod's changes

skill-design-style is a skill published in the GitHub repository sei-newbear/xp-harness (9 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 7,189 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 2026-08-31.

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

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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens