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.
npx agentmods add instructions/sei-newbear/xp-harness/claude-mdgit clone --depth 1 https://github.com/sei-newbear/xp-harnessWrote 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.
[](https://agentmods.dev/instructions/sei-newbear/xp-harness/claude-md)<a href="https://agentmods.dev/instructions/sei-newbear/xp-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/sei-newbear/xp-harness/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02898 | $0.02898 |
| Opus 5 | $0.01449 | $0.01449 |
| Sonnet 5 | $0.00580 | $0.00580 |
| Haiku 4.5 | $0.00290 | $0.00290 |
Grade A, and why
xp-harness CLAUDE.md 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xp-harness — このリポジトリで作業するときの working rules
このファイルは xp-harness 本体を改修するとき に守るべき改修者向け instruction。consumer に配布される skill / instruction ではない (= project root の CLAUDE.md は consumer 配布対象外)。
依頼者の真のゴール (= 改修者の方向性)
改修者が「やりたいこと」を伝えたら、main session (= コーディング Agent、現時点では Claude Code 等) が xp-harness の harness 機構 (= skill / CLAUDE.md / subagent) 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。
ここでの自走は「止まらず手を動かすこと」ではない (= philosophy の「対話と自走の境界」の通り、依頼者の意図を汲み、認識を揃えてから実行すること)。認識を揃える前に成果物を作るのは自走でなく自己満足で、ズレていれば手戻りを生む。カードや直前の会話で方向が見えても、それは「着手してよい合図」であって「認識が揃った」ではない。揃っていなければ、手を動かす前に揃える。
改修者が都度説明しないと整理できない状態が続くと、.apm/ 配下 (= 利用者向け本題) の改修が全く進まない。本リポジトリの改修者向け装置 (= 本 CLAUDE.md / .claude/skills/philosophy/ / .claude/skills/skill-design-style/ / .claude/agents/skill-reviewer.md) はすべて、その自走を支えるためのもの。
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 → harness 改修の Done は事前縛り最小化、事後評価許容
- 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
詳細な中核思想は .claude/skills/philosophy/SKILL.md に集約。常時 context に乗せる:
@.claude/skills/philosophy/SKILL.md
詳細な規律 / 判断軸 / 改修フローは .claude/skills/skill-design-style/SKILL.md に集約されている (= 下記の埋め込み参照を参照)。
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 |
|---|---|---|
| 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 |
| 改修者向け | CLAUDE.md (project root) / .claude/skills/harness-verification/ / .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 |
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)。philosophy skill / skill-design-style / skill-reviewer と同じパターン。
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.
- 5d ago First seen · 109 lines · 2,898 tokens per session scan A 4f4c84fbd72c
xp-harness CLAUDE.md is an instructions file published in the GitHub repository sei-newbear/xp-harness (9 stars, last pushed 28d ago), licensed MIT. It adds 2,898 tokens to every session, about $0.0145 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.