agent-harness-construction SKILL.md skillA

agent-harness-construction from affaan-m/ecc is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add affaan-m/ecc/agent-harness-construction@git:20260517.ec9ace9

Pins git:20260517.ec9ace9 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
affaan-m/ecc
Path
docs/ja-JP/skills/agent-harness-construction/SKILL.md
Versions recorded
1
Latest version
git:20260517.ec9ace9, committed May 17, 2026
Size
2,848 bytes
Repository stars
299,696
License
MIT

AI エージェントのアクション空間、ツール定義、観測フォーマットを設計・最適化して完了率を向上させます。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# エージェントハーネス構築

エージェントの計画、ツール呼び出し、エラーからの回復、完了への収束を改善する場合にこのスキルを使用します。

## コアモデル

エージェントの出力品質は以下によって制約されます:
1. アクション空間の品質
2. 観測の品質
3. 回復の品質
4. コンテキストバジェットの品質

## アクション空間の設計

1. 安定した明示的なツール名を使用する。
2. 入力スキーマファーストで絞り込んだものにする。
3. 決定論的な出力形状を返す。
4. 分離が不可能な場合を除き、キャッチオールツールは避ける。

## 粒度ルール

- 高リスク操作(デプロイ、マイグレーション、権限)にはマイクロツールを使用する。
- 一般的な編集・読み取り・検索ループには中規模ツールを使用する。
- ラウンドトリップのオーバーヘッドが支配的なコストである場合のみマクロツールを使用する。

## 観測の設計

すべてのツールレスポンスに含めるべき内容:
- `status`: success|warning|error
- `summary`: 一行の結果
- `next_actions`: 実行可能なフォローアップ
- `artifacts`: ファイルパス / ID

## エラー回復コントラクト

すべてのエラーパスに含めるべき内容:
- 根本原因のヒント
- 安全なリトライ指示
- 明示的な停止条件

## コンテキストバジェット管理

1. システムプロンプトを最小限かつ不変に保つ。
2. 大きなガイダンスはオンデマンドで読み込まれるスキルに移動する。
3. 長いドキュメントをインラインで挿入するより、ファイルへの参照を優先する。
4. 任意のトークン閾値ではなく、フェーズの境界でコンパクト化する。

## アーキテクチャパターンガイダンス

- ReAct: 不確実なパスを持つ探索的タスクに最適。
- 関数呼び出し: 構造化された決定論的フローに最適。
- ハイブリッド(推奨): ReAct 計画 + 型付きツール実行。

## ベンチマーク

追跡すべき指標:
- 完了率
- タスクあたりのリトライ数
- pass@1 および pass@3
- 成功タスクあたりのコスト

## アンチパターン

- セマンティクスが重複するツールが多すぎる。
- 回復ヒントのない不透明なツール出力。
- 次のステップなしのエラーのみの出力。
- 無関係な参照でコンテキストを過負荷にする。

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add affaan-m/ecc/agent-harness-construction@sha256:73fb1a7601ec7c0b

The line at the top of this page pins the label git:20260517.ec9ace9, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_tk25enyzunyii67h.svg)](https://markdownregistry.com/a/art_tk25enyzunyii67h)

6 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on May 17, 2026.

versioncommittedcommitsizeaudit
git:20260517.ec9ace9 latest2026-05-17 ec9ace9 2,848 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2848 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

affaan-m/ecc · 299,696 stars · license MIT · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_tk25enyzunyii67h
GET https://markdownregistry.com/api/v1/resolve?ref=affaan-m/ecc/agent-harness-construction
GET https://markdownregistry.com/api/v1/blob/73fb1a7601ec7c0bced1cb8025940c1aa27409d324136b2ff77300dbdf73b43a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from affaan-m/ecc

agent-introspection-debugging SKILL.md skill
affaan-m/ecc · .agents/skills/agent-introspection-debugging/SKILL.md · Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and…
git:20260918.c752aac · audit A · 299,696 stars
agent-sort SKILL.md skill
affaan-m/ecc · .agents/skills/agent-sort/SKILL.md · Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras…
git:20260918.c752aac · audit A · 299,696 stars
api-design SKILL.md skill
affaan-m/ecc · .agents/skills/api-design/SKILL.md · REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning…
git:20260918.c752aac · audit A · 299,696 stars
article-writing SKILL.md skill
affaan-m/ecc · .agents/skills/article-writing/SKILL.md · Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice…
git:20260918.c752aac · audit A · 299,696 stars
backend-patterns SKILL.md skill
affaan-m/ecc · .agents/skills/backend-patterns/SKILL.md · Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express…
git:20260918.c752aac · audit A · 299,696 stars
benchmark-methodology SKILL.md skill
affaan-m/ecc · .agents/skills/benchmark-methodology/SKILL.md · Use after competitive-platform-analysis has produced a tiered competitor set. Scores each competitor across nine…
git:20260918.c752aac · audit A · 299,696 stars
brand-discovery SKILL.md skill
affaan-m/ecc · .agents/skills/brand-discovery/SKILL.md · Use when a brand needs to discover or articulate its identity through structured multi-session interviews. Covers…
git:20260918.c752aac · audit A · 299,696 stars
brand-voice SKILL.md skill
affaan-m/ecc · .agents/skills/brand-voice/SKILL.md · Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that…
git:20260918.c752aac · audit A · 299,696 stars
bun-runtime SKILL.md skill
affaan-m/ecc · .agents/skills/bun-runtime/SKILL.md · Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel…
git:20260928.48decd0 · audit B · 299,696 stars
change-impact SKILL.md skill
affaan-m/ecc · .agents/skills/change-impact/SKILL.md · Perform evidence-backed impact analysis before changing code, data, interfaces, or governance documents, then compare…
git:20261002.4f08958 · audit A · 299,696 stars
coding-standards SKILL.md skill
affaan-m/ecc · .agents/skills/coding-standards/SKILL.md · Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed…
git:20260918.c752aac · audit A · 299,696 stars
competitive-platform-analysis SKILL.md skill
affaan-m/ecc · .agents/skills/competitive-platform-analysis/SKILL.md · Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any…
git:20260918.c752aac · audit A · 299,696 stars

Every file in affaan-m/ecc

Other files named agent-harness-construction

agent-harness-construction SKILL.md skill
hashgraph-online/awesome-codex-plugins · plugins/Colin4k1024/tsp/skills/agent-harness-construction/SKILL.md · Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
git:20260512.6523792 · audit A · 1,537 stars
agent-harness-construction SKILL.md skill
frankxai/claude-skills-library · absorbed/harness/agent-harness-construction/SKILL.md · Shape an agent's tools, observations, and recovery without adding a second coordinator. Use when defining a tool, a…
git:20261010.682b2ce · audit A · 47 stars
agent-harness-construction SKILL.md skill
fridrichmethod/awesome-skills · skills/agent-harness-construction/SKILL.md · Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
git:20260517.81511a7 · audit A · 15 stars

Browse by kind, by grade A, or by owner.