agent-harness-construction SKILL.md skillA

agent-harness-construction from gongyijie85/dsh-ecc is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add gongyijie85/dsh-ecc/agent-harness-construction@git:20260816.bad4355

Pins git:20260816.bad4355 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
gongyijie85/dsh-ecc
Path
skills/agent-harness-construction/SKILL.md
Versions recorded
1
Latest version
git:20260816.bad4355, committed Aug 16, 2026
Size
2,100 bytes
Repository stars
13
License
MIT

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent's tool set, action space, or observation format.

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

# Agent Harness Construction

Use this skill when you are improving how an agent plans, calls tools, recovers from errors, and converges on completion.

## Core Model

Agent output quality is constrained by:
1. Action space quality
2. Observation quality
3. Recovery quality
4. Context budget quality

## Action Space Design

1. Use stable, explicit tool names.
2. Keep inputs schema-first and narrow.
3. Return deterministic output shapes.
4. Avoid catch-all tools unless isolation is impossible.

## Granularity Rules

- Use micro-tools for high-risk operations (deploy, migration, permissions).
- Use medium tools for common edit/read/search loops.
- Use macro-tools only when round-trip overhead is the dominant cost.

## Observation Design

Every tool response should include:
- `status`: success|warning|error
- `summary`: one-line result
- `next_actions`: actionable follow-ups
- `artifacts`: file paths / IDs

## Error Recovery Contract

For every error path, include:
- root cause hint
- safe retry instruction
- explicit stop condition

## Context Budgeting

1. Keep system prompt minimal and invariant.
2. Move large guidance into skills loaded on demand.
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_pymc2zml6orpleue/e7fb390a6663b46ea5d3c2876753a5ce32ba3bad1889686b21a42894caa1742d.json

Then /plugin install agent-harness-construction@markdownregistry-pymc2zml6orpleue in Claude Code. It installs git:20260816.bad4355, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add gongyijie85/dsh-ecc/agent-harness-construction@sha256:e7fb390a6663b46e

The line at the top of this page pins the label git:20260816.bad4355, 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_pymc2zml6orpleue.svg)](https://markdownregistry.com/a/art_pymc2zml6orpleue)

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

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in gongyijie85/dsh-ecc/agent-harness-construction since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of agent-harness-construction from somewhere else? Ask it: where did my agent-harness-construction come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Aug 16, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260816.bad4355 latest2026-08-16 bad4355 2,100 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

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 (2100 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

gongyijie85/dsh-ecc · 13 stars · license MIT · pushed 2026-11-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_pymc2zml6orpleue
GET https://markdownregistry.com/api/v1/resolve?ref=gongyijie85/dsh-ecc/agent-harness-construction
GET https://markdownregistry.com/api/v1/blob/e7fb390a6663b46ea5d3c2876753a5ce32ba3bad1889686b21a42894caa1742d

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 gongyijie85/dsh-ecc

accessibility SKILL.md skill
gongyijie85/dsh-ecc · skills/accessibility/SKILL.md · Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that…
git:20260911.e73abf7 · audit A · 13 stars
agent-architecture-audit SKILL.md skill
gongyijie85/dsh-ecc · skills/agent-architecture-audit/SKILL.md · Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory…
git:20260816.674c4cc · audit A · 13 stars
agent-eval SKILL.md skill
gongyijie85/dsh-ecc · skills/agent-eval/SKILL.md · Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time…
git:20260816.674c4cc · audit A · 13 stars
agent-introspection-debugging SKILL.md skill
gongyijie85/dsh-ecc · skills/agent-introspection-debugging/SKILL.md · Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and…
git:20260816.ee4a89b · audit A · 13 stars
agent-payment-x402 SKILL.md skill
gongyijie85/dsh-ecc · skills/agent-payment-x402/SKILL.md · Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports…
git:20260816.ee4a89b · audit F · 13 stars
agent-self-evaluation SKILL.md skill
gongyijie85/dsh-ecc · skills/agent-self-evaluation/SKILL.md · Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity…
git:20260816.674c4cc · audit A · 13 stars
agent-sort SKILL.md skill
gongyijie85/dsh-ecc · 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:20260816.bad4355 · audit A · 13 stars
agentic-engineering SKILL.md skill
gongyijie85/dsh-ecc · skills/agentic-engineering/SKILL.md · Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when…
git:20260816.674c4cc · audit A · 13 stars
agentic-os SKILL.md skill
gongyijie85/dsh-ecc · skills/agentic-os/SKILL.md · Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash…
git:20260816.ee4a89b · audit A · 13 stars
ai-first-engineering SKILL.md skill
gongyijie85/dsh-ecc · skills/ai-first-engineering/SKILL.md · Engineering operating model for teams where AI agents generate a large share of implementation output. Use when setting…
git:20260816.674c4cc · audit A · 13 stars
ai-regression-testing SKILL.md skill
gongyijie85/dsh-ecc · skills/ai-regression-testing/SKILL.md · Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies…
git:20260816.674c4cc · audit A · 13 stars
android-clean-architecture SKILL.md skill
gongyijie85/dsh-ecc · skills/android-clean-architecture/SKILL.md · Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules…
git:20260816.ee4a89b · audit A · 13 stars

Every file in gongyijie85/dsh-ecc

Other files named agent-harness-construction

agent-harness-construction SKILL.md skill
affaan-m/ecc · docs/ja-JP/skills/agent-harness-construction/SKILL.md · 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。
git:20260517.ec9ace9 · audit A · 305,967 stars
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 · 1,584 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 · 17 stars
agent-harness-construction SKILL.md skill
ronnasayd/aipp · skills/everything-claude-code/agent-harness-construction/SKILL.md · Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
git:20260517.c044376 · audit A · 3 stars

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