Real Skill packageSource verifiedClawHub registry

agent-harness-architect

Agent Harness 架构设计师。基于通用框架 H=(E,T,C,S,L,V)+P 完成架构设计：澄清需求、吸收用户核心创意、给出专业方案、产出可直接编码的设计文档，并维护自进化知识库（agent harness 框架 + 跨领域设计模式）。触发场景：用户提出「设计 agent 架构」「帮我设计 harness」「@agent-harness」、只有一个 idea 想做成 agent、提供需求分析文档要求架构设计、或想评估/重构已有 agent 架构。

Identity and source

Publisher attributionhanliregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 55% rule confidence
Package forminstruction bundle27 recorded files
Canonical sourceClawHub registryclawhub:neuhanli:agent-harness-architect
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/23/2026.claude/skills/agent-harness-architect

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/23/2026.agents/skills/agent-harness-architect

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/23/2026skills/agent-harness-architect

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @neuhanli/agent-harness-architect
clawhub inspect @neuhanli/agent-harness-architect --version 1.0.0

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
27 / 27 inspected as text
Checked
8/23/2026, 1:06:03 PM
Scanner
0.1.3
Policy
1.0.3
2 inferred permission indicators
  • network access — automatically inferred
  • filesystem write — automatically inferred
3 dependency and API indicators
  • api: clawhub.ai
  • api: github.com
  • api: www.anthropic.com
External clawhub result: clean

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
8/23/2026, 12:13:33 PM
Release binding
Matches this record
  • vt: clean
  • skillspector: clean
  • llm: clean

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:1d1c51fd9f2b5ca3bb9bade350e2117e9001ea9184c21aaed1c58e4f774acb96
Show up to 27 recorded paths
  • assets/clarification-questionnaire.md
  • assets/design-doc.md
  • assets/framework-entry.md
  • assets/pattern-entry.md
  • references/capability-boundary.md
  • references/h-framework.md
  • references/knowledge/frameworks/archive/README.md
  • references/knowledge/frameworks/core/claude-code.md
  • references/knowledge/frameworks/core/codex-harness.md
  • references/knowledge/frameworks/core/deepseek-harness.md
  • references/knowledge/frameworks/core/hermes-agent.md
  • references/knowledge/frameworks/core/openclaw.md
  • references/knowledge/frameworks/inbox/README.md
  • references/knowledge/index.md
  • references/knowledge/patterns/actor-model.md
  • references/knowledge/patterns/capability-security.md
  • references/knowledge/patterns/cqrs.md
  • references/knowledge/patterns/declarative-configuration.md
  • references/knowledge/patterns/dependency-injection.md
  • references/knowledge/patterns/event-sourcing.md
  • references/knowledge/patterns/graph-state-machine.md
  • references/knowledge/patterns/immutable-state.md
  • references/knowledge/patterns/pure-function-effects.md
  • references/knowledge/patterns/reversible-computation.md
  • references/production-checklist.md
  • skill-card.md
  • SKILL.md

Source changelog

Agent Harness Architect 1.0.0 changelog: - Initial release: Launches full-featured agent harness architecture skill based on Anthropic's "Effective Harnesses for Long-Running Agents". - Includes comprehensive diagnosis, optimization planning, and auto-generation of deployable bridge artifacts (progress.json, session protocol, output gate). - Adds references, knowledge base (frameworks + patterns), production checklist, design and questionnaire templates. - Deprecates legacy skill-card.md in favor of new modular documentation structure. - Delivers step-by-step improvement workflow, platform-specific recommendations, and embedded self-improvement protocol.