.claude/skills/agent-harness-architectRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
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。
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/agent-harness-architectRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/agent-harness-architectRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/agent-harness-architectRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
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-architectclawhub inspect @neuhanli/agent-harness-architect --version 1.0.2This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
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.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:03b3c5f30579e12b11bf4f4a985c966b074d2dfa3f9854df5514b902e0c30b8bassets/clarification-questionnaire.mdassets/design-doc.mdassets/example-design-doc.mdassets/framework-entry.mdassets/pattern-entry.mdreferences/capability-boundary.mdreferences/framework-archive.mdreferences/framework-claude-code.mdreferences/framework-codex-harness.mdreferences/framework-deepseek-harness.mdreferences/framework-hermes-agent.mdreferences/framework-inbox.mdreferences/framework-letta.mdreferences/framework-mini-swe-agent.mdreferences/framework-openclaw.mdreferences/h-framework.mdreferences/knowledge-index.mdreferences/pattern-actor-model.mdreferences/pattern-capability-security.mdreferences/pattern-cqrs.mdreferences/pattern-declarative-configuration.mdreferences/pattern-dependency-injection.mdreferences/pattern-event-sourcing.mdreferences/pattern-graph-state-machine.mdreferences/pattern-immutable-state.mdreferences/pattern-pure-function-effects.mdreferences/pattern-reversible-computation.mdreferences/production-checklist.mdskill-card.mdSKILL.md- Improved documentation and workflow details for Agent Harness architecture design, emphasizing rigorous standards and professional delivery. - Clearly defines activation triggers, capability boundaries, and core framework structure (H = E,T,C,S,L,V + P). - Outlines detailed, step-by-step clarification and design processes, including specific criteria for producing directly codeable design documents. - Expands on evolution and curation of a knowledge base with strict inclusion criteria and transparent decision-making. - Establishes mandatory deliverables and quality gates for successful handover, including adversarial review and explicit bias self-checks.
Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.
These older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.
sha256:1d1c51fd9f2b5ca3bb9bade350e2117e9001ea9184c21aaed1c58e4f774acb96