What makes ai-architecture-harness-en notable?

1.3K downloads. Trust evidence available

How should ai-architecture-harness-en be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

ai-architecture-harness-en

Establish and use architectural guardrails for AI-assisted coding to prevent architecture collapse, feature regression, and drift across long multi-turn iter... Skill: ai-architecture-harness-en Owner: hgvgfgvh Summary: Establish and use architectural guardrails for AI-assisted coding to prevent architecture collapse, feature regression, and drift across long multi-turn iter... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-05-19T15:32:08.973Z | user - Initial release of ai-architecture-harness skill. - Provides a 4-layer model for architectural guardrails in AI-assisted

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.3k

Updated

Oct 10, 2026

Version

1.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.3K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.3K downloadsadoption · observed Oct 10, 2026
Latest release: 1.0.0release · observed May 19, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s174x9jg32fvtnq226ytye9w3d83h6tm:ai-architecture-harness-en

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-hgvgfgvh-ai-architecture-harness-en/snapshot"

Documentation

CLAWHUB

10,980 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: ai-architecture-harness
description: Establish and use architectural guardrails for AI-assisted coding to prevent architecture collapse, feature regression, and drift across long multi-turn iterations. Use when the user mentions AI coding, Agent coding, architecture collapse, Harness Engineering, design intent, acceptance rules, golden rules, architecture tests, or wants the codebase to be safer for AI Agent modifications.
---

# AI Coding Architecture Guardrails

## Goal

Help coding Agents modify large or complex projects without breaking existing architecture, core functionality, or long-term design intent.

When using this Skill, treat the repository as the source of truth, but treat human-maintained design intent as the highest-level guidance. Do not rely on long conversation history for critical context; key rules must be captured in repo docs or executable checks.

## Core model

Use a four-layer guardrail model:

```text
1. Human design-intent layer
2. Agent-synced architecture and acceptance docs layer
3. Hard automated constraints layer
4. Human review and golden-rules feedback layer
```

The Agent’s job is not free-form improvisation, but safe execution within clear boundaries and feedback loops.

## Recommended doc layout

When creating or improving guardrails for a project, prefer this minimal structure:

```text
AGENTS.md
docs/DESIGN_INTENT.md
docs/ARCHITECTURE.md
docs/ACCEPTANCE_RULES.md
docs/GOLDEN_RULES.md
docs/ARCHITECTURE_DRIFT.md
```

`DESIGN_INTENT.md` is maintained by humans. It records project goals, core architectural principles, non-negotiable tradeoffs, and historical design decisions. It is the “constitution”; do not let the Agent overwrite human intent with the current implementation.

`ARCHITECTURE.md` records the currently confirmed architecture map. It may be periodically synced by the Agent from code and `DESIGN_INTENT.md`, but accidental drift must not be automatically legitimized.

`ACCEPTANCE_RULES.md` records how to verify core features, architectural commitments, and non-regression behavior.

`GOLDEN_RULES.md` records strong rules distilled from real incidents. Each rule should include incident source, forbidden behavior, required behavior, and how to enforce it automatically.

`ARCHITECTURE_DRIFT.md` records gaps between design intent and current implementation, classified as: aligned with intent, reasonable evolution, technical debt, needs human decision, or violates design.

## Before you start coding

Before any non-trivial code change:

1. Read `AGENTS.md` if it exists.
2. Read `docs/DESIGN_INTENT.md`, `docs/ARCHITECTURE.md`, `docs/ACCEPTANCE_RULES.md`, and `docs/GOLDEN_RULES.md` if they exist.
3. Clarify architectural boundaries and behaviors this change must not break.
4. State the scope of this change before editing.
5. Do not proactively perform large refactors, renames, migrations, or abstraction overhauls unless the user explicitly asks.

If the project has no guardrail docs yet, create a

_meta.json

{
  "ownerId": "kn76tv8qxh5ap072zm27re50gh835yje",
  "slug": "ai-architecture-harness-en",
  "version": "1.0.0",
  "publishedAt": 1779204728973
}

skill-card.md

## Description:

Establish and use architectural guardrails for AI-assisted coding to prevent architecture collapse, feature regression, and drift across long multi-turn iterations.

This skill is ready for commercial/non-commercial use.

## Publisher:

[hgvgfgvh](https://clawhub.ai/user/hgvgfgvh)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and engineering teams use this skill to establish repository guardrails for AI-assisted coding, including design-intent docs, architecture acceptance rules, automated constraints, and golden-rule review loops.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill may propose or update architecture guardrail documents and tests in a repository.

Mitigation: Keep documentation and test changes scoped to the project, and review them before adopting them as constraints.

Risk: Overbroad architecture rules can freeze reasonable design evolution or encode incorrect assumptions.

Mitigation: Start with a minimal guardrail set, preserve human-maintained design intent, and classify uncertain drift for human decision.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/hgvgfgvh/skills/ai-architecture-harness-en)

## Skill Output:

**Output Type(s):** [Text, Markdown, Code, Shell commands, Configuration, Guidance]

**Output Format:** [Markdown with optional code and shell command blocks]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May create or update project documentation and tests when the user asks to apply guardrails.]

## Skill Version(s):

1.0.0 (source: server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular