How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

refine - Prompt - OpenSmartRoute

Name: refine
Author: ondrasek

Prompt file imported from ondrasek/acforge-cli (.claude/commands/issue/refine.md). Fill in {{arguments}} before use. Copyright stays with the author.

GitHub Issue Refinement

Enhance GitHub Issues through intelligent analysis, critical questioning, and comprehensive elaboration with automated workflow integration.

Instructions

Use Task tool to delegate to github-issues-workflow agent:
- Parse {{arguments}} to extract issue number/URL
- Fetch and analyze existing issue content thoroughly
- Conduct comprehensive research on context and dependencies
- Generate critical questions to clarify ambiguous requirements
- Elaborate on technical implementation considerations and edge cases
- Identify potential constraints, risks, and integration points
- Suggest improved acceptance criteria and test scenarios
- Analyze dependencies and cross-references with related issues
- Prepare structured refinement analysis
Present refinement results with:
- Critical Questions: Key clarifications needed from stakeholders
- Technical Analysis: Implementation considerations, constraints, and dependencies
- Enhanced Acceptance Criteria: Specific, measurable, and testable outcomes
- Risk Assessment: Potential issues, edge cases, and mitigation strategies
- Integration Points: Related issues, dependencies, and system impacts
Safety-First GitHub Integration:
- Generate read-only analysis requiring manual human review
- Never automatically modify GitHub issues without explicit approval
- Present refinement suggestions for manual application
- Include workflow automation recommendations with safety constraints

Usage Examples

/issue:refine 90
/issue:refine https://github.com/ondrasek/ai-code-forge/issues/90

Refinement Capabilities

Contextual Research: Analyze codebase, related issues, and project patterns
Critical Analysis: Question assumptions, identify gaps, and propose improvements
Technical Elaboration: Detailed implementation considerations and architecture impacts
Edge Case Detection: Identify potential failure scenarios and boundary conditions
Dependency Mapping: Cross-reference related issues and system components
Acceptance Criteria Enhancement: Transform vague requirements into measurable outcomes

Integration Features

Agent Coordination: Seamlessly integrates with github-issues-workflow agent
Context Preservation: Maintains clean separation between analysis and execution
Workflow Automation: Optional GitHub Actions integration with human oversight
Safety Mechanisms: Prevents infinite loops and over-automation through conservative design

Install refine and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

# GitHub Issue Refinement Enhance GitHub Issues through intelligent analysis, critical questioning, and comprehensive elaboration with automated workflow integration. ## Instructions 1. Use Task tool to delegate to github-issues-workflow agent: - Parse {{arguments}} to extract issue number/URL - Fetch and analyze existing issue content thoroughly - Conduct comprehensive research on context and dependencies - Generate critical questions to clarify ambiguous requirements - Elaborate on technical implementation considerations and edge cases - Identify potential constraints, risks, and integration points - Suggest improved acceptance criteria and test scenarios - Analyze dependencies and cross-references with related issues - Prepare structured refinement analysis 2. Present refinement results with: - **Critical Questions**: Key clarifications needed from stakeholders - **Technical Analysis**: Implementation considerations, constraints, and dependencies - **Enhanced Acceptance Criteria**: Specific, measurable, and testable outcomes - **Risk Assessment**: Potential issues, edge cases, and mitigation strategies - **Integration Points**: Related issues, dependencies, and system impacts 3. **Safety-First GitHub Integration**: - Generate read-only analysis requiring manual human review - Never automatically modify GitHub issues without explicit approval - Present refinement suggestions for manual application - Include workflow automation recommendations with safety constraints ## Usage Examples ``` /issue:refine 90 /issue:refine https://github.com/ondrasek/ai-code-forge/issues/90 ``` ## Refinement Capabilities - **Contextual Research**: Analyze codebase, related issues, and project patterns - **Critical Analysis**: Question assumptions, identify gaps, and propose improvements - **Technical Elaboration**: Detailed implementation considerations and architecture impacts - **Edge Case Detection**: Identify potential failure scenarios and boundary conditions - **Dependency Mapping**: Cross-reference related issues and system components - **Acceptance Criteria Enhancement**: Transform vague requirements into measurable outcomes ## Integration Features - **Agent Coordination**: Seamlessly integrates with github-issues-workflow agent - **Context Preservation**: Maintains clean separation between analysis and execution - **Workflow Automation**: Optional GitHub Actions integration with human oversight - **Safety Mechanisms**: Prevents infinite loops and over-automation through conservative design

{ "prompt": "# GitHub Issue Refinement\n\nEnhance GitHub Issues through intelligent analysis, critical questioning, and comprehensive elaboration with automated workflow integration.\n\n## Instructions\n\n1. Use Task tool to delegate to github-issues-workflow agent:\n - Parse {{arguments}} to extract issue number/URL\n - Fetch and analyze existing issue content thoroughly\n - Conduct comprehensive research on context and dependencies\n - Generate critical questions to clarify ambiguous requirements\n - Elaborate on technical implementation considerations and edge cases\n - Identify potential constraints, risks, and integration points\n - Suggest improved acceptance criteria and test scenarios\n - Analyze dependencies and cross-references with related issues\n - Prepare structured refinement analysis\n\n2. Present refinement results with:\n - **Critical Questions**: Key clarifications needed from stakeholders\n - **Technical Analysis**: Implementation considerations, constraints, and dependencies\n - **Enhanced Acceptance Criteria**: Specific, measurable, and testable outcomes\n - **Risk Assessment**: Potential issues, edge cases, and mitigation strategies\n - **Integration Points**: Related issues, dependencies, and system impacts\n\n3. **Safety-First GitHub Integration**:\n - Generate read-only analysis requiring manual human review\n - Never automatically modify GitHub issues without explicit approval\n - Present refinement suggestions for manual application\n - Include workflow automation recommendations with safety constraints\n\n## Usage Examples\n\n```\n/issue:refine 90\n/issue:refine https://github.com/ondrasek/ai-code-forge/issues/90\n```\n\n## Refinement Capabilities\n\n- **Contextual Research**: Analyze codebase, related issues, and project patterns\n- **Critical Analysis**: Question assumptions, identify gaps, and propose improvements\n- **Technical Elaboration**: Detailed implementation considerations and architecture impacts\n- **Edge Case Detection**: Identify potential failure scenarios and boundary conditions\n- **Dependency Mapping**: Cross-reference related issues and system components\n- **Acceptance Criteria Enhancement**: Transform vague requirements into measurable outcomes\n\n## Integration Features\n\n- **Agent Coordination**: Seamlessly integrates with github-issues-workflow agent\n- **Context Preservation**: Maintains clean separation between analysis and execution\n- **Workflow Automation**: Optional GitHub Actions integration with human oversight\n- **Safety Mechanisms**: Prevents infinite loops and over-automation through conservative design", "variables": [ "arguments" ], "notes": "Intelligently refine GitHub Issues through automated research, critical questioning, and elaboration. Tools: Task. Arguments: <issue number> or <issue URL>.", "metadata": { "source": { "provider": "github-claude-commands", "repository": "https://github.com/ondrasek/acforge-cli", "path": ".claude/commands/issue/refine.md", "ref": "2af5c8e78205cc9aeadb82c437087f461aed3fa7", "url": "https://github.com/ondrasek/acforge-cli/blob/2af5c8e78205cc9aeadb82c437087f461aed3fa7/.claude/commands/issue/refine.md", "key": "ondrasek/acforge-cli/.claude/commands/issue/refine.md" } } }

refine

About

GitHub Issue Refinement

Instructions

Usage Examples

Refinement Capabilities

Integration Features

Install refine and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Use it

Manifest

Reviews