Model Recommendation
Pick the right GitHub Copilot model for a given .agent.md or .prompt.md based on task complexity, capabilities, and subscription tier.
Overview
model-recommendation is an agent skill for the Build phase that analyzes Copilot .agent.md or .prompt.md files and recommends optimal AI models with cost and capability rationale.
Install
npx skills add https://github.com/github/awesome-copilot --skill model-recommendationWhat is this skill?
- Analyzes .agent.md and .prompt.md purpose, complexity, and required capabilities
- Maps recommendations across GPT-4.1, GPT-5 family, Claude Sonnet/Opus, Gemini, Grok, o3/o4-mini with deprecation context
- Factors Copilot Free, Pro, and Pro+ completion and premium multipliers
- Notes VS Code model auto-selection pool (Sept 2025+) excluding premium multipliers above 1
- Explains rationale for cost-efficiency vs performance trade-offs
- 14+ named Copilot models in scope including GPT-4.1 through o4-mini
Adoption & trust: 8.5k installs on skills.sh; 34.6k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You wrote a chat mode or prompt file but do not know which Copilot model balances quality, speed, and premium quota for that workload.
Who is it for?
Indie builders authoring Copilot agents who need tier-aware model matching before enabling a mode in daily workflow.
Skip if: Non-Copilot stacks (pure Claude Code or Cursor-only projects) where GitHub model names and premium rules do not apply.
When should I use this skill?
You have a .agent.md or .prompt.md path and need optimal Copilot model recommendations for task complexity and subscription tier.
What do I get? / Deliverables
You receive ranked model suggestions with task-specific rationale tied to your subscription tier so you can set the model in Copilot confidently.
- Ranked model recommendations
- Capability and cost rationale
- Tier-aware usage notes
Recommended Skills
Journey fit
Build → agent-tooling is where chat modes and prompt files are authored and tuned; model choice directly affects agent behavior and cost. Subphase agent-tooling covers analyzing chatmode/prompt definitions and aligning them with Copilot model strengths and premium limits.
How it compares
Structured model matrix for a specific prompt file—not generic “use the biggest model” chat advice.
Common Questions / FAQ
Who is model-recommendation for?
Solo developers using GitHub Copilot who maintain .agent.md or .prompt.md files and want data-informed model selection.
When should I use model-recommendation?
Use it in Build agent-tooling when defining a new chat mode, before Ship review if a prompt drives automated review, or when Validate scope needs a cheaper mini model for experiments.
Is model-recommendation safe to install?
It reads prompt files you specify and returns recommendations; check the Security Audits panel on this Prism page for the skill package source.
SKILL.md
READMESKILL.md - Model Recommendation
# AI Model Recommendation for Copilot Chat Modes and Prompts ## Mission Analyze `.agent.md` or `.prompt.md` files to understand their purpose, complexity, and required capabilities, then recommend the most suitable AI model(s) from GitHub Copilot's available options. Provide rationale based on task characteristics, model strengths, cost-efficiency, and performance trade-offs. ## Scope & Preconditions - **Input**: Path to a `.agent.md` or `.prompt.md` file - **Available Models**: GPT-4.1, GPT-5, GPT-5 mini, GPT-5 Codex, Claude Sonnet 3.5, Claude Sonnet 4, Claude Sonnet 4.5, Claude Opus 4.1, Gemini 2.5 Pro, Gemini 2.0 Flash, Grok Code Fast 1, o3, o4-mini (with deprecation dates) - **Model Auto-Selection**: Available in VS Code (Sept 2025+) - selects from GPT-4.1, GPT-5 mini, GPT-5, Claude Sonnet 3.5, Claude Sonnet 4.5 (excludes premium multipliers > 1) - **Context**: GitHub Copilot subscription tiers (Free: 2K completions + 50 chat/month with 0x models only; Pro: unlimited 0x + 1000 premium/month; Pro+: unlimited 0x + 5000 premium/month) ## Inputs Required: - `${input:filePath:Path to .agent.md or .prompt.md file}` - Absolute or workspace-relative path to the file to analyze Optional: - `${input:subscriptionTier:Pro}` - User's Copilot subscription tier (Free, Pro, Pro+) - defaults to Pro - `${input:priorityFactor:Balanced}` - Optimization priority (Speed, Cost, Quality, Balanced) - defaults to Balanced ## Workflow ### 1. File Analysis Phase **Read and Parse File**: - Read the target `.agent.md` or `.prompt.md` file - Extract frontmatter (description, mode, tools, model if specified) - Analyze body content to identify: - Task complexity (simple/moderate/complex/advanced) - Required reasoning depth (basic/intermediate/advanced/expert) - Code generation needs (minimal/moderate/extensive) - Multi-turn conversation requirements - Context window needs (small/medium/large) - Specialized capabilities (image analysis, long-context, real-time data) **Categorize Task Type**: Identify the primary task category based on content analysis: 1. **Simple Repetitive Tasks**: - Pattern: Formatting, simple refactoring, adding comments/docstrings, basic CRUD - Characteristics: Straightforward logic, minimal context, fast execution preferred - Keywords: format, comment, simple, basic, add docstring, rename, move 2. **Code Generation & Implementation**: - Pattern: Writing functions/classes, implementing features, API endpoints, tests - Characteristics: Moderate complexity, domain knowledge, idiomatic code - Keywords: implement, create, generate, write, build, scaffold 3. **Complex Refactoring & Architecture**: - Pattern: System design, architectural review, large-scale refactoring, performance optimization - Characteristics: Deep reasoning, multiple components, trade-off analysis - Keywords: architect, refactor, optimize, design, scale, review architecture 4. **Debugging & Problem-Solving**: - Pattern: Bug fixing, error analysis, systematic troubleshooting, root cause analysis - Characteristics: Step-by-step reasoning, debugging context, verification needs - Keywords: debug, fix, troubleshoot, diagnose, error, investigate 5. **Planning & Research**: - Pattern: Feature planning, research, documentation analysis, ADR creation - Characteristics: Read-only, context gathering, decision-making support - Keywords: plan, research, analyze, investigate, document, assess 6. **Code Review & Quality Analysis**: - Pattern: Security analysis, performance review, best practices validation, compliance checking - Characteristics: Critical thinking, pattern recognition, domain expertise - Keywords: review, analyze, security, performance, compliance, validate 7. **Specialized Domain Tasks**: -