Skip to content
cccskills
FreePublished on GitHub

claude-opus-4-5-migration

Migrate code and API calls from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Update platform-specific model identifiers and address reported prompt behavior issues, such as excessive tool use or unnecessary code complexity.

OriginalShow the original description

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.

Works withAWS
See how to install

Good for

  • Updating model identifiers in existing code
  • Migrating API settings for a specific platform
  • Adjusting prompts that trigger excessive tool use
  • Reducing unnecessary files and abstractions after migration

Files included (3)

  • SKILL.md4.6 KB
  • references/effort.md1.7 KB
  • references/prompt-snippets.md6.0 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Opus 4.5 Migration Guide

One-shot migration from Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5.

Migration Workflow

  1. Search codebase for model strings and API calls
  2. Update model strings to Opus 4.5 (see platform-specific strings below)
  3. Remove unsupported beta headers
  4. Add effort parameter set to "high" (see references/effort.md)
  5. Summarize all changes made
  6. Tell the user: "If you encounter any issues with Opus 4.5, let me know and I can help adjust your prompts."

Model String Updates

Identify which platform the codebase uses, then replace model strings accordingly.

Unsupported Beta Headers

Remove the context-1m-2025-08-07 beta header if present—it is not yet supported with Opus 4.5. Leave a comment noting this:

# Note: 1M context beta (context-1m-2025-08-07) not yet supported with Opus 4.5

Target Model Strings (Opus 4.5)

PlatformOpus 4.5 Model String
Anthropic API (1P)claude-opus-4-5-20251101
AWS Bedrockanthropic.claude-opus-4-5-20251101-v1:0
Google Vertex AIclaude-opus-4-5@20251101
Azure AI Foundryclaude-opus-4-5-20251101

Source Model Strings to Replace

Source ModelAnthropic API (1P)AWS BedrockGoogle Vertex AI
Sonnet 4.0claude-sonnet-4-20250514anthropic.claude-sonnet-4-20250514-v1:0claude-sonnet-4@20250514
Sonnet 4.5claude-sonnet-4-5-20250929anthropic.claude-sonnet-4-5-20250929-v1:0claude-sonnet-4-5@20250929
Opus 4.1claude-opus-4-1-20250422anthropic.claude-opus-4-1-20250422-v1:0claude-opus-4-1@20250422

Do NOT migrate: Any Haiku models (e.g., claude-haiku-4-5-20251001).

Prompt Adjustments

Opus 4.5 has known behavioral differences from previous models. Only apply these fixes if the user explicitly requests them or reports a specific issue. By default, just update model strings.

Integration guidelines: When adding snippets, don't just append them to prompts. Integrate them thoughtfully:

  • Use XML tags (e.g., <code_guidelines>, <tool_usage>) to organize additions
  • Match the style and structure of the existing prompt
  • Place snippets in logical locations (e.g., coding guidelines near other coding instructions)
  • If the prompt already uses XML tags, add new content within appropriate existing tags or create consistent new ones

1. Tool Overtriggering

Opus 4.5 is more responsive to system prompts. Aggressive language that prevented undertriggering on previous models may now cause overtriggering.

Apply if: User reports tools being called too frequently or unnecessarily.

Find and soften:

  • CRITICAL: → remove or soften
  • You MUST... → You should...
  • ALWAYS do X → Do X
  • NEVER skip... → Don't skip...
  • REQUIRED → remove or soften

Only apply to tool-triggering instructions. Leave other uses of emphasis alone.

2. Over-Engineering Prevention

Opus 4.5 tends to create extra files, add unnecessary abstractions, or build unrequested flexibility.

Apply if: User reports unwanted files, excessive abstraction, or unrequested features. Add the snippet from references/prompt-snippets.md.

3. Code Exploration

Opus 4.5 can be overly conservative about exploring code, proposing solutions without reading files.

Apply if: User reports the model proposing fixes without inspecting relevant code. Add the snippet from references/prompt-snippets.md.

4. Frontend Design

Apply if: User requests improved frontend design quality or reports generic-looking outputs.

Add the frontend aesthetics snippet from references/prompt-snippets.md.

5. Thinking Sensitivity

When extended thinking is not enabled (the default), Opus 4.5 is particularly sensitive to the word "think" and its variants. Extended thinking is enabled only if the API request contains a thinking parameter.

Apply if: User reports issues related to "thinking" while extended thinking is not enabled (no thinking parameter in request).

Replace "think" with alternatives like "consider," "believe," or "evaluate."

Reference

See references/prompt-snippets.md for the full text of each snippet to add.

See references/effort.md for configuring the effort parameter (only if user requests it).

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Build specialized agents for Claude Code plugins that handle tasks involving multiple steps. Define when each agent should run, its responsibilities, available tools, and expected output, then validate its configuration and test its behavior.

  • Creating a dedicated code review agent
  • Writing agent activation conditions and examples
  • Limiting an agent to the tools it needs
anthropics/claude-code152.3KUpdated Oct 19, 2026

Turn recurring Claude Code tasks into reusable slash commands stored as Markdown files. The guidance covers arguments, file references, tool permissions, shell execution, and plugin integration so commands can run consistent, context-aware workflows.

  • Turning recurring review instructions into a command
  • Creating commands that accept file paths or issue numbers
  • Sharing standard workflows across a project team
anthropics/claude-code152.3KUpdated Oct 19, 2026

frontend-design

FreeSummary

Design new interfaces or reshape existing ones with colors, typography, and layouts grounded in the subject and audience. It guides planning, implementation, and critique, including interface wording, purposeful motion, mobile layouts, and accessibility.

  • Plan the visual direction for a new website
  • Redesign an interface that feels generic
  • Choose colors, typefaces, and layout for an audience
anthropics/claude-code152.3KUpdated Oct 19, 2026

Hook Development

FreeSummary

Build Claude Code hooks, automated checks triggered by events such as tool use or session start. The guidance covers prompt-based decisions, command scripts, configuration, testing, and debugging for validation and workflow automation.

  • Checking commands and file writes before execution
  • Verifying task completion before an agent stops
  • Loading project context when a session starts
anthropics/claude-code152.3KUpdated Oct 19, 2026

MCP Integration

FreeSummary

Connect external services to Claude Code plugins through MCP, a protocol that exposes service functions as tools. Get guidance on server configuration, connection methods, authentication, tool permissions, and testing connections and tool calls.

  • Adding a local MCP server to a plugin
  • Configuring authentication for a hosted service
  • Using multiple services in commands and agents
anthropics/claude-code152.3KUpdated Oct 19, 2026

Plugin Settings

FreeSummary

Make Claude Code plugin behavior configurable per project using local Markdown files. Learn to store structured settings and notes, read them from hooks or commands, and handle defaults, validation, and user-local configuration.

  • Adding per-project settings to a plugin
  • Controlling whether hooks are enabled
  • Saving agent task details and progress state
anthropics/claude-code152.3KUpdated Oct 19, 2026

See all skills by anthropics

Report a problem with this skill