Workflow·Cloud & DevOps

Opus 4.5 Migration Guide

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5.

You say
Install this skill Read the source first Free Written by anthropics · unverified publisher
Context cost
3.1k tokensestimated from the bundle, loaded when it triggers
Bundle
3 files · 12.5 kBtext throughout, nothing executable
Licence
Source-availablefree to use
Last change
no release on file
Servers it uses
Noneruns standalone

What it does

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.

Installed, it changes the agent in these ways.

What this skill changes about the agent is not written down here yet. The listing was collected from its source, and the description is in its own SKILL.md.

Workflow

Runs a procedure end to end.

cloud
Filed under

Cloud & DevOps

The skill itself

This is the whole product. A skill is instructions the model reads, so there is nothing behind the listing you cannot see first — the front matter loads with every session, and the body below it loads when the skill triggers.

SKILL.md4.7 kB · 106 lines
--- name: claude-opus-4-5-migration 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. ---
6# Opus 4.5 Migration Guide
7
8One-shot migration from Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5.
9
10## Migration Workflow
11
121. Search codebase for model strings and API calls
132. Update model strings to Opus 4.5 (see platform-specific strings below)
143. Remove unsupported beta headers
154. Add effort parameter set to "high" (see references/effort.md)
165. Summarize all changes made
176. Tell the user: "If you encounter any issues with Opus 4.5, let me know and I can help adjust your prompts."
18
19## Model String Updates
20
21Identify which platform the codebase uses, then replace model strings accordingly.
22
23### Unsupported Beta Headers
24
25Remove the context-1m-2025-08-07 beta header if present—it is not yet supported with Opus 4.5. Leave a comment noting this:
26
27```python
28# Note: 1M context beta (context-1m-2025-08-07) not yet supported with Opus 4.5
29```
30
31### Target Model Strings (Opus 4.5)
32
33| Platform | Opus 4.5 Model String |
34|----------|----------------------|
35| Anthropic API (1P) | claude-opus-4-5-20251101 |
36| AWS Bedrock | anthropic.claude-opus-4-5-20251101-v1:0 |
37| Google Vertex AI | claude-opus-4-5@20251101 |
38| Azure AI Foundry | claude-opus-4-5-20251101 |
39
40### Source Model Strings to Replace
41
42| Source Model | Anthropic API (1P) | AWS Bedrock | Google Vertex AI |
43|--------------|-------------------|-------------|------------------|
44| Sonnet 4.0 | claude-sonnet-4-20250514 | anthropic.claude-sonnet-4-20250514-v1:0 | claude-sonnet-4@20250514 |
45| Sonnet 4.5 | claude-sonnet-4-5-20250929 | anthropic.claude-sonnet-4-5-20250929-v1:0 | claude-sonnet-4-5@20250929 |
46| Opus 4.1 | claude-opus-4-1-20250422 | anthropic.claude-opus-4-1-20250422-v1:0 | claude-opus-4-1@20250422 |
47
48**Do NOT migrate**: Any Haiku models (e.g., claude-haiku-4-5-20251001).
49
50## Prompt Adjustments
51
52Opus 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.
53
54**Integration guidelines**: When adding snippets, don't just append them to prompts. Integrate them thoughtfully:
55- Use XML tags (e.g., <code_guidelines>, <tool_usage>) to organize additions
56- Match the style and structure of the existing prompt
57- Place snippets in logical locations (e.g., coding guidelines near other coding instructions)
58- If the prompt already uses XML tags, add new content within appropriate existing tags or create consistent new ones
59
60### 1. Tool Overtriggering
61
62Opus 4.5 is more responsive to system prompts. Aggressive language that prevented undertriggering on previous models may now cause overtriggering.
63
64**Apply if**: User reports tools being called too frequently or unnecessarily.
65
66**Find and soften**:
67- CRITICAL: → remove or soften
68- You MUST...You should...
69- ALWAYS do XDo X
70- NEVER skip...Don't skip...
71- REQUIRED → remove or soften
72
73Only apply to tool-triggering instructions. Leave other uses of emphasis alone.
74
75### 2. Over-Engineering Prevention
76
77Opus 4.5 tends to create extra files, add unnecessary abstractions, or build unrequested flexibility.
78
79**Apply if**: User reports unwanted files, excessive abstraction, or unrequested features. Add the snippet from references/prompt-snippets.md.
80
81### 3. Code Exploration
82
83Opus 4.5 can be overly conservative about exploring code, proposing solutions without reading files.
84
85**Apply if**: User reports the model proposing fixes without inspecting relevant code. Add the snippet from references/prompt-snippets.md.
86
87### 4. Frontend Design
88
89**Apply if**: User requests improved frontend design quality or reports generic-looking outputs.
90
91Add the frontend aesthetics snippet from references/prompt-snippets.md.
92
93### 5. Thinking Sensitivity
94
95When 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.
96
97**Apply if**: User reports issues related to "thinking" while extended thinking is not enabled (no thinking parameter in request).
98
99Replace "think" with alternatives like "consider," "believe," or "evaluate."
100
101## Reference
102
103See references/prompt-snippets.md for the full text of each snippet to add.
104
105See references/effort.md for configuring the effort parameter (only if user requests it).
106
In the file
SKILL.md654 words
Files3
LicenceSource-available
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈90
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
3,035
on trigger
The instruction body and 2 supporting files, read only when the skill fires.
1.6%
of a 200k window
Ten skills this size would take about 16% of the window before you open a file.
050k100k150k200k context window

3.1k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Middling. Fine to keep on in a project where you use it weekly, worth unloading in one where you never do.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

Adoption
Installsnone yet
Ratingno reviews yet

The procedure it runs

The procedure has not been published here. It is in the skill’s own SKILL.md, which its author has not sent to the marketplace yet.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

It writes no files and reaches no network. All it changes is how the model reasons and writes.

What it asks for
Writes filesno
Network accessno

Read from the allowed-tools line of this skill’s own SKILL.md. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

3 files, 12.5 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • references/effort.md1.7 kB
  • references/prompt-snippets.md6.1 kB
  • SKILL.md4.7 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 3 files you can review in full before installing. The Source-available licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Opus 4.5 Migration Guide · 3.1k tokens when loaded npx mcprush@latest skill add anthropics/opus-4-5-migration-guide

Writes to .claude/skills/opus-4-5-migration-guide/ in the current project. Add --global to put it in your home directory instead, for every project.

Which clients pick it up on their own

A skill is a folder of text. A client with a skills folder reads it without being told; everywhere else the same text works, it is just handed to the model rather than found.

Claude Code.claude/skills/
Claude Desktop
ChatGPT
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok.grok/skills/
Zed.agents/skills/
Windsurf.windsurf/skills/
Agent SDK.claude/skills/
HTTP / API
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referenceanthropics/opus-4-5-migration-guide

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v
  • No earlier releases have been published to the marketplace.
Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

no reviews yet · no installs yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Who can post

Only accounts that have had the skill installed for fourteen days, so a review is written after living with it rather than after reading it. Publishers may reply once.

Publisher
Servers0
Claim this skill