Replace retired Claude model ids in commands, skills and converter docs
User description
Four Claude model ids in this repo passed their retirement dates. claude-3-5-haiku-20241022 and claude-3-5-sonnet-20241022 went out on 28 October 2025, claude-sonnet-4-20250514 and claude-opus-4-20250514 later. All four are on the model deprecations page. The one that actually runs is .claude/commands/karen/quick-score.md, where the frontmatter names a model the API no longer serves. The rest are examples people copy.
I replaced each id with the current model in the same tier, so a command written for Haiku still gets Haiku.
| File | Lines | Was | Now |
|---|---|---|---|
.claude/commands/karen/quick-score.md | 4 | claude-3-5-haiku-20241022 | claude-haiku-4-5-20251001 |
.claude/skills/slash-command-builder/SKILL.md | 29, 148, 232 | 3.5 Sonnet, 3.5 Haiku | claude-sonnet-4-6, claude-haiku-4-5-20251001 |
.claude/skills/slash-command-builder/FRONTMATTER.md | 174, 177, 180, 274, 302 | 3.5 Haiku, 3.5 Sonnet, Opus 4 | claude-haiku-4-5-20251001, claude-sonnet-4-6, claude-opus-4-8 |
.claude/skills/slash-command-builder/EXAMPLES.md | 68, 688 | claude-3-5-haiku-20241022 | claude-haiku-4-5-20251001 |
.claude/skills/creating-opencode-agents/SKILL.md | 66 | anthropic/claude-sonnet-4-20250514 | anthropic/claude-sonnet-4-6 |
.cursor/rules/creating-claude-commands.md | 281 | claude-3-5-sonnet-20241022 | claude-sonnet-4-6 |
packages/converters/docs/kiro-agents.md | 138 | claude-3-5-sonnet-20241022 | claude-sonnet-4-6 |
packages/converters/docs/opencode.md | 66 | anthropic/claude-sonnet-4-20250514 | anthropic/claude-sonnet-4-6 |
packages/converters/schemas/opencode.schema.json | 101 | anthropic/claude-sonnet-4-20250514 | anthropic/claude-sonnet-4-6 |
packages/converters/schemas/opencode-slash-command.schema.json | 55 | anthropic/claude-sonnet-4-20250514 | anthropic/claude-sonnet-4-6 |
Both schema edits sit in the examples array, so validation behaviour is unchanged. I reparsed both files as JSON afterwards. The temperature values next to these ids still work on the replacement models and are untouched.
Three files carry retired ids that I deliberately left alone.
docs/blog/slash-commands-compared.md and packages/webapp/public/blog/extensibility-landscape.md are published posts. They describe what the ecosystem looked like when you wrote them, and quietly editing that record is your call rather than mine.
docs/PLAYGROUND_IMPLEMENTATION_LOG.md has one inside a sample API response at line 291. It reads as a record of a response you got, not as guidance, so I left it.
I read this diff line by line before opening it, and I am happy to adjust or drop any part of it. What brought me here was a checker I maintain that flags retired Claude model IDs, so I am mentioning that up front rather than leaving you to wonder. I have not run the karen command against the API to reproduce a failure, the claim rests on the published retirement dates. If you would rather handle this your own way, or would rather not get this kind of contribution at all, tell me and I will not send another.
CodeAnt-AI Description
Replace retired Claude model references with current supported models
What Changed
- Commands and agent examples now use supported Claude Haiku, Sonnet, and Opus model identifiers
- Converter documentation and schema examples now generate configurations with current model identifiers
- Existing model tiers remain aligned, so fast, default, and complex-analysis examples keep their intended roles
Impact
✅ Fewer command failures from retired model IDs
✅ Working copy-and-paste examples
✅ Current generated agent configurations
💡 Usage Guide
Checking Your Pull Request
Every time you make a pull request, our system automatically looks through it. We check for security issues, mistakes in how you're setting up your infrastructure, and common code problems. We do this to make sure your changes are solid and won't cause any trouble later.
Talking to CodeAnt AI
Got a question or need a hand with something in your pull request? You can easily get in touch with CodeAnt AI right here. Just type the following in a comment on your pull request, and replace "Your question here" with whatever you want to ask:
@codeant-ai ask: Your question here
This lets you have a chat with CodeAnt AI about your pull request, making it easier to understand and improve your code.
Example
@codeant-ai ask: Can you suggest a safer alternative to storing this secret?
Preserve Org Learnings with CodeAnt
You can record team preferences so CodeAnt AI applies them in future reviews. Reply directly to the specific CodeAnt AI suggestion (in the same thread) and replace "Your feedback here" with your input:
@codeant-ai: Your feedback here
This helps CodeAnt AI learn and adapt to your team's coding style and standards.
Example
@codeant-ai: Do not flag unused imports.
Retrigger review
Ask CodeAnt AI to review the PR again, by typing:
@codeant-ai: review
Check Your Repository Health
To analyze the health of your code repository, visit our dashboard at https://app.codeant.ai. This tool helps you identify potential issues and areas for improvement in your codebase, ensuring your repository maintains high standards of code health.