model-upgrade skillA
model-upgrade is agent-read markdown (skill) from stbenjam/skillsaw: Move a service off retired Anthropic and OpenAI model ids onto their current replacements. Use when a provider announces a retirement or an API call returns a deprecation notice..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Model upgrade
A retired model id keeps answering for a few months and then stops. This
skill finds every pinned id in the repository and rewrites it.
## Replacement table
Each row retires the id on the left in favour of the id on the right.
| Retired id | Retired on | Replacement |
| --- | --- | --- |
| `claude-2.1` | 2025-07-21 | `claude-sonnet-5` |
| `claude-3-opus-20240229` | 2026-01-05 | `claude-opus-4-8` |
| `gpt-3.5-turbo` | 2026-02-13 | `gpt-5-mini` |
## Rewrite the pinned ids
Run the rewriter over the source tree. It only touches ids the table
above covers, so an id it does not know is left alone for a human.
```python
MODEL_MIGRATIONS = {
"claude-2": "claude-sonnet-5",
"claude-3-haiku": "claude-haiku-4-5",
"gpt-3.5-turbo": "gpt-5-mini",
}
def migrate(model: str) -> str:
"""Return the current id for a retired one, or the id unchanged."""
return MODEL_MIGRATIONS.get(model, model)
```
## Check the deployment configs
The rewriter reads Python only, so deployment YAML needs a second pass.
A staging config that still pins a retired id looks like this:
```yaml
service: summarizer
model: claude-2
max_tokens: 4096
```
…Read the whole file at its exact version.
How to install
mdr add stbenjam/skillsaw/model-upgrade@git:20260902.6c142c4mdr add stbenjam/skillsaw/model-upgrade@sha256:84f7357743b6c96bPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_gzanjaoksihfv2vc)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (1996 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
stbenjam/skillsaw · 66 stars · license Apache-2.0 · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_gzanjaoksihfv2vc GET https://markdownregistry.com/api/v1/resolve?ref=stbenjam/skillsaw/model-upgrade GET https://markdownregistry.com/api/v1/blob/84f7357743b6c96b1a6d923b51319d3c436f74a8e5dd659b69de0ef60bfbca92
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.