arthur-onboard-eval-provider skillB
arthur-onboard-eval-provider is agent-read markdown (skill) from arthur-ai/arthur-engine: Arthur onboarding sub-skill — Step 8: Configure an LLM provider for continuous evals (OpenAI, Anthropic, Gemini, Bedrock, or Vertex AI). Reads/writes .arthur-engine.env..
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
# Arthur Onboard — Step 8: Configure Eval Model Provider
## Read State
```bash
cat .arthur-engine.env 2>/dev/null || echo "(no state file)"
```
Parse `ARTHUR_ENGINE_URL` and `ARTHUR_API_KEY`.
---
## Check Existing Providers
```bash
curl -s \
-H "Authorization: Bearer $ARTHUR_API_KEY" \
"$ARTHUR_ENGINE_URL/api/v1/model_providers" | \
python3 -c "
import sys, json
d = json.load(sys.stdin)
for p in d.get('providers', []):
print(f'{p[\"provider\"]}: enabled={p[\"enabled\"]}')
"
```
**If an enabled provider exists:** Use it (prefer OpenAI > Anthropic > Gemini > Bedrock > Vertex AI). Write `ARTHUR_EVAL_PROVIDER` and `ARTHUR_EVAL_MODEL` to the state file, then exit this skill.
---
## If No Provider Enabled
Ask user to choose:
- `openai` → model `gpt-4o`
- `anthropic` → model `claude-3-5-haiku-20241022`
- `gemini` → model `gemini-1.5-flash`
- `bedrock` → model `anthropic.claude-3-haiku-20240307-v1:0`
- `vertex_ai` → model `gemini-1.5-flash`
- Skip → configure in the Arthur Engine UI later (write `ARTHUR_EVAL_PROVIDER=none` to state, then exit)
…Read the whole file at its exact version.
How to install
mdr add arthur-ai/arthur-engine/arthur-onboard-eval-provider@v1.0.0mdr add arthur-ai/arthur-engine/arthur-onboard-eval-provider@sha256:682e47085db2da6bPin 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_og3wmcopdjobsdbf)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-06-08 | 8a00f36 | 2,621 B | B | view · diff |
| git:20260527.14c2ed0 | 2026-05-27 | 14c2ed0 | 2,606 B | B | view |
Audit of the latest version
- fail: No instruction to read or print local credentials (matched: cat .arthur-engine.env)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2621 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 base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
arthur-ai/arthur-engine · 90 stars · license MIT · pushed 2026-09-24 · branch dev
API
GET https://markdownregistry.com/api/v1/artifacts/art_og3wmcopdjobsdbf GET https://markdownregistry.com/api/v1/resolve?ref=arthur-ai/arthur-engine/arthur-onboard-eval-provider GET https://markdownregistry.com/api/v1/blob/682e47085db2da6bab4f4f15d8078c915a5a52b8d243dd6c4633b8f0b427f101
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.