fetcher-openai-client SKILL.md skillA
fetcher-openai-client from ahoo-wang/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ahoo-wang/skills/fetcher-openai-client@git:20261004.2702e5dPins git:20261004.2702e5d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ahoo-wang/skills
- Path
plugins/ahoo-fetcher-skills/skills/fetcher-openai-client/SKILL.md- Versions recorded
- 6
- Latest version
- git:20261004.2702e5d, committed Oct 4, 2026
- First version recorded
- May 27, 2026
- Size
- 4,353 bytes
- Repository stars
- 2
- License
- Apache-2.0
Call OpenAI-compatible chat completions with `@ahoo-wang/fetcher-openai`: `OpenAI`, `ChatClient`, `chat.completions` streaming and non-streaming, `DoneDetector`, gateway base URLs, headers and interceptors, HTTP and mid-stream errors. Use whenever a Fetcher app requests or streams a chat completion from GPT or any OpenAI-compatible `/chat/completions` endpoint. For other SSE or LLM streams use fetcher-llm-streaming.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# fetcher-openai-client
## Decisions
- **Entry point**: `new OpenAI({ baseURL, apiKey, ...fetcherOptions })` builds its own `Fetcher`. `baseURL` and `apiKey` are required and have no defaults; requests go to `${baseURL}/chat/completions`, so the base URL must include `/v1`. Every other `FetcherOptions` field (`headers`, `timeout`, `fetch`, `validateStatus`, `interceptors`) configures that Fetcher; `apiKey` becomes `Authorization: Bearer <apiKey>` and wins over an `Authorization` in `headers`.
- **Static vs per-request headers**: a fixed header goes in `headers`; a value computed per request (trace id, signed timestamp) goes in a request interceptor on `openai.fetcher.interceptors.request`.
- **Existing Fetcher**: `new ChatClient({ fetcher })` takes a `Fetcher` instance or registered name (you set the `Authorization` header yourself).
- **Streaming is chosen by the request**: `chat.completions(req, signal?)` resolves to a `JsonServerSentEventStream<ChatResponse>` (ended by `DoneDetector` at `data: [DONE]`) when `stream: true`, otherwise a `ChatResponse`. A `stream` typed as plain `boolean` yields the union.
…Read the whole file at its exact version.
How to install
mdr add ahoo-wang/skills/fetcher-openai-client@sha256:bcc54aea18446f27The line at the top of this page pins the label git:20261004.2702e5d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_b4rwrxc7ojszo7ih)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between May 27, 2026 and Oct 4, 2026, about one every 26 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261004.2702e5d latest | 2026-10-04 | 2702e5d | 4,353 B | A | view · diff |
| git:20260925.dadfae9 | 2026-09-25 | dadfae9 | 3,089 B | A | view · diff |
| git:20260924.b36c6c8 | 2026-09-24 | b36c6c8 | 3,015 B | A | view · diff |
| git:20260818.2ff7b22 | 2026-08-18 | 2ff7b22 | 1,674 B | A | view · diff |
| git:20260804.1ce42d6 | 2026-08-04 | 1ce42d6 | 2,030 B | A | view · diff |
| git:20260527.808710c | 2026-05-27 | 808710c | 2,080 B | A | view |
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 (4353 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
ahoo-wang/skills · 2 stars · license Apache-2.0 · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_b4rwrxc7ojszo7ih GET https://markdownregistry.com/api/v1/resolve?ref=ahoo-wang/skills/fetcher-openai-client GET https://markdownregistry.com/api/v1/blob/bcc54aea18446f27a9979aad10815d29775a249cfbb90f38c82b3980d60b1fd3
Your AI assistant 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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from ahoo-wang/skills
Every file in ahoo-wang/skills