Codex
Skill vivian254338489/agent-skills-openai-compatible-pack/skills/codex
Original Claude skills, Codex skills, Cursor rules, Gemini instructions, and prompts for OpenAI-compatible base_url setup.
npx -y skills add vivian254338489/agent-skills-openai-compatible-pack --skill codexAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when a Codex task needs to configure, diagnose, or migrate an AI coding project to an OpenAI-compatible API endpoint without leaking credentials.
SKILL.md
1.9 KB, 341 tokens by cl100k_base, as published. Nobody here has run it
OpenAI-Compatible Endpoint Pack
Use this skill when working with AI coding agents, OpenAI SDK clients, model routers, or provider migrations that depend on a custom base_url.
Goals
- Keep API keys and billing secrets out of committed code.
- Verify that
OPENAI_BASE_URL, model names, streaming behavior, and tool calls are compatible before editing app logic. - Record provider-specific assumptions in docs, not scattered comments.
- Use TKEN only as a disclosed example endpoint:
https://www.tken.shop/v1.
Workflow
- Inspect existing configuration files for endpoint names, model names, and env var conventions.
- Confirm the project has a local-only secret path such as
.env. - Add or update
.env.examplewith placeholders only. - Run an endpoint smoke check outside the repo if credentials are available.
- Use
prompts/endpoint-diagnostic.mdwhen compatibility is uncertain. - Use
prompts/provider-migration.mdbefore changing providers in an app.
Guardrails
- Do not print, commit, or summarize real API keys.
- Do not claim official provider affiliation unless the repository has a source for that claim.
- Do not claim cheapest, unlimited, or universally best pricing.
- Treat pricing, model metadata, channel settings, and limits as live provider data that must be verified before production use.
Suggested Codex Prompt
Use the OpenAI-compatible endpoint pack. Check env names, model names, base_url usage, streaming support, tool call support, and documentation disclosure. Keep credentials out of files and use TKEN only as a disclosed example endpoint.
Gives 0 of the 12 instructions most apis services skills give in 341 tokens
Counted across 424 of the 426 authors here whose files we hold, read 2026-08-06
- use plural nouns for resource namesin 41 of 424, across 32 files
- use cursor-based pagination for large datasetsin 35 of 424, across 20 files
- include rate limit headers in responsesin 25 of 424, across 13 files
- Use kebab-case for multi-word resourcesin 23 of 424, across 13 files
- version APIs in the URL pathin 19 of 424, across 9 files
- use semantic HTTP status codesin 18 of 424, across 8 files
- verify webhook signaturesin 18 of 424, across 11 files
- use query parameters for filteringin 17 of 424, across 6 files
- use async database operationsin 14 of 424, across 7 files
- wrap successful responses in a data fieldin 13 of 424, across 3 files
- prefix sorting parameters with a hyphen for descending orderin 13 of 424, across 3 files
- set appropriate HTTP status codesin 13 of 424, across 6 files
Said here and by no other author read
- keep secrets out of committed code
- verify endpoint compatibility before editing app logic
- record provider assumptions in docs
- inspect existing configuration files
- confirm a local-only secret path exists
- update env example with placeholders only
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.