THE MEDIA FOR AI THAT ACTUALLY HELPS.English edition · Understand & take action
OpenAI

Manage an API OpenAI key without ever exposing it to clear

openai-platform-api-key

In brief

As an input door for identifiers when building, executing, testing, debugging or configuring, in Codex, an application, interface, script, CLI, or generator that relies on OpenAI, or an AI tool whose provider is not specified, including a request formulated only as "using AI". It also covers the configuration of OPENAI API KEY or a sk-proj key. The SKILL.md specifies not to block a model or prompt migration that can progress through source modifications and offline validation. Otherwise, she inspects safely, asks if a key needs to be reused or created before any of the work done by the user, and never exposes the secret in plain language. It is reserved for local or application Codex sessions, via the secure connector of OpenAI platform.

What it does

  • Serves as an identifier check before a job
  • Never exposes the key in plain language and distinguishes reuse and creation

Who it is for, and an example

People who, in a local or applicative Codex session, have to place or check an OpenAI key before calling the API.

Example request: "Before calling the API, check if there is already an OPENAI API KEY or a sk-proj key, and never display it in plain language. »

It is reserved for local or applicative Codex sessions, as an identifier check for a work of the API, and not as application, documentation or interface skill; it must not block a model migration or quick offline. Example written by iadujour.fr from the SKILL.md, not tested.

Install

In Codex: codex plugin add openai-developers@openai-curated (Official Place of Deposit).

codex plugin add openai-developers@openai-curated

Works with

  • Codex

Source: README: Codex plugin collection; the deposit marketplace is called "Official Codex". Other officers are not appointed.

Level: Intermediate

Suppose a project already in place at the publisher and the tools described in SKILL.md.

Good to know

Official deposit OpenAI. These are examples of Codex plugins, often written by the plugin editor (Figma, Stripe, Canva, etc.) and hosted here. Skill plugin "openai-developers" in openai/plugins.

SKILL.md excerpt

The original description, which the agent reads to decide whether to load the skill (in English):

Use when Codex is asked to build, run, test, debug, or configure an OpenAI-backed or provider-unspecified AI app, UI, script, CLI, generator, or tool, especially requests phrased only as "using AI" or generators driven by forms/user input; also use for OPENAI_API_KEY or sk-proj setup. Do not gate model or prompt migrations that can proceed with source edits and offline validation. Otherwise treat […]

Quoted from SKILL.md at commit b767f8f . The folder also contains 2 extra files (agents/, references/).

The SKILL.md has 138 lines and 8 main sections:

  • When To Use
  • Coordination With Implementation Skills
  • Safety Rules
  • Mandatory First Step
  • Credential Decision Messages
  • Workflow
  • Helper
  • References

Licence: No licence found

Checked on 10 November 2026 : no licence file in the skill folder or at the repository root.

No licence found: short excerpt quoted only (quotation right). For the full text, see the source.

Source. Card written by iadujour.fr from: Frontmatter, sections and body of the deposit. Checked on 10 November 2026. openai/plugins .
SAME PUBLISHER

Other OpenAI skills: Security and identity

Whole category
OpenAISecurity and identity

Create or update a repository threat template

threat-model

Used when Codex is already in the threat modelling phase of a scan, when the person explicitly invokes $threat-model, or when explicitly requests to create, update, or record a repository threat template.

Tools: CodexLevel: Intermediateupdated 08/10/2026
OpenAISecurity and identity

Discovering candidate safety findings in a scan phase

finding-discovery

Used when Codex is already in the discovery phase of a security scan, or when the person explicitly requests to discover candidate security findings in a repository or code change.

Tools: CodexLevel: Intermediateupdated 08/10/2026
DISCUSSION

Comments.

A field note, a question, a precision on this skill? Comments are reviewed before publication.

Published comments

Loading comments…

    Leave a comment

    Moderation charter. Every comment is reviewed before publication. We refuse hate speech, insulting or discriminatory language, advertising, spam and promotional links, off-topic posts and other people’s personal data.