Config

What it does

When your agent uses it

• Adding a new environment variable
• A new config property
• A new environment file
• A new utility-service URL

Example prompts

• “/config”

Requirements

• Node.js
• A credential in ACCESS_TOKEN

Workflow steps

5 steps, taken from the step headings in SKILL.md.

1. 1Understand how env files are loaded
2. 2Decide where the new value belongs
3. 3Add the env var to env/.env.example
4. 4Add the config property (only if warranted) with JSDoc
5. 5Consume the value from tests, fixtures, and helpers

What it can do on your machine

Read from SKILL.md and the folder at commit f6cbf35. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • npx
  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use npx and git, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • ACCESS_TOKEN
  • APP_PASSWORD

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Config loads about 2.8k tokens when it runs. Until then it costs about 180 tokens; SKILL.md has 1,097 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~180

When it runs · the whole SKILL.md, loaded when a task matches

~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:3

  aywright scaffold — env file layout (env/.env.*), dotenv loading via playwright.config.ts and the ENVIRONMENT variable,

• NoteMentions a .env fileSKILL.md:11

  alues is `process.env.*`, backed by `env/.env.${environment}`.

• NoteMentions a .env fileSKILL.md:16

  - **NEVER** commit `env/.env.dev`, `env/.env.staging`, or any other real env file containing credentials. Only `env/.env

• NoteMentions a .env fileSKILL.md:25

  | Env (active)   | `env/.env.${ENVIRONMENT}` | Real values, selected at runtime (`.env.dev` etc.) — untracked |

• NoteMentions a .env fileSKILL.md:35

  const environmentPath = `./env/.env.${environment}`;

• NoteMentions a .env fileSKILL.md:41

  Default environment is `dev` (file `env/.env.dev`).

• NoteMentions a .env fileSKILL.md:44

  hell** level; it is not declared in any `.env` file.

• NoteMentions a .env fileSKILL.md:80

  real value to your active env file (`env/.env.dev` or similar) — this file is untracked.

• NoteMentions a .env fileSKILL.md:151

  2. Create `env/.env.staging` **locally** (untracked) with the real staging URLs/credentials, using the same keys as `env

• NoteMentions a .env fileSKILL.md:153

  haven't changed) and **do not** commit `.env.staging`.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from idavidov13/agentic-playwright at commit f6cbf35, republished under its MIT licence (© idavidov13). 1,097 words, ~2,827 tokens.

name

config

description

Configuration and environment variable conventions for the Playwright scaffold — env file layout (env/.env.*), dotenv loading via playwright.config.ts and the ENVIRONMENT variable, config objects in config/app.ts and config/util/util.ts, and the rules for adding new env-driven values. Use when adding a new environment variable, a new config property, a new environment file, a new utility-service URL, or when a test/fixture needs to consume APP_URL / API_URL / APP_EMAIL / APP_PASSWORD / UTILITY_URL. This skill owns URLs, credentials, and env-driven settings — for endpoint paths and route constants use the enums skill, and for process.env.* typing (non-null assertion vs fallback) use the type-safety skill.

author

Ivan Davidov

const environment = process.env.ENVIRONMENT ?? 'dev';
const environmentPath = `./env/.env.${environment}`;
dotenv.config({ path: environmentPath });

APP_URL=https://your-app-url.com
API_URL=https://your-api-url.com
APP_EMAIL=your-email@example.com
APP_PASSWORD=your-secure-password
UTILITY_URL=https://your-utility-service.com

/**
 * Application configuration object.
 * Contains URL configuration for the main application.
 *
 * For route paths and API endpoints, use enums from `enums/app/app.ts`.
 */
export const appConfig = {
    /** Frontend application URL loaded from APP_URL env variable */
    appUrl: process.env.APP_URL,
    /** Backend API URL loaded from API_URL env variable */
    apiUrl: process.env.API_URL,
};

/**
 * Utility service configuration object.
 * Contains URL configuration for utility/helper services.
 *
 * For API endpoints, use enums from `enums/` folder.
 */
export const utilityConfig = {
    /** Utility service base URL */
    baseUrl: process.env.UTILITY_URL,
};

© idavidov13, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/config of idavidov13/agentic-playwright.

Open the folder on GitHubat commit f6cbf35