Intercom Multi Env Setup

What it does

When your agent uses it

• Setting up multi-environment deployments
• Configuring per-environment access tokens
• Implementing workspace isolation
• With phrases like intercom environments

Example prompts

• “intercom environments”
• “intercom staging”
• “intercom dev prod”
• “/intercom-multi-env-setup”

Requirements

• A credential in INTERCOM_ACCESS_TOKEN
• A credential in INTERCOM_WEBHOOK_SECRET
• Compatibility (from SKILL.md): Designed for Claude Code
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash(aws:*), Bash(gcloud:*), Bash(vault:*)

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Environment Configuration — a single loadConfig() reads NODE_ENV and merges shared secrets with per-environment defaults (debug, cache…
2. 2Environment-Aware Client Factory — a lazily-initialised getClient() that throws a clear, environment-named error when the token is missing.
3. 3Secret Management by Platform — store tokens in git-ignored .env. files locally and in GitHub Actions, AWS Secrets Manager, GCP Secret…
4. 4Production Safety Guards — an EnvironmentGuard with requireProduction() / preventProduction() so destructive jobs can never fire in the…
5. 5Webhook URL per Environment — map NODE_ENV to the correct public webhook URL so no code changes between deploys.
6. 6Environment Validation on Startup — probe the workspace on boot; fail fast in production, warn (but continue) elsewhere.

What it can do on your machine

Read from SKILL.md and the folder at commit 23ea8d4. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Bash(aws:*)
  • Bash(gcloud:*)
  • Bash(vault:*)

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript).

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

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • api.intercom.io

  Also links to:

  • developers.intercom.com
  • 12factor.net

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

• Credentials

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

  • INTERCOM_DEV_TOKEN
  • INTERCOM_STAGING_TOKEN
  • INTERCOM_PROD_TOKEN
  • INTERCOM_ACCESS_TOKEN
  • INTERCOM_WEBHOOK_SECRET

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

• Compatibility

  Designed for Claude Code

  From compatibility in the SKILL.md frontmatter.

Context cost

Intercom Multi Env Setup loads about 1.7k tokens when it runs, and up to ~3.9k if it reads all its reference files. Until then it costs about 96 tokens; SKILL.md has 561 words of instructions outside code blocks.

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

~96

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

~1.7k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3.9k

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:53

  latform** — store tokens in git-ignored `.env.<environment>` files locally and in GitHub Actions, AWS Secrets Manager, G

• NoteMentions a .env fileSKILL.md:88

  er-environment secret sets: git-ignored `.env.<environment>` files locally plus tokens in your CI/prod secret store (`IN

• NoteMentions a .env fileSKILL.md:99

  ssing env file | Copy `.env.example` to `.env.<environment>` |

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 jeremylongshore/tons-of-skills-marketplace at commit 23ea8d4, republished under its MIT licence (© jeremylongshore). 561 words, ~1,693 tokens.

name

intercom-multi-env-setup

description

Configure Intercom across development, staging, and production workspaces. Use when setting up multi-environment deployments, configuring per-environment access tokens, or implementing workspace isolation. Trigger with phrases like "intercom environments", "intercom staging", "intercom dev prod", "intercom environment setup", "intercom workspace isolation".

allowed-tools

Read, Write, Edit, Bash(aws:*), Bash(gcloud:*), Bash(vault:*)

compatibility

Designed for Claude Code

version

1.6.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, support, messaging, intercom

// src/config/intercom.ts
function loadConfig(): IntercomEnvironmentConfig {
  const env = (process.env.NODE_ENV || "development") as IntercomEnvironmentConfig["environment"];
  const shared = {
    accessToken: process.env.INTERCOM_ACCESS_TOKEN!,
    webhookSecret: process.env.INTERCOM_WEBHOOK_SECRET!,
    environment: env,
    baseUrl: "https://api.intercom.io",
  };
  const envDefaults = {
    development: { debug: true, cache: { enabled: false, ttlSeconds: 0 }, rateLimit: { maxConcurrency: 2 } },
    staging: { debug: false, cache: { enabled: true, ttlSeconds: 60 }, rateLimit: { maxConcurrency: 5 } },
    production: { debug: false, cache: { enabled: true, ttlSeconds: 300 }, rateLimit: { maxConcurrency: 10 } },
  };
  return { ...shared, ...envDefaults[env] } as IntercomEnvironmentConfig;
}
export const intercomConfig = loadConfig();

const guard = new EnvironmentGuard(intercomConfig.environment);

async function nightlyCleanup() {
  guard.preventProduction("nightlyCleanup"); // throws if NODE_ENV=production
  await deleteAllTestContacts();
}

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

Files

SKILL.md and 2 other files (references) in skills/.curated/intercom-multi-env-setup of jeremylongshore/tons-of-skills-marketplace.

• SKILL.md
• references/examples.md
• references/implementation.md

Open the folder on GitHubat commit 23ea8d4