Intercom Performance Tuning

What it does

When your agent uses it

• Experiencing slow API responses
• Implementing caching strategies
• Optimizing request throughput for Intercom integrations
• With phrases like intercom performance

Example prompts

• “intercom performance”
• “optimize intercom”
• “intercom latency”
• “/intercom-performance-tuning”

Requirements

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

Workflow steps

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

1. 1Response caching — wrap contact/conversation reads in an LRUCache (read-through), and invalidate on update or via webhook so cached data…
2. 2Efficient search queries — push predicates into the AND-combined query and request only the per_page you need (max 150), rather than…
3. 3Optimized pagination — stream large result sets with an async generator over cursor pagination (startingAfter) to keep memory flat, and…
4. 4Connection pooling — reuse TCP connections with an https.Agent (keepAlive: true) so you pay the TLS handshake cost once, not per request.
5. 5Parallel requests with rate awareness — fan out concurrent lookups through a p-queue bounded by concurrency + intervalCap so batches stay…
6. 6Performance monitoring — wrap every call in a measuredCall helper that emits a structured latency metric, so you can chart real P50/P95…

What it can do on your machine

Read from SKILL.md and the folder at commit 80f86df. 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

  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

  Links to these hosts (documentation or services it may open):

  • developers.intercom.com
  • github.com

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

• Credentials

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

  • INTERCOM_ACCESS_TOKEN

  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 Performance Tuning loads about 1.8k tokens when it runs, and up to ~3.9k if it reads all its reference files. Until then it costs about 100 tokens; SKILL.md has 630 words of instructions outside code blocks.

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

~100

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

~1.8k

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

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 80f86df, republished under its MIT licence (© jeremylongshore). 630 words, ~1,754 tokens.

name

intercom-performance-tuning

description

Optimize Intercom API performance with caching, search optimization, and pagination. Use when experiencing slow API responses, implementing caching strategies, or optimizing request throughput for Intercom integrations. Trigger with phrases like "intercom performance", "optimize intercom", "intercom latency", "intercom caching", "intercom slow", "intercom pagination".

allowed-tools

Read, Write, Edit

compatibility

Designed for Claude Code

version

1.6.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, support, messaging, intercom

const client = new IntercomClient({ token: process.env.INTERCOM_ACCESS_TOKEN! });

import { LRUCache } from "lru-cache";
import { IntercomClient } from "intercom-client";
import { Intercom } from "intercom-client";

const contactCache = new LRUCache<string, Intercom.Contact>({
  max: 5000,
  ttl: 5 * 60 * 1000,  // 5 minutes
});

const client = new IntercomClient({ token: process.env.INTERCOM_ACCESS_TOKEN! });

async function getContact(contactId: string): Promise<Intercom.Contact> {
  const cached = contactCache.get(contactId);
  if (cached) return cached;
  const contact = await client.contacts.find({ contactId });
  contactCache.set(contactId, contact);
  return contact;
}

const contact = await measuredCall("contacts.find", () =>
  client.contacts.find({ contactId: "abc123" })
);
// → {"metric":"intercom.api.call","operation":"contacts.find","duration_ms":84,"status":"success"}

© 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-performance-tuning of jeremylongshore/tons-of-skills-marketplace.

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

Open the folder on GitHubat commit 80f86df