Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/intercom/claude-plugin-external/install-messengernpx skills add intercom/claude-plugin-external --skill install-messengergit clone --depth 1 https://github.com/intercom/claude-plugin-externalWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00104 | $0.02983 |
| Opus 5 | $0.00052 | $0.01491 |
| Sonnet 5 | $0.00021 | $0.00597 |
| Haiku 4.5 | $0.00010 | $0.00298 |
Grade A, and why
install-messenger scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install Intercom Messenger
Help the user install the Intercom Messenger on their website or application with JWT-based identity verification. This is the secure default — it prevents user impersonation by cryptographically signing user identity on the server.
Only use the insecure (non-JWT) installation if the user explicitly asks for an "insecure installation". Never default to it.
Requirements
Gather these from the user before proceeding:
-
Workspace ID (also called App ID) — A short alphanumeric string like
abc12345.- Found on the Intercom Messenger install page
- Or in the URL bar:
https://app.intercom.com/a/apps/<workspace_id>/...
-
Identity Verification Secret (also called Messenger API Secret) — Found on the Messenger Security page. This is the HMAC secret used to sign JWTs. It must never appear in frontend code.
Ask the user for both values. Do not proceed without the Workspace ID. If they don't have the Identity Verification Secret yet, direct them to the Messenger Security page to enable it.
In all generated code, replace YOUR_WORKSPACE_ID with the user's actual Workspace ID. Do not leave placeholders — substitute the real values they provided.
Installation Overview
The secure installation has two parts:
- Backend: Create an API endpoint that generates a signed JWT for the current authenticated user
- Frontend: Boot the Messenger with the JWT from the backend
Always implement both parts. The backend generates the JWT; the frontend passes it to the Messenger.
Step 1: Backend — JWT Generation Endpoint
Create a server-side endpoint that the frontend calls to get a signed JWT for the currently authenticated user. The JWT must be signed with HS256 using the Identity Verification Secret.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 235 lines · 104 tokens per session scan A 73f5dfb79789
install-messenger is a skill published in the GitHub repository intercom/claude-plugin-external (2 stars, last pushed 4mo ago), licensed MIT. It adds 104 tokens to every session and 2,983 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.