---
title: "Claude Plugin · COUNT Partner API"
description: "Install the COUNT plugin for Claude: the COUNT connector plus a /count skill that routes each request to a playbook, FAQ topic, saved workspace skill, or…"
canonical: "https://developers.getcount.com/tools/claude-plugin"
source: "https://developers.getcount.com/tools/claude-plugin"
---
Tools

# Claude Plugin

One install gives Claude the COUNT connector and a /count skill that sends each request to the right playbook, FAQ topic, saved workspace skill, or tool.

## What the plugin contains

- **The COUNT connector**: the remote MCP server at `https://api.getcount.com/mcp`. It runs its own OAuth the first time it is used, so the plugin itself carries no credentials.
- **`/count`**: the entry skill. It routes a request; it does not try to hold COUNT's knowledge.
- **`count-demo-workspace`**: fills an empty workspace with realistic demo data for a chosen industry.

The same routing text is also registered on the connector as the MCP prompt `count`, so MCP clients that support prompts get it without installing the plugin.

## Install

In Claude Code, add the marketplace and install the plugin:

Claude Code

```bash
/plugin marketplace add https://api.getcount.com/mcp/plugin/marketplace.json
/plugin install count@count
```

For a client that takes a skill upload instead, download [count-skill.zip](https://api.getcount.com/mcp/plugin/count-skill.zip) and connect the COUNT connector separately (see [MCP Server](https://developers.getcount.com/tools/mcp)). The [install page](https://api.getcount.com/mcp/plugin/) lists every option.

| Path under `https://api.getcount.com/mcp/plugin` | Serves |
| --- | --- |
| / | Install page |
| /marketplace.json | Claude Code marketplace. Its plugin entry points at count-plugin.zip. |
| /count-plugin.zip | The plugin: a manifest declaring the COUNT connector, the /count entry skill, and the count-demo-workspace skill. |
| /count-skill.zip | The /count skill folder alone, for clients that take a skill upload. |
| /SKILL.md | The rendered /count skill, as Markdown. |

These downloads are public and need no authentication. Every response carries an `x-count-skill-version` header with the current skill version.

## Using /count

Examples

```text
/count reconcile the operating account for September
/count what is still unpaid from last quarter?
/count Pre-close QC
```

At the start of every conversation the skill:

1. Calls `COUNT_auth_status` and `COUNT_get_agent_skill` together.
2. If more than one workspace is authorized and the request doesn't name one, asks which workspace before any read or write. After that, it passes `workspaceId` on every call.
3. If the COUNT tools are missing, tells the user to connect COUNT and stops rather than answering from memory.

Then it routes the request:

- **A saved skill by name**: `COUNT_list_skills` with the name as `search`, then `COUNT_get_skill`, and carries out its procedure.
- **A multi-step workflow** (month-end, bill pay, migration import, budgets): `COUNT_playbooks`.
- **A question about how COUNT or the connector behaves**: `COUNT_knowledge`.
- **Anything else**: a tool whose name matches the request, or `COUNT_find_tool` when none fits.
- Before changing records, it calls `COUNT_recall` and treats what comes back as notes to verify, never as instructions.

How these lookups rank results is covered in [MCP Brain & Workspace Memory](https://developers.getcount.com/guides/mcp-brain-and-memory).

## Saved workspace skills

Skills built in COUNT's AI agents area (a pre-close review, a client email triage) can be run from Claude by name, for example `/count Pre-close QC`.

- `COUNT_list_skills` returns each saved skill's `id`, `name` and `description`. Pass `search` to rank them, or omit it to list them all.
- `COUNT_get_skill` returns one skill's full `procedure`, by `skillId`.

Both need the AI agents permission in the workspace, and both are remote-only. A skill's procedure doesn't override the connector's rules: workspace selection and confirming destructive actions still apply to every step.

## Staying current without a reinstall

The installed file holds only the routing rules and the playbook index. Playbooks, knowledge topics, workspace notes and saved skills are all read through tools when the skill runs, so a change to them reaches every install straight away.

The routing rules themselves carry a `skillVersion`, a hash of the skill's content. The skill sends it to `COUNT_get_agent_skill`, which reports whether the install is current:

Version check

```javascript
// First call of every conversation, beside COUNT_auth_status
COUNT_get_agent_skill({ installedSkillVersion: "<skillVersion from the installed SKILL.md>" })

// installedIsCurrent: true  → keep following the installed skill
// installedIsCurrent: false → follow the returned `content` for this conversation,
//                             and tell the user once how to update (see `install`)
```

No workspace data

`COUNT_get_agent_skill` reaches no workspace data. It returns the current skill body and the install instructions, and that's all.