$ ~/registry/skill/composiohq-composio-skills-token-metrics-automation

SKILL

token-metrics-automation

Name: token-metrics-automation
Author: Composio

Automate Token Metrics queries and analysis workflows through Rube MCP tools.

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

Prompt only, no code
Open source
Community-trusted· 64.7k

Summary

This skill is essentially an open-source instruction/prompt artifact with visible source and strong community signals. The main security consideration is that it relies on an external Rube MCP service and a Token Metrics connection, so requests, sessions, and account authorization leave the local environment.

CredentialsCaution

The material says no API key is needed for the skill itself, but it explicitly requires establishing a `token_metrics` external connection via `RUBE_MANAGE_CONNECTIONS` and completing an auth-link flow. That implies third-party account authorization/tokens are still involved, even if the README does not expose the exact credential format, creating normal credential custody and misuse considerations.

Network egressCaution

The README explicitly requires adding the remote MCP endpoint `https://rube.app/mcp` and using Composio/Rube for search, connection management, and tool execution. User requests, session IDs, tool arguments, and potentially Token Metrics data will be sent to external services, but the material does not show unrelated or covert exfiltration endpoints.

Code executionLow risk

Based on the provided material, this is a prompt-only skill/instruction and does not describe spawning local processes, running shell commands, installing dependencies, or invoking host system capabilities. Its behavior is mainly orchestrating external MCP tools rather than executing code locally.

Data accessCaution

There is no stated ability to read local files, disks, or host resources. However, it can access data from the connected Token Metrics account through remote tools and passes `session_id`, arguments, and `memory` within Rube sessions, so the effective data scope depends mainly on the external account permissions and remote service handling.

Supply chainCaution

Positive factors: the skill entry comes from a GitHub open-source repository with very strong community stars. Limiting factors: the license and maintenance status are unknown, and the key execution surface depends on external Rube/Composio services rather than being fully locally auditable. Therefore, the supply-chain posture is caution rather than high risk.

Recommendations

Only connect after confirming that `rube.app/mcp` and related Composio/Token Metrics services meet your data compliance requirements.
Use least-privilege authorization for the Token Metrics connection and regularly review/revoke connections you no longer need.
Avoid placing unnecessary sensitive information into tool arguments, session memory, or free-text inputs.
Prefer vendors that provide a clear license, maintenance status, and data-handling documentation.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "token-metrics-automation" skill from askskill:
1. Download https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/token-metrics-automation/SKILL.md
2. Save it as ~/.claude/skills/token-metrics-automation/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// docs

Token Metrics Automation via Rube MCP

Automate Token Metrics operations through Composio's Token Metrics toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/token_metrics

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Token Metrics connection via RUBE_MANAGE_CONNECTIONS with toolkit token_metrics
Always call RUBE_SEARCH_TOOLS first to get current tool schemas

Setup

Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.

Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
Call RUBE_MANAGE_CONNECTIONS with toolkit token_metrics
If connection is not ACTIVE, follow the returned auth link to complete setup
Confirm connection status shows ACTIVE before running any workflows

Tool Discovery

Always discover available tools before executing workflows:

RUBE_SEARCH_TOOLS
queries: [{use_case: "Token Metrics operations", known_fields: ""}]
session: {generate_id: true}

This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.

Core Workflow Pattern

Step 1: Discover Available Tools

RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific Token Metrics task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["token_metrics"]
session_id: "your_session_id"

Step 3: Execute Tools

RUBE_MULTI_EXECUTE_TOOL
tools: [{
  tool_slug: "TOOL_SLUG_FROM_SEARCH",
  arguments: {/* schema-compliant args from search results */}
}]
memory: {}
session_id: "your_session_id"

Known Pitfalls

Always search first: Tool schemas change. Never hardcode tool slugs or arguments without calling RUBE_SEARCH_TOOLS
Check connection: Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing tools
Schema compliance: Use exact field names and types from the search results
Memory parameter: Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Session reuse: Reuse session IDs within a workflow. Generate new ones for new workflows
Pagination: Check responses for pagination tokens and continue fetching until complete

Quick Reference

Operation	Approach
Find tools	`RUBE_SEARCH_TOOLS` with Token Metrics-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `token_metrics`
Execute	`RUBE_MULTI_EXECUTE_TOOL` with discovered tool slugs
Bulk ops	`RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`
Full schema	`RUBE_GET_TOOL_SCHEMAS` for tools with `schemaRef`

Powered by Composio

Automate Composio tasks via Rube MCP with tool schema lookup first.

ComposioGet→

$ loading_