Skip to content
Documentation

CLI + Skills

AI coding agents work best when they understand your systems, APIs, and tools. The superglue CLI ships with a skill — a structured reference that teaches agents how to use every sg command, handle auth, build tools, and debug failures. Install once, works across 35+ agents.

Installing the CLI

Section titled “Installing the CLI”
Terminal window
npm install -g @superglue/cli

Setup

Section titled “Setup”

Browser login:

Terminal window
sg login

Opens your superglue web app to authorize the CLI and stores an OAuth session. Check the active identity with sg whoami.

Environment variables (CI, AI agents, non-interactive):

Terminal window
export SUPERGLUE_API_KEY="your-api-key"
export SUPERGLUE_API_ENDPOINT="https://api.superglue.cloud"  # optional, this is the default

Verify: sg system list — if you see fetch failed or auth errors, double-check your API key and endpoint.

Installing the Skill

Section titled “Installing the Skill”

The skill gives your AI agent full CLI knowledge — commands, auth patterns, tool schemas, debugging, and deployment. Install once and the agent references it automatically.

Universal Install (all agents)

Section titled “Universal Install (all agents)”
Terminal window
npx skills add superglue-ai/cli

Auto-detects your installed agents. Target a specific agent with -g -a <agent>:

Terminal window
npx skills add superglue-ai/cli -g -a claude-code
npx skills add superglue-ai/cli -g -a codex
npx skills add superglue-ai/cli -g -a cursor

Agent-Specific Install

Section titled “Agent-Specific Install”

From the Anthropic marketplace:

Terminal window
/plugin install superglue@claude-plugins-official

Or load from local install:

Terminal window
claude --plugin-dir $(npm root -g)/@superglue/cli

What the Skill Provides

Section titled “What the Skill Provides”
  • All CLI commands with flags, options, and usage patterns
  • Authentication patterns — credential placeholders, OAuth flows, header formats
  • Tool configuration schema — step configs, data selectors, transforms, pagination
  • Debugging workflows — common errors, --include-step-results, sg system call for isolation
  • Deployment patterns — SDK, REST API, webhooks (via references/integration.md)
  • Specialized references for databases, file servers, and transforms (loaded on demand)

Adding Project-Specific Context

Section titled “Adding Project-Specific Context”

The skill teaches the AI how to use superglue. Add a section to your project’s AI config file (CLAUDE.md, AGENTS.md, or .cursorrules) so it knows to use the skill and discover your setup dynamically:

## Using Superglue


When working with superglue tools — via the CLI, SDK, or REST API:


1. Invoke the superglue skill and read the SKILL.md file before running any sg command
2. Read the relevant reference files for the task (e.g. http, postgres, file-handling, integration)
3. Ensure the CLI is configured (sg login has been run or env vars are set)
4. Run sg system list and sg tool list to discover the current setup before building or modifying anything
5. Never hardcode system IDs or tool IDs — always discover them dynamically

Best Practices

Section titled “Best Practices”

Always test systems before building tools

Section titled “Always test systems before building tools”

Have the agent run sg system call to verify auth and see the actual response shape before constructing a tool config:

Terminal window
sg system call --system-id stripe \
  --url "https://api.stripe.com/v1/customers?limit=2" \
  --headers '{"Authorization":"Bearer <<stripe_api_key>>"}'

Use --include-step-results when debugging

Section titled “Use --include-step-results when debugging”

Shows the raw API response from each step — pinpoints whether the issue is auth, the endpoint, or a transform:

Terminal window
sg tool run --draft <id> --payload '{}' --include-step-results

Never paste secrets into chat

Section titled “Never paste secrets into chat”

Use --sensitive-credentials when creating systems via the CLI so secrets are prompted securely:

Terminal window
sg system create --id my_api --url https://api.example.com \
  --credentials '{"client_id":"abc"}' \
  --sensitive-credentials client_secret,api_key

LLM-Readable Documentation

Section titled “LLM-Readable Documentation”

For agents that don’t support skills, we provide full docs in LLM-friendly formats:

File URL Purpose
Index llms.txt Lightweight index of all pages
Full docs llms-full.txt Complete documentation in one file

If your tool can fetch URLs — give it the URL. If it requires file uploads — download llms-full.txt and upload directly.

Support & Resources

Section titled “Support & Resources”