Use c1i with AI coding agents

Set up c1i as a skill for Claude Code, Cursor, and other AI coding agents so they can manage users, apps, entitlements, and access requests in C1.

c1i is designed from the ground up for AI agents. The c1i docs skill command exports a self-contained skill file that teaches your AI coding agent how to use every c1i command, discover API endpoints, and manage C1 resources — without needing external documentation.

What is a skill file?

A skill file is a structured markdown document that gives an AI coding agent the context it needs to use a tool effectively. The skill file produced by c1i docs skill covers:

• All c1i commands, flags, and output formats
• API discovery workflows (how to find and understand endpoints)
• Common API endpoints and pagination patterns
• Authentication setup

When you add this skill file to your agent’s context, the agent can manage users, apps, entitlements, tasks, and access requests in C1 through natural-language instructions.

Generate the skill file

Run c1i docs skill to output the skill file to your terminal:

c1i docs skill

To write it directly to a file:

c1i docs skill -o SKILL.md

The docs skill command works without authentication, so you can generate the skill file before logging in.

Set up c1i with Claude Code

Claude Code loads skills from .claude/skills/ in your project directory. To add c1i as a skill:

1. Create the skills directory if it doesn’t exist:

   mkdir -p .claude/skills/c1i
   
2. Generate the skill file into that directory:

   c1i docs skill -o .claude/skills/c1i/SKILL.md
   
3. Verify the file was created:

   cat .claude/skills/c1i/SKILL.md
   

   You should see the skill content starting with a YAML frontmatter block containing name: c1i.

4. Start using c1i through Claude Code. You can now give Claude natural-language instructions like:

   • “List all users with status enabled”
   • “Search for entitlements related to admin access”
   • “Show me all open access request tasks”
   • “Create a grant request for user X to entitlement Y”

Make sure c1i is installed and authenticated (c1i auth login) before asking Claude Code to run c1i commands. For non-interactive setups (CI, containers, headless servers), set C1I_URL, C1I_CLIENT_ID, and C1I_CLIENT_SECRET as environment variables instead of running auth login — c1i picks them up automatically. See Credential storage for the full precedence order.

Set up c1i with Cursor

Cursor uses project rules to provide context to its AI. To add the c1i skill:

Project rule (recommended)

1. Create the rules directory if it doesn’t exist:

   mkdir -p .cursor/rules
   
2. Generate the skill file as a Cursor rule:

   c1i docs skill -o .cursor/rules/c1i.md
   
3. Open Cursor and start giving instructions. Cursor’s AI now understands c1i and can run commands on your behalf.

User rule (global)

To make c1i available across all your Cursor projects, add it as a user rule:

1. Open Cursor and go to Settings > Rules > User Rules.

2. Generate the skill file:

   c1i docs skill
   
3. Copy the output and paste it into the user rules text area.

Set up c1i with other agents

The skill file is plain markdown with YAML frontmatter, so it works with any AI coding agent that accepts context files. The general pattern:

1. Generate the skill file:

   c1i docs skill -o c1i-skill.md
   
2. Add the file wherever your agent reads context. Common locations:

   Agent	Where to put the skill file
   Claude Code	.claude/skills/c1i/SKILL.md
   Cursor	.cursor/rules/c1i.md
   Windsurf	.windsurfrules (append the content)
   GitHub Copilot	.github/copilot-instructions.md (append the content)
   Cline	.clinerules (append the content)

3. Authenticate c1i if you haven’t already:

   c1i auth login --url your-tenant.conductor.one
   

Example workflows

Once your agent has the c1i skill, you can use natural language to accomplish common tasks.

Confirm the active identity

Ask your agent to verify which user it’s acting as before making changes:

"Who am I authenticated as in C1, and how many roles do I have?"

The agent runs c1i auth whoami and reports the user ID, display name, email, and counts of roles, permissions, and feature flags.

Explore the API

Ask your agent to discover what’s available before running authenticated commands:

"What C1 API endpoints are available for managing tasks?"

The agent uses c1i docs endpoints and c1i docs endpoint to explore the API without credentials.

Audit user access

"List all enabled users, then show me entitlements for the AWS app"

The agent runs c1i users list --status=enabled and c1i entitlements list --app-id=<id> and presents the results.

For broader queries where you want a fast answer rather than a full dataset, ask the agent to limit results:

"Show me 5 example users with status enabled — just enough to verify the data shape."

The agent runs c1i users list --status=enabled --limit=5. c1i tightens the per-call request size to match --limit and stops auto-paginating once the cap is reached, so the API call is small even when the underlying tenant has thousands of users.

Manage access requests

"Show me all open tasks assigned to me and approve the ones related to the staging environment"

The agent runs c1i tasks list --state=open --assigned-to-me, filters the results, and uses c1i tasks approve for the matching tasks.

Investigate an app’s accounts

"Find all unmapped accounts in the Okta app and list their details"

The agent runs c1i accounts list --app-id=<id> --unmapped-only to surface accounts that haven’t been linked to C1 users.

Keep the skill file up to date

The skill file is versioned — it includes the c1i version in its frontmatter. When you update c1i, regenerate the skill file to pick up any new commands or changes:

# Update c1i
go install github.com/ConductorOne/c1i@latest

# Regenerate the skill file
c1i docs skill -o .claude/skills/c1i/SKILL.md

Pages related to c1i agent setup

• Install c1i — installation, authentication, and configuration
• c1i command reference — complete list of commands, subcommands, and flags