We’ve added a CLI for Claude Platform to make every API endpoint...
ClaudeDevs@ClaudeDevs
135 views
Jun 02, 2026
~1 min read
Advertisement
1
We’ve added a CLI for Claude Platform to make every API endpoint runnable from your terminal.
Call the Messages API, stand up Claude Managed Agents, pipe results straight into your shell.
The ant CLI is well understood by coding agents (Claude Code) using the claude-api skill.
Call the Messages API, stand up Claude Managed Agents, pipe results straight into your shell.
The ant CLI is well understood by coding agents (Claude Code) using the claude-api skill.
2
For interactive login, the CLI supports "ant auth login".
This runs a browser OAuth flow, scopes the token to a workspace, and stores it for you.
That one credential is then used by the CLI (and even the SDKs) to authenticate your API calls.
This runs a browser OAuth flow, scopes the token to a workspace, and stores it for you.
That one credential is then used by the CLI (and even the SDKs) to authenticate your API calls.
3
Every API resource is a subcommand, including messages, models, and files.
Build requests from typed flags or piped YAML, inline a file with @.path, reshape any response with --transform.
Output as json, yaml, jsonl, or explore (default) for a TUI you can fold and search.
Build requests from typed flags or piped YAML, inline a file with @.path, reshape any response with --transform.
Output as json, yaml, jsonl, or explore (default) for a TUI you can fold and search.
4
Use the ant CLI to create and update Claude Managed Agents, locally or from CI.
Version control your agent as YAML in Git and have CI run "ant beta:agents update" to sync changes to the Claude Platform.
Version control your agent as YAML in Git and have CI run "ant beta:agents update" to sync changes to the Claude Platform.
5
The CLI can kick off a Managed Agents session, send it an event, and the agent goes to work: reasoning, calling tools, working toward an answer.
When it's done (or stuck), pull the trace: every event, every tool call, every decision is retrievable from the same CLI.
When it's done (or stuck), pull the trace: every event, every tool call, every decision is retrievable from the same CLI.
6
Claude Code knows how to use ant using the built-in "/claude-api" skill
Ask it to list your sessions, upload a folder of PDFs, or debug a run.
It shells out to the CLI and reads the results back without any glue code.
Install with brew, curl, or go: platform.claude.com/docs/en/api/sd…
Ask it to list your sessions, upload a folder of PDFs, or debug a run.
It shells out to the CLI and reads the results back without any glue code.
Install with brew, curl, or go: platform.claude.com/docs/en/api/sd…