Agent mode

Fully autonomous browser interaction. The AI browses, captures, and writes the client end-to-end.

Agent mode hands the steering wheel to the AI. Describe the goal in plain English; providers such as Playwright MCP or Chrome DevTools MCP route browser actions over MCP, whereas agent-browser shells upstream's CLI directly after Reverse API Engineer resolves the binary (PATH agent-browser, else npm install -g <pin>, else npx -y) and prompt-injected skill workflows.

Agent mode capturing a job board autonomously — Agent mode: autonomous capture and codegen in one flow.

When to use it

You want full automation, no manual browsing required.
The site exposes a stable, predictable flow (public job boards, docs sites, marketing APIs).
You're scripting captures from another agent, a cron job, or CI.

Running interactively

reverse-api-engineer
# the session starts in agent mode
> all open jobs on jobs.ashbyhq.com/openai

Or start from the subcommand: in a terminal, agent opens the same session and starts the run right away, with its options kept for the prompts you type next.

reverse-api-engineer agent --prompt "all open jobs on jobs.ashbyhq.com/openai" --headless

The agent's steps, messages and reasoning stream into the conversation. Type a follow-up when it finishes, answer its questions in the input bar, and press Esc to stop it. /resume picks a past run back up where it stopped.

Running non-interactively

With --json, --json-stream or --no-interactive, agent never opens the session: it prints plain output and exits, which is what scripts and other agents want.

reverse-api-engineer agent \
  --prompt "capture the public jobs api" \
  --url https://example.com/jobs \
  --json | jq

The --json flag makes the command emit a single JSON document on stdout (see Scripted usage for the schema and exit codes).

Use --json-stream when a supervising agent wants NDJSON progress events during the browser and generation loop:

reverse-api-engineer agent \
  --prompt "capture the public jobs api" \
  --url https://example.com/jobs \
  --json-stream

For wrapper or CI validation without launching a browser, use:

reverse-api-engineer agent \
  --prompt "capture the public jobs api" \
  --url https://example.com/jobs \
  --dry-run

--dry-run implies JSON output and checks prompt, URL, SDK config, browser tooling, and output directory writability.

Agent providers

Pick the provider in /settings then "agent provider".

Playwright MCP browser automation with your configured SDK. Combines browser control and real-time reverse-engineering in a single workflow. Use --headless when running on machines without a display.

Reasoning model

The agent's reasoning model is the same as your configured SDK model. See Model selection to change it.