npx rea-agents setup
@@ -53,760 +54,263 @@ REA connects your agent to tools for inspecting native binaries, JavaScript and
Setup registers REA with your agent and installs matching workflow instructions. Native analysis can use an existing Hopper or Ghidra installation; setup can optionally install Hopper with approval. Static JavaScript analysis needs neither engine.
+> **[Visit the REA website](https://morluto.github.io/rea/)** for setup instructions, illustrated guides, and real case studies.
+
## Quick start
-### Run setup (recommended)
+### Set up your agent
-Set up REA with your agent:
+With Node.js and npm installed, run:
```bash
npx rea-agents setup
```
-Choose which supported agents should use REA, then review the exact paths and changes before approving. Existing REA registrations are selected by default; newly detected agents are available to select, but detection alone does not select them. Setup adds MCP access and REA's guided workflow for selected agents. Hopper is a separate optional choice with its own consent. Setup can also record an existing Ghidra installation.
+Choose your agents, review the proposed changes, and approve them. Setup adds
+REA's MCP server and matching workflow instructions, with backups of existing
+configuration. Restart your agent afterward.
-Setup shows its changes before applying them and backs up existing configuration. See [Installation and setup](docs/installation.md) for requirements and setup options.
+Setup supports Claude Code, Codex, Cursor, Gemini CLI and
+[other agents](docs/installation.md#supported-agents). See
+[installation and setup](docs/installation.md) for provider configuration and
+manual MCP registration.
-### AI Coding Assistants (optional)
-
-Add the skill to your AI coding assistant for richer context:
-
-```bash
-npx skills add morluto/rea --skill reverse-engineer-anything
-```
-
-The skill provides REA's investigation workflow. Run setup above to connect REA to your agent and configure analysis tools. Setup already installs a version-matched skill by default; this command installs the repository version.
-
-### With an agent (recommended)
-
-After setup, restart your agent and [describe the app or feature](#just-ask-your-agent) you want to understand. Hopper can run in demo mode; if it shows a first-run prompt, choose the demo or enter an existing license.
-
-REA supports Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI, Windsurf, Devin, OpenCode, Antigravity, GitHub Copilot CLI, Command Code, and VS Code. Existing REA registrations are selected by default during setup; other detected agents remain unselected until chosen. Other agents can use the [manual MCP configuration](#manual-mcp-configuration).
-
-### First result from the terminal
-
-For your extracted JavaScript/Electron application tree or ASAR, run:
-
-```bash
-npx -y rea-agents@latest analyze-javascript-application /absolute/path/to/app --json
-```
-
-Replace the path with your target (for example, `"D:/apps/example"` on Windows).
-This returns inline Evidence, recovered graph, limitations, and unknowns without
-MCP setup, Hopper, Ghidra, or executing the application. For a native app, configure
-its engine first, then use `analyze` with that app's path. Run `doctor` when you
-need diagnosis; it is not a prerequisite for each analysis.
-
-### Check readiness for the task at hand
-
-`rea doctor` without options is an audit of the whole integration. It checks
-every detected agent registration, the installed skill, and every optional
-analysis engine, so it can report `healthy: false` while your current task works.
-Choose a readiness scope for the work you are doing:
-
-| Task | Readiness check |
-| ----------------------------------- | -------------------------------------------------------------------------------------------- |
-| Static JavaScript/Electron analysis | None. Run `analyze-javascript-application` directly. |
-| Troubleshoot one analysis engine | `rea doctor --provider ghidra --json` (or `hopper`, `ida`) |
-| Check one agent's MCP registration | `rea doctor --client codex --json` (see [client IDs](docs/installation.md#supported-agents)) |
-| Check the installed skill | `rea doctor --skill --json` |
-
-A scoped report has `scope.mode: "explicit"`. Only `scope_checks` determine
-`healthy` and the exit status. Everything else is listed in
-`informational_checks`; you don't need to fix it for this task. For example, a
-missing engine you are not using needs no repair. `environment_healthy` still
-summarizes the full audit. `--target` adds a target check, but without a scope
-option the report remains audit-wide.
-
-When more than one installed engine supports a native target, REA does not pick
-one: opening the target fails with `code: "capability_unavailable"`,
-`details.selection_reason: "ambiguous"`, and the providers in
-`details.candidate_ids`. Choose one once: pass `--provider` on
-the CLI or `provider_id` on `open_binary`, or set `REA_ANALYSIS_PROVIDER` as a
-standing preference. An explicit selector overrides the environment variable.
-The session keeps that choice and never falls back to another engine.
-Recovery depends on `details.selection_reason`. For `ambiguous`, choose one of
-the candidates. For `provider_unavailable`, the engine you selected needs repair,
-so run `rea doctor --provider |
-Decompile -Open an app and recover readable code, strings, names, and other clues about how it works. - |
-
-Understand -Follow the code from one part of the app to another until the agent can explain how a feature actually works. - |
-
-Recreate -Turn what the agent learned into a feature for your own product, adapted to your stack, interface, and requirements. - |
-