# REA reverse engineering

Omnius includes [`rea-agents` 6.7.0](https://www.npmjs.com/package/rea-agents/v/6.7.0)
as a required dependency, with the matching MIT-licensed investigation skill
and reference guides. The [REA documentation](https://rea.tools/) describes its
supported targets and analysis providers.

```sh
omnius rea status --json
omnius rea analyze-javascript-application "/absolute/path/to/app" --json
omnius rea --help
```

`omnius rea` runs the installed package directly. It preserves trailing arguments
and exit status, requires no model server, and performs no additional npm
download or setup. Static JavaScript/Electron inspection does not need a native
decompiler. Native routes use existing provider configuration; Omnius does not
install Ghidra, Java, Hopper, IDA, or other engines automatically. REA's optional
native providers keep their own prerequisites.

The `omnius-rea` and `reverse-engineer-anything` skills appear in normal skill
discovery from any working directory. Only their metadata enters the skill
listing; their bodies and reference guides load when selected. Project-local
skills retain precedence. The shipped `assets/rea/UPSTREAM.json` records the
upstream release integrity and checksums of the original skill and license.

For an MCP connection, `omnius rea mcp-config` prints the exact installed stdio
binding without changing any client configuration. `omnius rea --mcp` starts that
server with unmodified protocol streams. Use the existing MCP onboarding path
when a task benefits from that connection. Ordinary tasks do not start REA or
load its full tool catalog.

The upstream `omnius rea mcp add` and `omnius rea mcp doctor` commands retain
their registration and connection-diagnostic behavior and arguments.

Begin with the user's explicit artifact or capture. Keep static observations,
runtime observations, inferences, and unknowns distinct. Preserve evidence
identities and coverage limits; execute a target only within the requested
investigation's scope.
