Frequently asked questions

The questions that come up most often. For the canonical references see the install walkthrough, the configuration reference, and the reviewer pipeline overview.

How do I install Synthex?

Inside Claude Code, register the LumenAI marketplace with `/plugin marketplace add bluminal/lumenai`, then install the plugin with `/plugin install synthex`. From the project you want Synthex to manage, run `/synthex:init` to scaffold the standard layout. There is no SDK to install and no API key to manage — everything happens inside your existing Claude Code session.

Where does configuration live?

Project-level configuration lives at `.synthex/config.yaml` and overrides the plugin's shipped defaults. Anything you don't specify falls back, so the file only needs to contain values you actually want to override. The Configuration reference page documents every key and the resolution order: plugin defaults → project file → per-command overrides → per-invocation parameters.

Can I use models other than Claude for review?

Yes. The `code_review` and `implementation_plan` config blocks support a multi-model branch where the same artifact is sent to Claude and to one or more external CLI adapters running other LLM families. The Multi-Model Review Orchestrator fans them all out in parallel; the Findings Consolidator merges the outputs. Different model families have different blind spots — running multiple in parallel catches errors any single family would miss.

How do I contribute an agent or command back to Synthex?

Open a pull request against the LumenAI repository at https://github.com/bluminal/lumenai. The plugin source lives at `plugins/synthex/`. The Authoring agents and Authoring commands docs cover the conventions Synthex itself follows. Project-specific extensions — agents or commands that shouldn't go upstream — work as their own plugin alongside Synthex; the marketplace is just a Git repository so you can host one anywhere.

Where do I file bugs or feature requests?

Open an issue on the LumenAI repository at https://github.com/bluminal/lumenai/issues. Include the agent or command name, your `.synthex/config.yaml` (with secrets redacted), and the expected vs. actual behavior. For Claude Code itself — the runtime that hosts the plugin — file at https://github.com/anthropics/claude-code/issues.

How many tasks should I run in parallel?

The conservative default is 3 concurrent tasks (configurable via `next_priority.concurrent_tasks`). Most laptops handle ~75% of CPU cores comfortably (Aggressive). Going beyond that (Yolo mode, one task per core) maximises throughput but inflates `[H]` review queues — you'll be staring at a lot of pending approvals. The right value depends on your patience for review more than your machine's capacity.