Platform matrix
Flow-Next is first-class on Claude Code, OpenAI Codex, Factory Droid, Cursor, xAI Grok Build, and OpenCode. First-class means the canonical plugin files are consumed (as-is or through the generated mirror), skills and slash commands run, multi-agent flows are verified, and setup detects the host.
Full install commands, update paths, and org-wide deployment are on Install. This page is the one-screen comparison.
| Host | Delivery | Slash form | Review backends | Ralph |
|---|---|---|---|---|
| Claude Code | Plugin marketplace | /flow-next:<name> | all | supported |
| Factory Droid | Plugin marketplace (auto-translates the Claude format) | /flow-next:<name> | all | supported |
| OpenAI Codex | install-codex.sh, pre-built mirror | $flow-next-<name> | all | supported |
| Cursor | Team-marketplace repo import (recommended) or install-cursor.sh | /flow-next:<name>, autocomplete lists /flow-next-<name> | host (recommended from inside Cursor) + bridges | intentionally not built |
| xAI Grok Build | Reads the canonical Claude plugin as-is; detected via GROK_AGENT=1 | /flow-next:<name> | host single-family fail-closed; cross-family via bridges | intentionally not built |
| OpenCode | install-opencode.sh scatters into ~/.config/opencode/ | /flow-next-<name> (flat) | host (agent-pinned) + codex | intentionally not built |
“Intentionally not built” is a posture, not a tiering gap: Ralph’s guard hooks need a hook schema those three hosts do not expose in a compatible shape, and pilot + land cover the same ground without them.
What differs in practice
Section titled “What differs in practice”- Where
flowctlcomes from. Every host resolves it from the plugin install, never from a copy in your repo. Claude Code and Droid use their plugin-root env vars; Cursor, Grok, and OpenCode derive the plugin root from the skill file’s own path; Codex uses${CODEX_HOME:-$HOME/.codex}/scripts/. On Claude Code bareflowctlalso works in the agent’s shell. - Which instruction file setup writes. Lifecycle docs default to
CLAUDE.md, model routing toAGENTS.md, and hosts that read both get both. - Subagent model pins. An agent definition’s
model:field is honored on Claude Code, Droid, and Grok; ignored on Cursor (subagents inherit the session model); best-effort on Codex. The full reach table is in Model routing. - Blocking questions. Claude Code and Droid use the native structured ask; the Codex mirror rewrites those into plain numbered prompts; Cursor asks natively.
- Two Codex homes. A machine with more than one
CODEX_HOMEneeds the installer run per home. See Install.
What does not differ
Section titled “What does not differ”The pipeline, the gates, the receipts, and the spec format are identical everywhere. A repo set up on one host works unchanged on another, because everything Flow-Next writes lives in .flow/ and the intelligence is whichever host agent is running. That is the whole point of the skills-own-judgment split.