Flow-Next Plugin Marketplace

      

The workflow layer for AI coding agents: durable specs, re-anchored workers, adversarial reviews, receipts. Everything lives in your repo. Zero external dependencies. Uninstall: rm -rf .flow/. </div> > 📖 Full doc index → · 🌐 flow-next.dev · 👥 Teams guide · 💬 Discord ---

Agentic engineering compresses implementation from weeks to hours — and quietly removes every safety valve pre-agentic Agile relied on. The standups, the hallway clarification, the mid-flight course correction that used to finish a vague ticket over a two-week cycle: gone. When an agent can ship the task in one sitting, a rough ticket plus a chat scrollback is the whole work surface. That work surface fails predictably. Agents drift mid-task, forget requirements, overfit to recent context, and hand reviewers 10K-line diffs with no focus signal. The bottleneck didn't disappear — it moved upstream, to requirements, review, and verification. The spec has to carry the weight. Flow-Next fixes the operating model, not just the prompt. It turns rough intent into durable specs, specs into context-sized task graphs, task graphs into re-anchored worker runs, and implementation into reviewed PRs with receipts. Between idea and merge it defines six named handover objects — each reviewable on its own, verified by a different model, and frozen at handover. The artifact chain is not bureaucracy. It is the conversation that would otherwise be missing.

Flow-Next is an AI agent orchestration plugin: 28 agent-native skills covering the full lifecycle — idea → spec → tasks → review → ship → maintain — layered on a bundled pure-stdlib Python CLI (flowctl). The host agent is the intelligence; flowctl is the deterministic plumbing. No external services, no SaaS, no global config. | Tenet | What it means | |---|---| | Spec-driven | Intent survives the chat. The unit of work is the spec — not the ticket, not the transcript, not the PR title. One durable document at .flow/specs/<id>.md, evolving through layers. | | Context-fit planning | Right-sized task slices. Specs decompose into dependency-ordered tasks, each sized to one fresh ~100k-token context window. | | Re-anchored work | Fresh context per task. Every worker subagent re-reads the spec, the task, and git state before touching code — no token bleed, no stale assumptions. | | Adversarial gates | Fix until SHIP. A different model (RepoPrompt / Codex / Copilot) reviews every plan and every implementation. Different models make different mistakes — the disagreement surface is where the gaps live. | | Receipts | "Done" means there is proof. Commits, tests, review verdicts, and evidence recorded per task — never narration. | | Multi-harness | One workflow everywhere. First-class on Claude Code, OpenAI Codex, and Factory Droid; runs on Grok Build and Cursor; community OpenCode port. | | Self-improving | Compounds as you work. Memory, glossary, decision records, and strategy grow as side-effects of the workflow you already run — no manual "refresh" ceremony, ever. | And one tenet about trust: everything lives in your repo under .flow/. Specs, tasks, memory, receipts — all of it is yours, in git, code-reviewable. Uninstall is rm -rf .flow/. ---