Fire one prompt and walk away. Install once, scaffold a flow fitted to your stack, then take changes from spec to a reviewed, committed branch. New to the idea? Start with the concept.
In Claude Code, from the repo you want to set up:
/plugin marketplace add chrisjenx/cjs-orchestrator/plugin install develop@cjs-orchestrator/develop:init detects your stack, confirms your real gate commands with you, and writes the per-repo definitions plus safe hooks into .claude/./develop:run <spec | ticket | idea> per change, and /develop:flywheel periodically to tune the flow from its postmortems.Nothing is transplanted: /develop:init reads this repo's commands and conventions and grows from a minimal core. Re-run it any time to refresh discovery: it reconciles, it doesn't clobber.
Three static, portable skills. Their behaviour is fitted to your repo because they read the definitions init discovered, not because they were rewritten for you.
Detects your stack, discovers the real build/test/lint/coverage commands (CI is the source of truth), and writes .claude/develop.config.json, a routing table, a starter CLAUDE.md, safe hooks, and a flywheel doc. Confirms with you before writing.
The orchestrator loop. Plans, works in an isolated worktree, dispatches one executor per phase, then runs a fixed quality tail (validate → audit → tidy → finalize) wired to your gates. Blocks the commit until they pass; hands off a branch (never pushes).
Reads the accumulated postmortems, flags finding categories that keep escaping (or are breaking-class), and proposes the cheapest fix (a hook, gate, rule, anchor, or a new reviewer), human-gated. This is how the flow gets stronger over time.
The orchestrator doesn't decide "done" by judgement: it clears a phase only when a command ran and produced evidence. So the flow's ceiling is set by what your repo can mechanically verify. Point it at a repo with strong gates and it's formidable; point it at one with no checks and it can only confirm what little there is.
CLAUDE.md. Your conventions, stated plainly. The code-reviewer reviews against the rules that exist; it won't invent standards. Vague or missing rules mean vague review./develop:flywheel after a few features and promote the recurring escapes into hooks/gates/rules. The line tightens every cycle, but only if you feed it.Weak checks aren't a blocker to starting: /develop:init degrades gracefully and uses whatever you confirm. But the gap between "it ran" and "it's trustworthy" is exactly the gap between a repo with strong mechanical checks and one without. That's where the payoff lives.
The plugin ships static, portable skills and agents. /develop:init writes only the repo-specific definitions they read, so the flow is fitted without being a copy you have to maintain.
.claude/develop.config.json: your gates (tagged cheap/heavy), stack, model tiers, capsdevelop-routing.json: artifact-shape → agent (starts with a generalist fallback)CLAUDE.md: a short starter from your discovered conventionsdevelop-flywheel.md: the postmortem log plus your promoted checkshooks/: a worktree guard plus a generic command timeout/develop:init, /develop:run, /develop:flywheelYour routing table references the bundled agents by name. Specialists you add later live in your own .claude/agents/, grown via the flywheel.
Reuse first, defer creation to workflows: the flow prefers the skills/agents/rules you already have, and when something's missing it proposes building it, rather than quietly hand-rolling one-off helpers.
/develop:run plans, builds, and runs the quality tail. The finalize phase logs a postmortem: what escaped, classified preventable vs irreducible./develop:flywheel reads the postmortems, and for each recurring (or breaking-class) escape proposes the cheapest lever: a hook, gate, rule, anchor, or a new or pruned reviewer..claude/ without you.Want the why behind all of this? The concept page walks the full pipeline, the design trade-offs, and the portable patterns.