Spec-Driven Delivery · Claude Code
A toolkit that turns Claude Code into a spec-driven delivery line — requests are grilled into specifications, plans are challenged until no gaps remain, and code ships only after gated review and a verification loop.
It is built around three things you can see on this page: an interactive pipeline schematic, a set of expert review modes, and a live statusline for the terminal. Claude is the primary engine and drives every phase. Codex — OpenAI's CLI coding agent — is an optional second engine you turn on, and configure, through /m:setup.
/m is a set of nineteen Claude Code commands and skills that run software delivery as one disciplined pipeline instead of a chat. The work moves through gated phases, each phase proves it finished before the next begins, and the project's own memory is read at every step. Three parts make up the system:
Pipeline
Gated delivery
One command — /m:develop — drives every change through five phases: refine, plan, implement, review, iterate. Each runs as a discrete skill behind a marker-file gate.
Support · memory
Project state
Utility stages build and feed the per-repo .m/ memory — index, tasks, progress, gaps, research — the shared state every pipeline stage reads.
Expert modes
Review lenses
Specialist review modes clip onto the work — some run by hand, others load themselves when matching files are edited — to harden security, Go, React, and business logic.
/m:develop orchestrates the five phases below. The boundaries between them are hooks, not honor rules — a phase cannot start until the previous one has written its completion marker, so the pipeline can't quietly skip a step.
Claude and Codex are engines, not models — each runs its own underlying models. The pipeline runs on Claude by default and works fully Claude-only. Codex is a dual-engine add-on: when it is on, a second engine independently checks the plan, the research, and the review, and disagreements are surfaced side-by-side rather than silently merged.
Claude Code is the surface and Claude is the engine driving every phase — refine, plan, implement, review, iterate. Its models — Opus, Sonnet, and Haiku — are used across stages by weight of task.
Nothing else is required. With Codex off, every stage runs Claude-only and the pipeline behaves exactly the same, minus the second opinion.
OpenAI's CLI coding agent, used as an optional second engine for /m:plan, /m:research, and /m:review. When enabled it runs automatically on every applicable pass and is token-metered per run, so its cost stays capped.
You turn it on or off — and pick its model (gpt-5.5, gpt-5.4, …), reasoning effort, and fast mode — with the /m:setup wizard. Settings live in each repo's .m/pipeline.yml; set enabled: false to go Claude-only.
Getting running is short. Claude Code is all you need for the full pipeline; Codex is a deliberate, optional second step.
Everything in /m runs on top of Claude Code. Once it is installed and authenticated, the pipeline is usable end-to-end on Claude alone.
The nineteen commands and skills live under ~/.claude/commands/m/ and ~/.claude/skills/m-*/. With them in place, /m:develop and the individual phases are available in any project.
Want the dual-engine second opinion? Run the guided setup wizard. It checks the Codex CLI and login, then walks you through the choices and writes them for you:
Codex needs its own CLI and a ChatGPT login; /m:setup tells you exactly what is missing and how to fix it. Read-only check first? Run /m:setup --check.
Each repo's .m/pipeline.yml holds the codex: block — enabled, fast_mode, model, reasoning_effort, and the token budget. Absent file means built-in defaults apply; /m:setup can write it for you.
Two companion pages go deeper — the full interactive pipeline schematic, and the statusline that rides along in your terminal.
An engineering working-drawing of all nineteen stages — five gated phases, support and expert lanes, dual-engine checks, and per-repo memory. Select any component to read its live specification.
Open the schematic → Terminal companion m-statuslineA single-file Claude Code statusline — model, context burn, and pipeline state at a glance, with the pixel-burn duck brand. Drops into your Claude Code config.
Open the statusline page →