ai-blueprint

Read-only code quality audit for a Blueprint project. Reviews the active feature, changed files, a selected path, or the full project for maintainability issues such as duplication, dead code, DRY violations, inconsistent patterns, overgrown files or functions, unused exports, missing or disabled tests, standards drift, and obvious security or performance risks. Use when the user runs /audit, invokes $audit, asks to audit the code, review code quality, check for dead code, check for duplicates, clean up a vibe-coded project, or make sure the code still meets project standards.

Optional explicit Blueprint mode for one bounded spec/build/check/audit pass. It can pick or resume the current feature, write the spec when needed, create or reuse the branch, implement small steps, run build/tests/checks, create checkpoint commits after passing steps, audit changed code, repair confirmed high-severity findings, and stop with a review packet. It never completes, merges, pushes, deploys, publishes, sends, or performs destructive actions without explicit approval. Use only when the user explicitly runs /autopilot, invokes $autopilot, or directly asks for Autopilot.

Validate and, when needed, normalize the two planning docs before generating blueprint/context/project-overview.md from blueprint/project-plan.md and blueprint/build-plan.md. The overview is the single AI-facing source of truth that project instructions load every session. Use when the user runs /overview, invokes $overview, has just finished writing or editing the plans, asks to shape rough plans into the Blueprint format, or asks to regenerate the project overview.

Prepare a Blueprint project for deployment to Render or Vercel. Reads the plans, project commands, app config, and current repo state; verifies build, start, output, env, health checks, and provider config; can create or update render.yaml or vercel.json when requested; and stops before any external deploy, service creation, remote env change, push, publish, or destructive action unless the user explicitly approves. Use when the user runs /release, invokes $release, asks for Render setup, Vercel setup, deploy readiness, deployment config, render.yaml, or vercel.json.

Wrap up a finished feature or fix. Runs a final safety pass, archives its spec to blueprint/history/features/ (feature) or blueprint/history/fixes/ (fix), checks features off the build plan, resets blueprint/context/current-feature.md to its stub, makes one feature-level commit, then squash-merges the branch to main and deletes it. Merges only with explicit approval, then asks separately before pushing main. Use when the user runs /complete, or asks to finish, wrap up, merge, or close out the current feature or fix after it's built and reviewed.

Run a read-only Blueprint health check for setup, onboarding, required files, tool adapters, commands, Blueprint visibility, ignore rules, planning readiness, overview freshness, and workflow drift. Use when the user runs /doctor, asks whether the Blueprint is installed correctly, wants a health check, setup check, doctor pass, or says something feels off before starting or resuming work.

Build the feature or fix spec'd in blueprint/context/current-feature.md, one small reviewable step at a time. Creates the branch, implements each step, shows the diff and explains it in plain English, tests, and iterates until it works. After each approved step it offers an optional commit checkpoint on the branch; the feature-level commit, merge, and logging are /complete's job. Use when the user runs /implement, or asks to build, implement, or start the current feature or fix once its spec is ready.

Set up the Blueprint after overlaying it onto a freshly scaffolded or early project. Detects the stack, relocates the copied Blueprint README when needed, updates AGENTS.md commands, sets the CLAUDE.md project title when present, tunes coding-standards.md, checks ai-interaction.md and .gitignore, asks whether Blueprint workflow files should be committed or kept local-only, confirms which tool adapters to keep, and tells the user exactly what to fill in before /overview or $overview. Use when the user runs /onboard, invokes $onboard, just copied the Blueprint into a new project, or asks what to do after overlaying the Blueprint. For an existing app with meaningful shipped features, use adopt instead.

Show where the project stands: build-plan progress, the current feature's checked and unchecked steps, git state, drift warnings, and the exact next action. Read-only. Use when the user runs /status, asks where things stand, what's next, what's in progress, or is picking work back up after a break or a context clear.

Generate a human manual try guide for the current or most recently completed Blueprint feature. Reads the spec, project commands, and available app context, then tells the user exactly what to start, where to go, what to click or run, what to expect, and what would count as wrong. Read-only. Use when the user runs /try, invokes $try, asks how to test manually, asks where to click, asks how to see the change, or wants a manual review path after /implement, /autopilot, /check, or /complete.

Bring the blueprint into an existing (brownfield) codebase. Surveys the real repo, interviews you for the intent code can't reveal, then generates the two plans you own (project-plan.md with shipped features, build-plan.md as a checklist with existing features already checked) plus coding-standards.md reflecting the project's actual conventions - and points you at /overview to finish. Use when the user runs /adopt, is overlaying the blueprint onto an app that already has meaningful code, or asks to adopt or bootstrap the workflow into an existing project. For freshly scaffolded or early projects, use onboard instead.

Add or normalize unit testing for a Blueprint project. Detects the stack, reuses an existing test runner when present, or installs the stack-native unit test runner when missing, then adds one small example test, updates AGENTS.md commands, runs build and tests, and reports the diff. Use when the user runs /tests, invokes $tests, asks to add unit tests, set up unit testing, configure tests, or make tests part of the Blueprint workflow.

Prove the current work actually does what its spec says by running the real app and observing behavior against the "done when" criteria in current-feature.md. Drives the app (browser, CLI, or server), captures evidence (screenshots, output, console/network errors), and reports pass/fail per criterion. Does not edit source or commit - it observes; fixing stays /implement's job. Use when the user runs /check, asks to confirm a step or feature works, wants proof before /complete, or wants to check a change in the running app rather than just the build. (Supersedes the built-in /verify with a spec-aware version inside blueprint projects.)

Read-only briefing on an upcoming build-plan feature before you spec it. With no argument, briefs the next unchecked item; given a number or name, briefs that one. Reads build-plan.md and project-overview.md and explains what the feature is, what it depends on, what it will touch, how big it is, and whether it will split - without writing anything. Use when the user runs /brief, asks what the next feature involves, wants to understand or preview a feature before /feature, or is deciding what to build or reorder next.

Turn a feature from build-plan.md into a buildable spec. With no argument, specs the next unchecked item in the build plan; given a number or name, specs that one. Sizes the feature and splits anything too big into smaller sub-features (4a, 4b, ...), writes small, reviewable build steps to blueprint/context/current-feature.md, then red-teams its own draft for gaps, oversized steps, and scope creep before stopping at a review gate. Use when the user runs /feature, names or numbers a feature, or asks to spec out, break down, or start the next feature.

Document an ad-hoc bug fix or small change (one not in the build plan) into blueprint/context/current-feature.md so it runs through the same build loop. Writes a short fix spec and stops; then /implement builds it and /complete logs it to blueprint/history/fixes/ and merges. Use when the user runs /fix, reports a bug, or asks to fix or change something that isn't a planned build-plan feature.

Interactively prototype the look of a project. Asks about the desired look and feel and which pages to draft, proposes a plan, and only then writes throwaway static HTML/CSS mockups to prototypes/ that share one theme (a set of CSS theme variables). A plan-first, pre-build helper that sits outside the spec-driven feature loop, like scaffolding. Use when the user runs /prototype, names screens to mock up, or asks to prototype the layout, theme, or look and feel.