wb-flow Documentation

Appearance

wb-flow Documentation ​

The official documentation for the 33-command /wb* agentic workflow system.

This is a field manual — opinionated, direct, and written for developers who actually use these commands rather than just read about them.

The Daily Workflow Loop — Orient → Plan → Execute → Validate → Commit → Close

Who is this for? ​

Stack-agnostic. wb-flow runs on any project where you have source files and markdown — Vue, React, Svelte, Solid, Next.js, Nuxt, Astro, Django, FastAPI, Rails, Go, Rust, anything. The 33 commands operate on package.json, source trees, and report folders; none of them care which framework wrote the code they're reading.

The one exception: /wbToWBC converts code to use the wbc-ui2 component primitives, which are Vue-based. If you're not on Vue, ignore that one command. The other 32 are universal.

Why examples skew Vue. This documentation was authored within a Vue monorepo (wb-core, wb-press, wbdataviewer2.wbc-ui.com), so every worked example draws from there. The patterns transfer one-for-one — /wbAudit reads source code the same way whether the source is .vue, .tsx, or .py.

What you need on day one:

  • A folder with code in it (any language)
  • A way to run the commands (any AI agent environment that accepts prompts)
  • Nothing else — no Node version requirement, no framework lock-in

How outputs are tagged (v1.8+) ​

Every output file from a suggestion-emitting command (/wbPlan, /wbAudit, /wbReview, /wbVision, /wbIdea, /wbStandup, /wbNext, /wbActOn) carries three metadata layers:

1. YAML front-matter:

yaml
---
type: 🔨 Worker     # the dominant action type
emits: mixed         # `pure` or `mixed`
---

2. A Requires column in every recommendation table:

#RequiresSuggestion…
1🔨 WorkerRefactor bin/install.js…
2✅ ValidatorAudit the new auth middleware…
3📋 MechanicalRun npm pack --dry-run…

3. The four canonical action types:

  • 🧠 Planner — Deep reasoning, strategy, multi-step decomposition
  • ✅ Validator — Big-thinker code-quality judgment, scoring
  • 🔨 Worker — Coder/executor: surgical code edits, refactors
  • 📋 Mechanical — Run command, parse output, format report. No judgment

See concepts/model_recommendations for which model to use per role.

How to read this documentation ​

FolderWhen to read it
start_here/First time using the system, or returning after weeks away
concepts/When you want to understand why the system works the way it does
daily_use/When you've forgotten which command to run at 10am vs. 4pm
commands/Per-command deep-dives — seven reading files per command
session_lifecycle/When and how to start and stop AI sessions cleanly

The seven files per command:

FileLengthRead when
hub (wbX.md)1 pageQuick overview: purpose, invocation, what happens
eli51–2 paragraphsOne-line mental model
practical1 pageAbout to run the command, need trade-offs
expert2–3 pagesConsidering modifying the template
examples3–5 pagesForgot what the output looks like
exhaustive4–6 pagesNeed the definitive edge-case simulation
live_demo2–4 pagesWant the command grounded in an actual workspace

Reading order for a new user ​

  1. start_here/installation — NPM, NPX, or Git installation
  2. start_here/getting_started — 30-day onboarding plan
  3. start_here/first_run_walkthrough — Annotated first session
  4. start_here/bootstrapping_existing_project — Inheriting code without /wbSetup
  5. concepts/overview_agentic_workflows — Commands grouped by the question they answer
  6. daily_use/the_daily_playbook — Morning → midday → afternoon → evening shape
  7. commands/ — Pick the command you're about to use; read its practical file

If you only ever read one of these, read the daily playbook.

Concept deep-dives ​

Cross-cutting ideas that don't belong in any single command's docs:

The 33-command catalog ​

Grouped by the question you're asking when you reach for them.

"What is this codebase?" — Context Builders ​

#CommandPurposeHub
01/wbSetupWrite context.md + dev.md for a new packagehub
02/wbContextRefresh package context against current codehub
03/wbStandupMonorepo-wide scan: what's in-flight, what's stalehub

"What should I do next?" — Planners ​

#CommandPurposeHub
04/wbPlanBreak a goal into a worker/validator task tablehub
05/wbVisionBrainstorm features when the queue is emptyhub
06/wbIdeaCapture and score speculative ideashub
07/wbNextPick the next optimal command based on repo statehub
08/wbHelpPrint the command catalog or per-command helphub
09/wbActOnTriage a diagnostic doc into ranked actionshub
10/wbExplainGenerate a persistent explanation of code or a taskhub

"Execute and validate" — Workers & Validators ​

#CommandPurposeHub
11/wbWorkExecute tasks defined in a plan filehub
12/wbValidAudit /wbWork output against the plan — PASS/FAILhub

"Is this any good?" — Critics ​

#CommandPurposeHub
13/wbAuditBrutal review against production standardshub
14/wbReviewPR-style review of a change vs. its planhub
15/wbTestRun tests, classify failureshub
16/wbCheckPre-flight quiz to verify AI understandinghub

"Clean this up" — Surgeons ​

#CommandPurposeHub
17/wbCleanFind dead code, stale files, forgotten console.loghub
18/wbRefactorRestructure code without changing behaviorhub
19/wbDebugHypothesize then investigate a specific errorhub
20/wbDocGenerate JSDoc + READMEs from codehub

"Ship it" — Shippers ​

#CommandPurposeHub
21/wbReleaseBump versions, unpick workspace:*hub
22/wbPublishBuild + push a package to npmhub
23/wbDeployBuild + push an app to a web hosthub
24/wbLicenseInject premium gating and license checkshub
25/wbBroadcastGenerate release announcement kithub
26/wbMonetizeBootstrap Free/Pro/Dev tier plumbinghub

"Version control" — Archivist ​

#CommandPurposeHub
27/wbGitAnalyze diff, draft Conventional Commithub
28/wbLogAppend a quick log note to the session trackerhub

"Protect & cross-cut" — Security, Translation, Migration ​

#CommandPurposeHub
29/wbSecureRed-team scan: secrets, XSS, insecure depshub
30/wbTranslatePull hardcoded strings to i18n keyshub
31/wbToWBCRewrite legacy/Vuetify into wbc-ui2 componentshub

"Session telemetry" — Tracking ​

#CommandPurposeHub
32/wbTrackToggle session-wide logging of /wb* invocationshub
33/wbStopTrackFinalize session, archive tracker, prepare for closurehub

What this documentation is NOT ​

  • Not the runtime templates. The source-of-truth _template.md files that define what each command actually does live in packages/wb-flow/templates/commands/. This documentation covers how to use them.
  • Not API documentation. Every file is hand-authored for human readers.
  • Not exhaustive on flags. If a command has 12 flags but only 3 matter daily, the docs cover the 3. The full flag list is in the runtime template.

wb-flow documentation — flow.wbc-ui.com · wb-flow on npm · wi-bg.com