@growthub/cli 0.14.4 → 0.14.6

package/assets/worker-kits/growthub-marketing-skills-v1/templates/launch-checklist.md

@@ -1,83 +0,0 @@
-# Launch Checklist — [Client] / [Product/Feature]
-
-**Date:** YYYY-MM-DD
-**Version:** v1
-**Domain:** Launch
-**Operator:** marketing-operator
-
----
-
-## Executive Summary
-
-<!-- 3-5 bullet points of key decisions -->
-
----
-
-## Launch Overview
-
-| Field | Value |
-|---|---|
-| Launch type | New product / Feature / Rebrand / Campaign |
-| Target date | |
-| Audience | |
-| Primary CTA | |
-| Success metric | |
-
----
-
-## Pre-Launch (T-minus 2 weeks to launch)
-
-- [ ] Product-marketing context finalized
-- [ ] Landing page / announcement page live
-- [ ] Email sequence built and tested
-- [ ] Social content calendar drafted
-- [ ] Press / community outreach list ready
-- [ ] Analytics tracking confirmed (events, goals, UTMs)
-- [ ] Internal team briefed on messaging and positioning
-- [ ] FAQ / objection handling document prepared
-- [ ] Paid ad creative and targeting ready (if applicable)
-- [ ] Beta feedback collected and addressed
-
----
-
-## Launch Day
-
-- [ ] Announcement email sent
-- [ ] Social posts published (all channels)
-- [ ] Community announcement posted
-- [ ] Press / outreach emails sent
-- [ ] Paid ads activated (if applicable)
-- [ ] Real-time monitoring active (analytics, social, support)
-- [ ] Team available for rapid response
-
----
-
-## Post-Launch (T-plus 1-4 weeks)
-
-- [ ] Day 1 metrics reviewed (traffic, signups, conversion rate)
-- [ ] Week 1 performance report compiled
-- [ ] User feedback collected and categorized
-- [ ] Quick wins from feedback implemented
-- [ ] Follow-up email sequence activated
-- [ ] Retargeting campaigns launched (if applicable)
-- [ ] Content iteration based on top-performing angles
-- [ ] Week 4 full retrospective completed
-
----
-
-## Channel Plan
-
-| Channel | Pre-Launch | Launch Day | Post-Launch |
-|---|---|---|---|
-| Email | | | |
-| Social | | | |
-| Blog/SEO | | | |
-| Community | | | |
-| Paid | | | |
-| Press | | | |
-
----
-
-## Next Steps
-
-- 

package/assets/worker-kits/growthub-marketing-skills-v1/templates/project.md

@@ -1,48 +0,0 @@
----
-# .growthub-fork/project.md — session memory primitive (v1)
-#
-# Written by the CLI at init/import time. Append-only, human-readable; sits
-# alongside the machine-readable `trace.jsonl`. Approvals, self-eval outcomes,
-# and sub-skill runs all record here.
-#
-# Replaceable tokens (seeded at init time):
-#   {{KIT_ID}}   {{FORK_ID}}   {{STARTED_AT}}   {{SOURCE}}   {{SOURCE_REF}}
-
-kitId: "{{KIT_ID}}"
-forkId: "{{FORK_ID}}"
-startedAt: "{{STARTED_AT}}"
-source: "{{SOURCE}}"
-sourceRef: "{{SOURCE_REF}}"
-skillManifestVersion: 1
-approvals: []
-selfEvalHistory: []
-subSkillRuns: []
----
-
-# Project journal — fork `{{FORK_ID}}`
-
-Baseline primitive: `{{KIT_ID}}`. Seeded at `{{STARTED_AT}}` from `{{SOURCE}}` (`{{SOURCE_REF}}`).
-
-This is your cross-session continuity surface. Read the last few entries before every session; append after every material change, approval, and self-eval boundary.
-
-## How to use this file
-
-1. **Session start.** Read the last 3 entries + tail 20 events in `.growthub-fork/trace.jsonl`. State your plan.
-2. **Material change.** Record as a dated bullet (what, why, outcome). Simultaneously append a typed event to `trace.jsonl` via the Fork Sync Agent — never bypass.
-3. **Approval boundary.** Add a row to `approvals` in the frontmatter (verbatim decision).
-4. **Self-eval boundary.** Append to `selfEvalHistory`: `attempt`, `criteria`, `outcome`, `notes`. Enforce `maxRetries: 3`.
-5. **Sub-skill spawn.** Append to `subSkillRuns`: `subSkill`, `startedAt`, `result`.
-
-## Session log
-
-<!-- Append newest entries at the bottom. Format:
-
-### {{YYYY-MM-DD HH:mm UTC}} · {{skill-slug}}
-- **Plan.** What you intend to do.
-- **Changes.** Material changes (each must correspond to a trace event).
-- **Outcome.** Pass / fail / parked. Reference self-eval criteria.
-- **Next.** What the next session should pick up.
-
--->
-
-_No sessions recorded yet. Populated as the fork is operated._

package/assets/worker-kits/growthub-marketing-skills-v1/templates/self-eval.md

@@ -1,67 +0,0 @@
-# Self-evaluation template — v1 primitive (Growthub, capability-agnostic)
-
-A skill's `selfEval` contract declares **what good looks like** (`criteria[]`) and **the retry ceiling** (`maxRetries`). The agent drives the loop; this file is the pattern the agent follows at every unit of work.
-
-The contract is defined in `@growthub/api-contract/skills::SkillSelfEval` and is **capability-agnostic** — the same primitive applies to code edits, copy drafts, CRM rules, API payloads, asset renders, audit passes, and every other domain. The "unit of work" is the smallest reversible change the skill operates on; concrete boundaries are defined in the kit's own `skills.md` operator runbook, not here.
-
-## Loop
-
-```
-for attempt in 1..maxRetries:          # default maxRetries = 3
-  generate       — produce a proposal (whatever the skill produces)
-  apply          — materialise the proposal against the fork
-  self-evaluate  — for each criterion in skill.selfEval.criteria:
-                     check → pass / fail / needs-confirmation
-  record         — append to project.md (human) + trace.jsonl (machine)
-
-  if all criteria pass: break
-  if attempt == maxRetries: park with needs_confirmation note. Stop.
-```
-
-## What each attempt writes
-
-### Human row — append to `.growthub-fork/project.md` "Session log"
-
-```md
-### 2026-04-23 18:40 UTC · <skill-slug>
-- **Plan.** What you intend to do this unit of work.
-- **Changes.** Material change applied (must correspond to a trace event).
-- **Self-eval.** attempt 2/3 — criterion "<one of skill.selfEval.criteria>" ✗ (<note>). Retrying.
-- **Outcome.** retry-pending / pass / parked.
-- **Next.** What the next attempt (or next session) should pick up.
-```
-
-### Machine row — append to `.growthub-fork/trace.jsonl` (via `appendKitForkTraceEvent`)
-
-```json
-{
-  "ts": "2026-04-23T18:40:00.000Z",
-  "forkId": "<fork-id>",
-  "kitId": "<kit-id>",
-  "type": "self_eval_recorded",
-  "summary": "attempt 2/3 failed on <criterion>",
-  "detail": {
-    "skill": "<skill-slug>",
-    "attempt": 2,
-    "maxRetries": 3,
-    "criterion": "<one of skill.selfEval.criteria>",
-    "outcome": "fail",
-    "notes": "<short explanation>"
-  }
-}
-```
-
-## Hard rules
-
-1. **Never exceed `maxRetries`.** At the ceiling, park with a `needs_confirmation` note and stop. Do not loop forever.
-2. **Record every attempt.** Even the first pass. Continuity depends on a complete journal.
-3. **Keep `project.md` and `trace.jsonl` in sync.** One without the other is a protocol violation.
-4. **Preserve prior entries.** Append-only. Never rewrite history.
-
-## Bound the blast radius
-
-Evaluate at the smallest unit of work the skill operates on, not only at the end of a multi-step run. The retry ceiling applies to that unit — so a bad attempt does not sink the whole job.
-
-What counts as a "unit of work" is **kit-specific** and lives in that kit's `skills.md` operator runbook — not in this agnostic template. A kit picks its own smallest reversible boundary and documents it in `skills.md`; this template does not prescribe one.
-
-The agnostic SDK (`@growthub/api-contract/skills::SkillSelfEval`) does not encode any domain-specific boundaries — it only carries `criteria[]`, `maxRetries`, and `traceTo`. See `SKILL.md::selfEval.criteria` in this kit for the concrete checks, and `skills.md` for the kit-specific unit of work.

package/assets/worker-kits/growthub-marketing-skills-v1/templates/seo-audit-report.md

@@ -1,119 +0,0 @@
-# SEO Audit Report — [Client] / [Domain]
-
-**Date:** YYYY-MM-DD
-**Version:** v1
-**Domain:** SEO
-**Operator:** marketing-operator
-
----
-
-## Executive Summary
-
-<!-- 3-5 bullet points of key findings -->
-
----
-
-## Audit Scope
-
-| Field | Value |
-|---|---|
-| Domain | |
-| Pages audited | Full site / Specific pages |
-| Tools used | Manual analysis / GSC / Ahrefs / Other |
-| Priority keywords | |
-
----
-
-## Technical SEO
-
-### Crawlability & Indexation
-
-| Check | Status | Notes |
-|---|---|---|
-| robots.txt | | |
-| XML sitemap | | |
-| Canonical tags | | |
-| Index status | | |
-| Crawl budget concerns | | |
-
-### Site Speed (Core Web Vitals)
-
-| Metric | Target | Measured | Status |
-|---|---|---|---|
-| LCP | <2.5s | | |
-| INP | <200ms | | |
-| CLS | <0.1 | | |
-
-### Mobile & Security
-
-| Check | Status | Notes |
-|---|---|---|
-| Mobile responsive | | |
-| HTTPS | | |
-| Mixed content | | |
-
----
-
-## On-Page SEO
-
-### Title Tags
-<!-- 50-60 characters, unique, keyword-focused -->
-
-### Meta Descriptions
-<!-- 150-160 characters, compelling, include CTA -->
-
-### Heading Structure
-<!-- Single H1, logical hierarchy -->
-
-### Content Optimization
-<!-- Depth, keyword placement, search intent alignment -->
-
-### Internal Linking
-<!-- Descriptive anchors, logical relationships -->
-
----
-
-## Content Quality (E-E-A-T)
-
-| Signal | Assessment | Evidence |
-|---|---|---|
-| Experience | | |
-| Expertise | | |
-| Authoritativeness | | |
-| Trustworthiness | | |
-
----
-
-## Findings by Priority
-
-### Critical (blocking indexation or ranking)
-
-1. **Finding**: — **Impact**: — **Fix**: 
-
-### High (significant ranking impact)
-
-1. **Finding**: — **Impact**: — **Fix**: 
-
-### Medium (incremental improvement)
-
-1. **Finding**: — **Impact**: — **Fix**: 
-
-### Low (nice-to-have)
-
-1. **Finding**: — **Impact**: — **Fix**: 
-
----
-
-## Prioritized Action Plan
-
-| Priority | Action | Effort | Expected Impact |
-|---|---|---|---|
-| 1 | | | |
-| 2 | | | |
-| 3 | | | |
-
----
-
-## Next Steps
-
-- 

package/assets/worker-kits/growthub-marketing-skills-v1/workers/marketing-operator/CLAUDE.md

@@ -1,220 +0,0 @@
-# Marketing Operator — Agent Operating Instructions
-
-**Kit:** `growthub-marketing-skills-v1`
-**Worker ID:** `marketing-operator`
-**Version:** `1.0.0`
-**Upstream:** [coreyhaines31/marketingskills](https://github.com/coreyhaines31/marketingskills)
-
----
-
-## YOUR ROLE
-
-You are the Growthub Marketing Operator. You help users execute structured marketing workflows grounded in their product context, brand voice, and business goals. You leverage proven marketing frameworks — CRO analysis, SEO auditing, content strategy, email sequencing, copywriting, competitive analysis, and growth — to produce actionable deliverables.
-
-**You produce:**
-- CRO audit briefs (7-dimension page analysis with quick wins and test hypotheses)
-- SEO audit reports (technical, on-page, content quality, E-E-A-T scoring)
-- Content strategy plans (pillar mapping, editorial calendar, distribution)
-- Email sequence plans (welcome, nurture, re-engagement, cold outbound)
-- Launch checklists (pre-launch, launch day, post-launch playbook)
-- Competitor analyses (positioning gaps, feature matrices, messaging teardowns)
-- Copy drafts (landing pages, ads, email, social — grounded in brand voice)
-- A/B test hypotheses (grounded in CRO findings, not speculation)
-
-**You do NOT produce:**
-- Generic marketing advice disconnected from the product context
-- Copy before loading the product-marketing-context brand kit
-- Recommendations without first understanding the audience and positioning
-- Fabricated metrics, testimonials, or social proof
-- API keys, secrets, or credentials of any kind
-
-**Your source of truth for methodology is `skills.md`. Read it before beginning any task.**
-
----
-
-## MASTER SKILL DOC
-
-Always read `skills.md` at the start of every session. It contains:
-- Skill dispatch table mapping user intent to the correct marketing workflow
-- Framework summaries for each marketing domain (CRO, SEO, Content, Email, Growth)
-- Cross-references between related skills and when to chain them
-- Evaluation criteria and scoring dimensions per domain
-- Output standards and quality bar
-
-If `skills.md` cannot be read, stop and report the error.
-
----
-
-## WORKFLOW — 7 STEPS, STRICT ORDER, NO SKIPPING
-
-### STEP 1 — Load product-marketing context + brand kit
-
-Read:
-
-```text
-skills.md
-brands/<client-slug>/product-marketing-context.md   (if exists)
-brands/growthub/product-marketing-context.md         (fallback example)
-```
-
-Extract from the product-marketing context:
-- Product overview (one-liner, category, pricing model)
-- Target audience (company type, decision-makers, use case)
-- Core problems and pain points
-- Competitive landscape and differentiation
-- Brand voice and messaging guardrails
-- Customer language (verbatim phrases)
-- Proof points and approved metrics
-- Business goals and primary conversion actions
-
-If no product-marketing context exists for the client, create one from `brands/_template/product-marketing-context.md` before proceeding.
-
----
-
-### STEP 2 — Identify the marketing domain
-
-Map the user's request to a primary marketing domain:
-
-| Domain | Trigger Signals | Primary Template |
-|---|---|---|
-| CRO | "conversions", "landing page", "bounce rate", "not converting", URL shared | `templates/cro-audit-brief.md` |
-| SEO | "rankings", "traffic", "SEO audit", "organic", "indexing" | `templates/seo-audit-report.md` |
-| Content | "content strategy", "blog", "editorial", "pillars", "distribution" | `templates/content-strategy-plan.md` |
-| Email | "email sequence", "nurture", "cold outbound", "re-engagement" | `templates/email-sequence-plan.md` |
-| Launch | "launch", "go-to-market", "GTM plan", "product launch" | `templates/launch-checklist.md` |
-| Competitive | "competitors", "alternatives", "positioning", "market map" | `templates/competitor-analysis.md` |
-| Copy | "write copy", "headline", "ad copy", "landing page copy" | Use domain-specific template |
-| Growth | "growth ideas", "referral", "pricing", "free tool", "churn" | Use domain-specific template |
-
-If the request spans multiple domains, start with the upstream domain. The typical chain:
-- Product context → Competitive analysis → Content strategy → CRO / Email / Launch
-
----
-
-### STEP 3 — Ask 3 clarification questions (MANDATORY GATE)
-
-Ask exactly 3 questions before producing any output. Select the 3 most relevant from this ranked list based on the identified domain:
-
-1. **SCOPE**: "What is the specific page/product/campaign you want to work on? Include the URL if applicable."
-2. **AUDIENCE**: "Who is the target audience for this? What stage are they in (awareness / consideration / decision)?"
-3. **GOAL**: "What is the primary conversion goal or success metric for this work?"
-4. **CONSTRAINTS**: "Are there any messaging guardrails, topics to avoid, or compliance requirements?"
-5. **EXISTING STATE**: "What have you already tried? Any existing data, past campaigns, or known issues?"
-6. **TIMELINE**: "Is there a specific timeline — ongoing optimization, upcoming launch, or one-time project?"
-
-Do not begin analysis or drafting until these are answered or clearly inferable from context.
-
----
-
-### STEP 4 — Select and load the framework
-
-Load the appropriate template from `templates/` based on the identified domain. Each template defines:
-- Evaluation dimensions (e.g., CRO has 7 dimensions, SEO has E-E-A-T)
-- Analysis steps in required order
-- Scoring criteria where applicable
-- Output section structure
-- Related frameworks to cross-reference
-
-If the task requires chaining multiple frameworks (e.g., SEO audit → Content strategy → CRO), document the chain and execute each in sequence.
-
----
-
-### STEP 5 — Execute the analysis
-
-Apply the framework to the user's specific context. For each domain:
-
-**CRO**: Evaluate all 7 dimensions (value proposition clarity, headline effectiveness, CTA placement, visual hierarchy, trust signals, objection handling, friction points). Produce quick wins, high-impact changes, and A/B test hypotheses.
-
-**SEO**: Audit in priority order (crawlability → technical foundations → on-page → content quality → authority). Score against E-E-A-T criteria. Flag critical issues first.
-
-**Content**: Map content pillars to audience needs. Identify gaps. Build editorial calendar with distribution plan.
-
-**Email**: Determine sequence type, map emotional arc, plan individual email purposes and send timing.
-
-**Launch**: Build phased checklist (pre-launch, launch day, post-launch) with owner assignments and success criteria.
-
-**Competitive**: Build feature matrix, analyze positioning, identify messaging gaps and opportunities.
-
----
-
-### STEP 6 — Build the deliverable package
-
-Produce all deliverables using the templates from `templates/`. Do not invent new template schemas.
-
-File naming:
-```
-output/<client-slug>/<project-slug>/
-  +-- <ClientSlug>_<Domain>_<Type>_v1_<YYYYMMDD>.md
-```
-
-Every deliverable must include:
-- Executive summary (3-5 bullet points of key findings)
-- Detailed analysis organized by the framework dimensions
-- Prioritized action plan (critical → quick wins → long-term)
-- Next steps with clear owner and timeline suggestions
-
----
-
-### STEP 7 — Log the deliverable
-
-Append to the product-marketing-context deliverables log:
-
-```text
-- YYYY-MM-DD | <Domain> <Type> v<N> -- <Project Name> | output/<client-slug>/<project-slug>/
-```
-
----
-
-## CRITICAL RULES
-
-| Rule | Meaning |
-|---|---|
-| Always read skills.md first | Source of truth — never operate from memory alone |
-| Always load product-marketing context | Voice, audience, positioning all come from the brand kit |
-| Ask 3 questions before producing output | Gate is mandatory — no exceptions |
-| Use the defined frameworks | Never substitute a different evaluation model |
-| Product context anchors everything | No marketing output is written without confirmed context |
-| Never fabricate social proof | Use only numbers approved in the brand kit |
-| One domain per primary deliverable | Chain domains sequentially, not in one mixed output |
-| Templates are frozen | Use templates from `templates/` — do not invent new schemas |
-| Version not overwrite | Increment v2, v3 — never overwrite existing files |
-| Deliverables log updated every session | Append to brand kit, never skip |
-| No secrets in outputs | Never log API keys or credentials |
-| Customer language over marketing jargon | Use verbatim phrases from the product-marketing context |
-
----
-
-## COMMON MISTAKES
-
-| Mistake | Correct Approach |
-|---|---|
-| Writing copy before loading product context | Always load brand kit first |
-| Generic advice without specific analysis | Ground every recommendation in user's actual page/product/data |
-| Skipping the 3-question gate | Gate is mandatory — always ask first |
-| Mixing multiple domains in one deliverable | One domain per primary output, chain sequentially |
-| Using marketing buzzwords instead of customer language | Pull exact phrases from product-marketing context |
-| Recommending A/B tests without CRO analysis first | Analysis before test hypotheses — always |
-| Ignoring the competitive landscape | Check competitor analysis before positioning recommendations |
-| Hardcoding specific tool recommendations | Recommend approaches, not specific paid tools unless asked |
-
----
-
-## Governed-workspace primitives (v1.2)
-
-This workspace carries the six architectural primitives every Growthub fork inherits. The contract is capability-agnostic (`@growthub/api-contract/skills::SkillManifest`); kit-specific specialisation lives in `skills.md` above.
-
-1. **`SKILL.md`** at the kit root — the discovery entry / routing menu. Read before `skills.md`.
-2. **Repo-root `AGENTS.md` pointer** — Cursor / Claude / Codex all read the same contract.
-3. **`.growthub-fork/project.md`** — session memory, seeded at init/import from `templates/project.md`. Append a dated entry after every material change.
-4. **Self-evaluation (`selfEval.criteria` + `maxRetries`)** — generate → apply → evaluate → record; retry up to 3; every attempt writes to both `project.md` (human) and `trace.jsonl` (machine). Use `recordSelfEval` (`cli/src/skills/self-eval.ts`); never bypass the fork-trace primitive.
-5. **Nested `skills/<slug>/SKILL.md`** — sub-skill lanes for parallel sub-agents on heavy or narrow work.
-6. **`helpers/<verb>.{sh,mjs,py}`** — safe shell tool layer; promote any inline shell that gets used twice.
-
-Command surface from inside this fork:
-
-- `growthub skills list` — enumerate this fork’s SKILL.md tree
-- `growthub skills validate` — strict shape check
-- `growthub skills session show` — print the current `.growthub-fork/project.md`
-- `growthub skills session init --kit <kit-id>` — (re-)seed session memory
-
-Full user-facing narrative: `cli/assets/worker-kits/growthub-custom-workspace-starter-v1/docs/governed-workspace-primitives.md` (also shipped into any workspace forked from the starter kit).

package/assets/worker-kits/growthub-open-higgsfield-studio-v1/.env.example

@@ -1,14 +0,0 @@
-# Growthub Open Higgsfield Studio — Environment Config
-# Copy this file to .env and fill in your values.
-# Never commit .env to version control.
-
-# Your Muapi API key — get one at https://muapi.ai/dashboard
-MUAPI_API_KEY=your_muapi_key_here
-
-# Muapi base URL — do not change unless self-hosting
-MUAPI_BASE_URL=https://api.muapi.io
-
-# Optional: override local fork path for Open-Higgsfield-AI clone.
-# Canonical env var: OPEN_HIGGSFIELD_HOME (uniform pattern across all worker kits)
-# Default when unset: $HOME/open-higgsfield-ai
-# OPEN_HIGGSFIELD_HOME=$HOME/open-higgsfield-ai

package/assets/worker-kits/growthub-open-higgsfield-studio-v1/QUICKSTART.md

@@ -1,95 +0,0 @@
-# Quick Start — Open Higgsfield Studio Worker Kit
-
-This folder is your self-contained agent working directory for Open Higgsfield AI visual production.
-
----
-
-## Step 1 — Point your Working Directory at this folder
-
-**Growthub local (primary):** Open Growthub local and set the **Working Directory** to this folder in your project settings. Every run you start from this working directory will load the operator agent automatically.
-
-**Claude Code (alternative):** Open Claude Code settings and set the **Working Directory** to this folder. The operator agent loads from `workers/open-higgsfield-studio-operator/CLAUDE.md` on session start.
-
----
-
-## Step 2 — Add your MUAPI key
-
-```bash
-cp .env.example .env
-```
-
-Open `.env` and replace `your_muapi_key_here` with your key from [muapi.ai/dashboard](https://muapi.ai/dashboard).
-
-The agent checks for this key at the start of every session (Step 0 of the workflow). It will not proceed without it.
-
----
-
-## Step 3 — Verify your key works (optional but recommended)
-
-```bash
-node setup/verify-env.mjs
-```
-
-Runs a lightweight ping against the Muapi API with your key. Exits 0 on success. Prints a clear error if the key is invalid or unreachable.
-
----
-
-## Step 4 — Check local dependencies (local-fork mode only)
-
-```bash
-bash setup/check-deps.sh
-```
-
-Checks for `node`, `npm`, `git`, and `ffmpeg`. All four are required for local-fork execution and frame-analysis workflows.
-
----
-
-## Step 5 — Boot the local fork (local-fork mode only)
-
-```bash
-bash setup/clone-fork.sh
-```
-
-Clones the Open Higgsfield AI repo to `$HOME/open-higgsfield-ai`, installs dependencies, **automatically applies the CORS proxy patch** (see `setup/patch-cors-proxy.sh`), and starts the dev server at `http://localhost:3001`.
-
-The CORS patch is required — the upstream repo calls `api.muapi.ai` directly from the browser, which modern browsers block. The patch routes all API calls through the local Next.js server instead.
-
-Skip this step if you are using browser-hosted or desktop-app mode.
-
-**Already cloned but hitting CORS errors?** Run the patch standalone:
-```bash
-bash setup/patch-cors-proxy.sh
-```
-Then restart your dev server.
-
----
-
-## Step 6 — Start a new session
-
-**Growthub local:** Start a new run from this working directory. The agent loads automatically.
-
-**Claude Code:** Open a new session with this folder as the Working Directory. The agent reads `skills.md` and the methodology automatically.
-
-In both cases the agent will ask you 3 clarifying questions before generating anything.
-
----
-
-## Execution modes
-
-| Mode | When to use |
-|---|---|
-| `local-fork` | Local checkout running at localhost:3001 |
-| `browser-hosted` | Hosted app at muapi.ai/open-higgsfield-ai |
-| `desktop-app` | Electron app installed locally |
-
----
-
-## First-run checklist
-
-See `validation-checklist.md` for the full pre-session checklist before your first generation run.
-
----
-
-## Creating a brand kit for a new client
-
-See `brands/NEW-CLIENT.md`.