qualia-framework 2.6.0 → 3.2.0

package/framework/skills/zoho-workflow/SKILL.md

@@ -1,51 +0,0 @@
----
-name: zoho-workflow
-description: Zoho Invoice and Mail operations - create invoices, send emails, manage contacts. Use when Fawzi mentions invoicing, email, or Zoho.
-tags: [zoho, invoice, email, billing, crm]
----
-
-# Zoho Workflow
-
-
-## Zoho Invoice
-
-- Create, edit, send, and void invoices
-- List and search invoices by client, status, date
-- Manage items, taxes, contacts, and expenses
-- Mark invoices as sent/paid, send payment reminders
-- Generate invoice PDFs and email them to clients
-- Create recurring invoices and credit notes
-- When Fawzi says "invoice [client]" — create the full invoice, don't just explain how
-- Default sender org: Qualia Solutions
-
-## Zoho Mail
-
-- Read inbox, sent, drafts, and folder contents
-- Send emails and reply to threads
-- Move, label, and organize messages
-- Search emails by sender, subject, date
-- When Fawzi says "email [someone]" or "check inbox" — do it directly
-- Use Fawzi's primary Zoho Mail account
-
-## Email Formatting Rules (MANDATORY)
-
-- Always append Fawzi's signature at the bottom of every email
-- Read signature HTML from `~/.claude/knowledge/email-signature.html`
-- Never use dashes (---) or horizontal separators
-- Never use emojis
-- Professional, direct tone
-- Keep it concise and action-oriented
-
-## General Rules
-
-- Always act, don't just describe. Execute operations directly.
-- Fetch the organization ID first if needed (use the list/get org tools)
-- If a tool call fails, debug it — check params, retry with fixes
-
-## Trigger Phrases
-
-- "invoice [client]" → Create and send invoice
-- "email [someone]" → Compose and send email
-- "check inbox" → Read inbox
-- "send reminder" → Payment reminder
-- "create contact" → New Zoho contact

package/framework/statusline-command.sh

@@ -1,117 +0,0 @@
-#!/bin/bash
-# Qualia statusline — teal-branded, compact, informative
-# Layout: ◆ dir  branch [status] │ phase │ model ━━━━ 23%
-
-input=$(cat)
-
-USED_PCT=$(echo "$input" | jq -r '.context_window.used_percentage // empty')
-MODEL=$(echo "$input" | jq -r '.model.display_name')
-CWD=$(echo "$input" | jq -r '.workspace.current_dir')
-
-[ -z "$USED_PCT" ] && exit 0
-
-USED_INT=$(printf '%.0f' "$USED_PCT")
-
-# Directory shortening (last 2 segments max)
-DIR="$CWD"
-DIR="${DIR/#$HOME/\~}"
-DEPTH=$(echo "$DIR" | tr -cd '/' | wc -c)
-if [ "$DEPTH" -gt 2 ]; then
-  DIR=$(echo "$DIR" | rev | cut -d'/' -f1-2 | rev)
-  DIR="…/$DIR"
-fi
-
-# ── Colors ──
-T='\033[38;2;0;188;175m'         # teal
-TB='\033[38;2;45;226;210m'       # teal bright
-TD='\033[38;2;0;120;112m'        # teal dim
-W='\033[38;2;220;225;230m'       # white
-G='\033[38;2;70;78;88m'          # gray
-GR='\033[38;2;52;211;153m'       # green
-Y='\033[38;2;234;179;8m'         # yellow
-R='\033[38;2;239;68;68m'         # red
-P='\033[38;2;189;147;249m'       # purple
-X='\033[0m'                      # reset
-
-# Context bar color
-if [ "$USED_INT" -ge 70 ]; then CB="$R"
-elif [ "$USED_INT" -ge 50 ]; then CB="$Y"
-else CB="$T"; fi
-
-# ── Project + phase detection ──
-PROJECT=""
-PHASE=""
-
-if [ -f "$CWD/.planning/STATE.md" ]; then
-  PROJECT=$(grep -m1 "^Project:" "$CWD/.planning/STATE.md" 2>/dev/null | sed 's/^Project: *//')
-  # Get phase number only (e.g. "3 of 6") — not the full description
-  PHASE_RAW=$(grep -m1 "^Phase:" "$CWD/.planning/STATE.md" 2>/dev/null | sed 's/^Phase: *//')
-  if [ -n "$PHASE_RAW" ]; then
-    # Extract "N of M" pattern or just take first 12 chars
-    PHASE_SHORT=$(echo "$PHASE_RAW" | grep -oP '^\d+ of \d+' 2>/dev/null)
-    [ -z "$PHASE_SHORT" ] && PHASE_SHORT=$(echo "$PHASE_RAW" | head -c 12)
-    PHASE="$PHASE_SHORT"
-  fi
-fi
-
-[ -z "$PROJECT" ] && [ -f "$CWD/package.json" ] && PROJECT=$(node -e "try{console.log(require('$CWD/package.json').name||'')}catch(e){}" 2>/dev/null)
-
-# Git branch
-BRANCH=$(git -C "$CWD" --no-optional-locks branch --show-current 2>/dev/null)
-GIT_STATUS=""
-if [ -n "$BRANCH" ]; then
-  GIT_RAW=$(git -C "$CWD" --no-optional-locks status --porcelain 2>/dev/null | head -20)
-  if [ -n "$GIT_RAW" ]; then
-    M=$(echo "$GIT_RAW" | grep -c '^ M\|^MM\|^AM')
-    S=$(echo "$GIT_RAW" | grep -c '^[MARCD] ')
-    U=$(echo "$GIT_RAW" | grep -c '^??')
-    [ "$M" -gt 0 ] && GIT_STATUS+="!${M}"
-    [ "$S" -gt 0 ] && GIT_STATUS+="+${S}"
-    [ "$U" -gt 0 ] && GIT_STATUS+="?${U}"
-  fi
-fi
-
-# ── Context bar ──
-BAR_W=10
-FILLED=$(( USED_INT * BAR_W / 100 ))
-[ "$FILLED" -gt "$BAR_W" ] && FILLED=$BAR_W
-EMPTY=$(( BAR_W - FILLED ))
-BAR=""; for ((i=0; i<FILLED; i++)); do BAR+="━"; done
-EBAR=""; for ((i=0; i<EMPTY; i++)); do EBAR+="─"; done
-
-# ── Build statusline ──
-OUT=""
-
-# ◆ brand mark
-OUT+="${TB}◆${X} "
-
-# Directory (teal)
-OUT+="${T}${DIR}${X}"
-
-# Git branch (purple, compact)
-if [ -n "$BRANCH" ]; then
-  OUT+=" ${P}${BRANCH}${X}"
-  [ -n "$GIT_STATUS" ] && OUT+="${Y}[${GIT_STATUS}]${X}"
-fi
-
-# Separator
-OUT+=" ${G}│${X} "
-
-# Qualia mode + phase (teal, the important bit)
-if [ -n "$PROJECT" ]; then
-  OUT+="${TB}${PROJECT}${X}"
-  [ -n "$PHASE" ] && OUT+=" ${TD}p${PHASE}${X}"
-elif [ -n "$PHASE" ]; then
-  OUT+="${T}p${PHASE}${X}"
-fi
-
-# If neither project nor phase, show "ad-hoc"
-[ -z "$PROJECT" ] && [ -z "$PHASE" ] && OUT+="${TD}ad-hoc${X}"
-
-# Separator + model (compact)
-OUT+=" ${G}│${X} ${G}${MODEL}${X}"
-
-# Context bar
-OUT+=" ${CB}${BAR}${G}${EBAR}${X} ${CB}${USED_INT}%%${X}"
-
-printf "$OUT"

package/framework/teams/default/inboxes/plan-04.json

@@ -1,9 +0,0 @@
-[
-  {
-    "from": "team-lead",
-    "text": "Checkpoint approved. All verification passed:\n- Server boots clean, 96 permissions cached\n- All 9 Phase 1.4 endpoints return 401 unauthenticated (tested with /api/v1/ prefix)\n- Health endpoint returns 200\n- pnpm check-types: 5/5 workspaces pass, 0 errors\n- Route ordering confirmed: /mine before /:claimId in startup logs\n\nContinue to create SUMMARY.md and update STATE.md.",
-    "summary": "Approve checkpoint, continue SUMMARY",
-    "timestamp": "2026-03-22T01:22:15.460Z",
-    "read": false
-  }
-]

package/framework/teams/review-team.md

@@ -1,75 +0,0 @@
-# Review Team
-
-> Five specialist reviewers analyze code in parallel, results synthesized into unified report.
-
-## Agents
-
-- **code-simplicity-reviewer**
-  - subagent_type: code-simplicity-reviewer
-  - role: Identify unnecessary complexity, premature abstractions, YAGNI violations, over-engineering
-  - focus: Code structure, abstractions, function complexity, dead code
-
-- **performance-oracle**
-  - subagent_type: performance-oracle
-  - role: Identify performance bottlenecks, N+1 queries, memory leaks, missing indexes, bundle size issues
-  - focus: Database queries, API latency, rendering performance, caching opportunities
-
-- **kieran-typescript-reviewer**
-  - subagent_type: kieran-typescript-reviewer
-  - role: TypeScript quality — strict types, naming conventions, pattern adherence, type safety gaps
-  - focus: Type definitions, generics usage, any/unknown, null handling, naming
-
-- **security-auditor**
-  - subagent_type: security-auditor
-  - role: RLS policies, service_role exposure, auth patterns, input validation, secrets scanning, dependency vulnerabilities
-  - focus: Supabase security, auth flows, env var handling, XSS/injection prevention
-
-- **red-team-qa** (optional — spawn when reviewing auth, payments, or user input)
-  - subagent_type: red-team-qa
-  - role: Adversarial QA — actively tries to break the implementation via edge cases, error paths, boundary conditions
-  - focus: Permission bypasses, unexpected inputs, race conditions, error handling gaps
-
-## Pattern
-
-fan-out (all 5 parallel) → synthesize into REVIEW-REPORT.md
-
-## Shared Context
-
-- .planning/STATE.md — what was built, current phase
-- Recent git diff (last N commits relevant to the review scope)
-
-## Coordination Rules
-
-- Each reviewer produces findings independently — no coordination needed
-- Reviewers are read-only — they analyze and report, they don't fix
-- Findings should include file:line references
-- Each reviewer rates findings: CRITICAL / HIGH / MEDIUM / LOW
-
-## Output
-
-REVIEW-REPORT.md in current directory with sections:
-
-```markdown
-# Review Report
-
-## Summary
-{Overall assessment — 1-2 sentences}
-
-## Simplicity Review
-{From code-simplicity-reviewer}
-
-## Performance Review
-{From performance-oracle}
-
-## TypeScript Quality Review
-{From kieran-typescript-reviewer}
-
-## Security Review
-{From security-auditor}
-
-## Action Items
-| # | Severity | Finding | File:Line | Reviewer |
-|---|----------|---------|-----------|----------|
-| 1 | Critical | ... | ... | ... |
-| 2 | Warning | ... | ... | ... |
-```

package/framework/teams/ship-team.md

@@ -1,86 +0,0 @@
-# Ship Team
-
-> Quality gate → Deploy → Verify. Pipeline pattern — abort if any step fails.
-
-## Agents
-
-- **quality-gate**
-  - subagent_type: test-agent
-  - role: Run tsc, eslint, build. Ensure no type errors, lint violations, or build failures.
-  - commands: |
-    npx tsc --noEmit
-    npx next lint (or eslint .)
-    npm run build (or next build)
-  - abort_on_fail: true
-
-- **deploy**
-  - subagent_type: general-purpose
-  - role: Commit staged changes, push to remote, deploy to hosting platform
-  - commands: |
-    git add -A && git commit (if uncommitted changes)
-    git push origin {branch}
-    vercel --prod (default) OR wrangler deploy (if armenius)
-  - abort_on_fail: true
-
-- **verify**
-  - subagent_type: test-agent
-  - role: Run 6-check post-deploy verification against production URL
-  - checks: |
-    1. HTTP 200 — homepage loads
-    2. Auth flow — login/signup endpoint responds
-    3. Console errors — no critical JS errors
-    4. API latency — key endpoints < 500ms
-    5. SSL — valid certificate
-    6. Build artifacts — no source maps exposed
-  - abort_on_fail: false (report issues but don't rollback)
-
-## Pattern
-
-pipeline: quality-gate → deploy → verify
-
-Each step must succeed before the next begins. If quality-gate fails, deployment is blocked. If deploy fails, verification is skipped.
-
-## Shared Context
-
-- ~/.claude/knowledge/qualia-context.md — project inventory, deploy commands, Supabase refs
-- .planning/STATE.md — current project state
-- Project's local CLAUDE.md — project-specific deploy config
-
-## Coordination Rules
-
-- quality-gate runs ALL checks before passing — partial pass is a fail
-- deploy detects hosting platform from project context (Vercel default, Cloudflare for armenius)
-- verify uses the production URL from deploy output
-- If Supabase project: deploy also runs `supabase db push` if pending migrations exist
-
-## Output
-
-SHIP-REPORT.md in current directory:
-
-```markdown
-# Ship Report
-
-**Date:** {date}
-**Branch:** {branch}
-**Deploy URL:** {url}
-
-## Quality Gate
-- tsc: ✓ / ✗ ({error count})
-- lint: ✓ / ✗ ({warning count})
-- build: ✓ / ✗ ({duration})
-
-## Deployment
-- Platform: Vercel / Cloudflare
-- URL: {production url}
-- Commit: {sha}
-
-## Verification
-| Check | Status | Details |
-|-------|--------|---------|
-| HTTP 200 | ✓/✗ | {status code} |
-| Auth flow | ✓/✗ | {details} |
-| Console errors | ✓/✗ | {count} |
-| API latency | ✓/✗ | {ms} |
-| SSL | ✓/✗ | {expiry} |
-| Source maps | ✓/✗ | {exposed?} |
-```

package/profiles/fawzi.json

@@ -1,16 +0,0 @@
-{
-  "code": "QS-FAWZI-2024",
-  "name": "Fawzi",
-  "fullName": "Fawzi Goussous",
-  "role": "OWNER",
-  "since": "2024",
-  "location": "Nicosia, Cyprus",
-  "type": "founder",
-  "language": "ar-en",
-  "permissions": {
-    "canDeploy": true,
-    "canModifyFramework": true,
-    "canAccessAllProjects": true,
-    "canApproveWork": true
-  }
-}

package/profiles/hasan.json

@@ -1,16 +0,0 @@
-{
-  "code": "QS-HASAN-2026",
-  "name": "Hasan",
-  "fullName": "Hasan",
-  "role": "DEVELOPER",
-  "since": "March 2026",
-  "location": "Cyprus",
-  "type": "part-time",
-  "language": "en",
-  "permissions": {
-    "canDeploy": false,
-    "canModifyFramework": false,
-    "canAccessAllProjects": false,
-    "canApproveWork": false
-  }
-}

package/profiles/moayad.json

@@ -1,16 +0,0 @@
-{
-  "code": "QS-MOAYAD-2025",
-  "name": "Moayad",
-  "fullName": "Moayad",
-  "role": "DEVELOPER",
-  "since": "December 2025",
-  "location": "Jordan",
-  "type": "full-time",
-  "language": "ar-en",
-  "permissions": {
-    "canDeploy": true,
-    "canModifyFramework": false,
-    "canAccessAllProjects": true,
-    "canApproveWork": false
-  }
-}

package/templates/CLAUDE-owner.md

@@ -1,52 +0,0 @@
-# CLAUDE.md — Qualia Solutions
-
-## Identity
-**Fawzi Goussous** — Founder, Qualia Solutions. Nicosia, Cyprus.
-
-- Stack: Next.js 16+, React 19, TypeScript, Supabase, Vercel, VAPI, ElevenLabs, Telnyx, Retell AI, OpenRouter
-- Partner: Jay | Team: Moayad (full-time, Jordan), Ahasan (part-time, Cyprus)
-
-## Role: OWNER
-
-Full authority over all projects, deployments, architecture, and client decisions.
-- Deploy directly to production
-- Make architectural decisions unilaterally
-- Access all Supabase projects and service role keys
-- Modify the Qualia framework (CLAUDE.md, skills, hooks)
-
-## Rules
-- Read before Write/Edit — no exceptions
-- Feature branches only — never commit to main/master
-- MVP first. Build only what's asked. No over-engineering.
-- Root cause on failures — no band-aids
-- `npx tsc --noEmit` after multi-file TS changes
-- Glob/Grep directly — no Task(Explore) unless 5+ rounds needed
-- For non-trivial work (multi-file changes, architectural decisions, unfamiliar codebases), confirm understanding before coding — quick tasks are exempt
-- See `rules/security.md` for auth, RLS, Zod, secrets rules
-- See `rules/frontend.md` for design standards
-- See `rules/deployment.md` for deploy checklist
-
-## Collaboration
-Collaborator, not executor. Speak up about bugs, simpler approaches, bad architecture.
-Be honest. Default to action. Never speculate on unread code. Say when blocked.
-- Direct, action-oriented, no fluff. Code > theory.
-- Arabic or English — match whatever language is used
-
-## Workflow
-- **MANDATORY FIRST ACTION**: On every session start, invoke the `qualia-start` skill before doing anything else. This is non-negotiable — do not wait for user input, do not skip it, do not just acknowledge the hook message. Actually invoke the skill using the Skill tool.
-- Subagents (Sonnet) for research. Opus for complex reasoning.
-- `/compact` at 60%. `/clear` between tasks. `/learn` after mistakes.
-
-## Qualia Mode (always active)
-These behaviors apply to ALL interactions:
-- **Frontend guard:** Read .planning/DESIGN.md before any frontend file changes
-- **Deploy guard:** Check .planning/REVIEW.md freshness before any deploy command (run /qualia-review to generate)
-- **Intent verification:** Confirm before modifying 3+ files in one response
-- **Task-type detection:** Auto-load relevant skill patterns based on what's being done
-- **Quality defaults:** Security rules, tsc checks, RLS consideration — always enforced
-
-## Compaction — ALWAYS preserve:
-Project path/name/ref, branch, modified files, decisions, test results, in-progress work, errors, Qualia phase/milestone state, Qualia mode active/inactive state, session digest context.
-
-## Learned Patterns & Gotchas
-See ~/.claude/knowledge/learned-patterns.md for full rules and project gotchas.

package/templates/CLAUDE.md.hbs

@@ -1,58 +0,0 @@
-# CLAUDE.md — {{role}} Profile
-
-## Identity
-**{{fullName}}** — {{roleTitle}} at Qualia Solutions. {{location}}.
-{{#if isOwner}}One-man dev shop. Websites, AI agents, voice agents, AI automation.
-- Direct, action-oriented, no fluff. Code > theory.{{/if}}
-{{#if isArabic}}- يعني اذا حكى عربي رد عربي، اذا انجليزي رد انجليزي، واذا خلط خلط معه{{/if}}
-- Stack: Next.js 16+, React 19, TypeScript, Supabase, Vercel, VAPI, ElevenLabs, Telnyx, Retell AI, OpenRouter
-
-## Role: {{role}}
-{{#if isOwner}}You are the founder. Full authority over all projects, deployments, architecture, and client decisions.
-- Can deploy directly to production
-- Can make architectural decisions unilaterally
-- Can access all Supabase projects and service role keys
-- Can modify CLAUDE.md, skills, hooks, and framework config
-- Can approve/reject employee work{{/if}}
-{{#if isDeveloper}}You are a developer at Qualia Solutions, working under Fawzi Goussous (founder).
-- Work on feature branches only — never push to main/master
-- Submit PRs for review before merging
-{{#if canDeploy}}- Can deploy to production with approval{{else}}- Do NOT deploy to production — Fawzi handles deploys{{/if}}
-{{#if canAccessAllProjects}}- Can access all assigned Supabase projects{{else}}- Access limited to assigned projects only{{/if}}
-- Cannot modify the Qualia framework (CLAUDE.md, skills, hooks)
-- Ask Fawzi when unsure about architecture decisions{{/if}}
-
-## Rules
-- Read before Write/Edit — no exceptions
-- Feature branches only — never commit to main/master
-- MVP first. Build only what's asked. No over-engineering.
-- Root cause on failures — no band-aids
-- `npx tsc --noEmit` after multi-file TS changes
-- Glob/Grep directly — no Task(Explore) unless 5+ rounds needed
-- For non-trivial work (multi-file changes, architectural decisions, unfamiliar codebases), confirm understanding before coding: "Here's what I understand: [summary]. Correct?" — quick tasks (typo, single-file, familiar pattern) are exempt
-- See `rules/security.md` for auth, RLS, Zod, secrets rules
-- See `rules/frontend.md` for design standards
-- See `rules/deployment.md` for deploy checklist
-
-## Collaboration
-Collaborator, not executor. Speak up about bugs, simpler approaches, bad architecture.
-Be honest. Default to action. Never speculate on unread code. Say when blocked.
-
-## Workflow
-- **MANDATORY FIRST ACTION**: On every session start, invoke the `qualia-start` skill before doing anything else. This is non-negotiable — do not wait for user input, do not skip it, do not just acknowledge the hook message. Actually invoke the skill using the Skill tool.
-- Subagents (Sonnet) for research. Opus for complex reasoning.
-- `/compact` at 60%. `/clear` between tasks. `/learn` after mistakes.
-
-## Qualia Mode (always active)
-These behaviors apply to ALL interactions:
-- **Frontend guard:** Read .planning/DESIGN.md before any frontend file changes
-- **Deploy guard:** Check .planning/REVIEW.md freshness before any deploy command (run /qualia-review to generate)
-- **Intent verification:** Confirm before modifying 3+ files in one response
-- **Task-type detection:** Auto-load relevant skill patterns based on what's being done
-- **Quality defaults:** Security rules, tsc checks, RLS consideration — always enforced
-
-## Compaction — ALWAYS preserve:
-Project path/name/ref, branch, modified files, decisions, test results, in-progress work, errors, Qualia phase/milestone state, Qualia mode active/inactive state, session digest context.
-
-## Learned Patterns & Gotchas
-See ~/.claude/knowledge/learned-patterns.md for full rules and project gotchas.

package/templates/env.claude.template

@@ -1,12 +0,0 @@
-#!/bin/bash
-# Qualia Solutions — Claude Code API Keys
-# Source this file in your shell profile: source ~/.claude/.env.claude
-# chmod 600 ~/.claude/.env.claude
-
-# Ask Fawzi for the keys you need for your assigned projects
-export FIRECRAWL_API_KEY=
-export SENTRY_ACCESS_TOKEN=
-export SUPABASE_ACCESS_TOKEN=
-export ELEVEN_API_KEY=
-export VAPI_TOKEN=
-export TELNYX_API_KEY=