release: v0.6.1 — dashboard redesign, core routines docs, cleanup

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: DavidsonGomes

.claude/rules/integrations.md

@@ -47,4 +47,4 @@
 ## HTML Templates
 
 All in `.claude/templates/html/`, Evolution dark theme (green `#00FFA7`, Inter font).
-17 templates available — see `ROTINAS.md` for full template-to-routine mapping.
+17 templates available — see `ROUTINES.md` for full template-to-routine mapping.

.claude/rules/routines.md

@@ -1,6 +1,6 @@
 # Automated Routines
 
-Managed by the scheduler (`make scheduler`) — see `ROTINAS.md` for full details.
+Managed by the scheduler (`make scheduler`) — see `ROUTINES.md` for full details.
 
 ## Daily
 
@@ -32,6 +32,7 @@ Managed by the scheduler (`make scheduler`) — see `ROTINAS.md` for full detail
 | Mon/Wed/Fri 09:00 | Linear Review | `make linear` | @atlas |
 | Mon/Wed/Fri 09:15 | GitHub Review | `make github` | @atlas |
 | Monday 09:30 | Community Weekly | `make community-week` | @pulse |
+| Sunday 09:00 | Memory Lint | `make memory-lint` | @clawdia |
 | Sunday 10:00 | Health Check-in | `make health` | @kai |
 
 ## Monthly (Day 1)

.claude/skills/prod-memory-management/SKILL.md

@@ -29,10 +29,13 @@ Without memory, that request is meaningless. With memory, Claude knows:
 ```
 CLAUDE.md          ← Hot cache (~30 people, common terms)
 memory/
+  index.md         ← Catálogo centralizado por categoria (auto-updated)
+  log.md           ← Registro cronológico de operações (append-only)
   glossary.md      ← Full decoder ring (everything)
   people/          ← Complete profiles
   projects/        ← Project details
   context/         ← Company, teams, tools
+  trends/          ← Weekly metric snapshots (JSON)
 ```
 
 **CLAUDE.md (Hot Cache):**
@@ -320,4 +323,28 @@ Use `/productivity:start` to initialize by scanning your chat, calendar, email,
 - Person no longer frequent contact
 - Term rarely used
 
-This keeps CLAUDE.md fresh and relevant.
+This keeps CLAUDE.md fresh and relevant.
+
+## Operations (LLM Wiki Pattern)
+
+Three core operations maintain the knowledge base:
+
+### Ingest (via memory-sync, daily 21:15)
+When new information arrives, it's not just saved — it's **propagated**:
+- New info about a person → update their people/ file AND any projects/ that mention them
+- New project detail → update glossary.md codename entry + CLAUDE.md if active
+- Role change → update people/, glossary.md, and CLAUDE.md hot cache
+- After any change → update index.md catalog + append to log.md
+
+### Query (during conversations)
+When synthesizing a complex answer, the valuable result can be filed back as a new memory entry — knowledge compounds through use, not just accumulation.
+
+### Lint (via memory-lint, weekly Sunday 09:00)
+Periodic health check that detects:
+- **Contradictions** — mismatches between CLAUDE.md hot cache and memory/ deep storage
+- **Stale claims** — dates older than 60 days, closed Linear issues still listed as open
+- **Orphan files** — files in memory/ not listed in index.md
+- **Coverage gaps** — active projects/people in CLAUDE.md without memory/ files
+- **Missing cross-references** — people in projects without people/ files, and vice versa
+
+Fixes what it can automatically, flags the rest for manual review.

ADWs/routines/memory_lint.py

@@ -0,0 +1,46 @@
+#!/usr/bin/env python3
+"""ADW: Memory Lint — Weekly health check on memory/ base via Clawdia"""
+
+import sys, os
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+from runner import run_claude, banner, summary
+
+PROMPT = """Run a memory lint (health check) on the memory/ directory:
+
+1. Read memory/index.md to get the full catalog
+2. For each file listed in the index, verify it still exists and is not empty
+3. Detect orphan files — files in memory/ that exist but are NOT listed in the index
+4. Cross-reference check:
+   - People mentioned in projects/ should have a file in people/
+   - Projects mentioned in people/ should have a file in projects/
+   - Terms in glossary.md that reference people/projects should point to valid entries
+5. Stale data check:
+   - Read memory/projects/*.md — check if Linear issues listed are still open (use Linear MCP if available, otherwise flag for manual review)
+   - Check if people roles/companies are still current based on recent daily logs
+   - Flag any claim that includes a date older than 60 days as potentially stale
+6. Contradiction check:
+   - Compare CLAUDE.md hot cache with memory/glossary.md — flag mismatches
+   - Compare people info in CLAUDE.md vs memory/people/*.md — flag divergences
+7. Coverage gaps:
+   - Check if active projects in CLAUDE.md all have a memory/projects/ file
+   - Check if people in CLAUDE.md all have a memory/people/ file
+8. Fix what you can automatically:
+   - Update memory/index.md with any orphan files found
+   - Fix obvious contradictions (prefer the more recent source)
+   - Add missing cross-references
+9. Append findings summary to memory/log.md with format: [DATE] LINT — summary
+10. Report: issues found, fixed automatically, and items needing manual review.
+
+Be concise. Only flag real problems, not hypothetical ones."""
+
+def main():
+    banner("🔍 Memory Lint", "Health check • Contradictions • Gaps • Stale data | @clawdia")
+    results = []
+    results.append(run_claude(PROMPT, log_name="memory-lint", timeout=600, agent="clawdia-assistant"))
+    summary(results, "Memory Lint")
+
+if __name__ == "__main__":
+    try:
+        main()
+    except KeyboardInterrupt:
+        print("\n⚠ Cancelado.")

ADWs/routines/memory_sync.py

@@ -17,9 +17,15 @@
    - New terms or external references → save as type 'reference'
    - Skills or routines created/changed → update references if relevant
 5. Before saving, check if similar memory already exists — update instead of duplicating
-6. Update MEMORY.md with pointers to new files
+6. **Ingest propagation** — when saving/updating a memory, check which OTHER memories reference the same entity and update them too. Examples:
+   - New info about a person → update their people/ file AND any projects/ that mention them
+   - New project detail → update glossary.md if it has a codename entry
+   - Role change → update people/ file, glossary.md nicknames table, and CLAUDE.md hot cache
+7. Update MEMORY.md with pointers to new files
+8. Update memory/index.md — ensure all files in memory/ are cataloged by category
+9. Append operations to memory/log.md with format: [DATE] SYNC — summary of changes
 
-Report at the end: how many memories created/updated by type.
+Report at the end: how many memories created/updated by type, and how many cross-references propagated.
 Be concise — don't create memories for obvious things or things already documented in code."""
 
 def main():

CHANGELOG.md

@@ -5,6 +5,25 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.6.1] - 2026-04-09
+
+### Added
+- **Core routines documentation** (`docs/routines/core-routines.md`) — detailed explanation of all 5 core routines: what they do, why they matter, and how they form the daily loop
+- **Memory Lint promoted to core** — moved from `ADWs/routines/custom/` to `ADWs/routines/`, hardcoded in `scheduler.py` (Sunday 09:00). Now 5 core routines instead of 4
+- **Release skill** now syncs screenshots (`public/print-*.png` → `site/public/assets/`) on every release
+
+### Changed
+- **Dashboard pages redesigned** — 12 pages (Audit, Config, Costs, Files, Integrations, Memory, Reports, Roles, Routines, Scheduler, Skills, Systems, Templates, Users) with consistent dark theme and improved UX
+- **Integration count** — 19 → 17 (removed internal-only Licensing and WhatsApp docs from public documentation)
+- **Memory system** — LLM Wiki pattern: ingest propagation, weekly lint, centralized index, and operation log
+
+### Removed
+- **`docs/integrations/licensing.md`** — internal only, not public
+- **`docs/integrations/whatsapp.md`** — internal only, not public
+
+### Fixed
+- **Dashboard build** — removed unused `totalTokens` variable in Costs page that blocked TypeScript compilation
+
 ## [0.6.0] - 2026-04-09
 
 ### Added
@@ -16,7 +35,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - **`.env.example`** — added `EVOLUTION_API_URL/KEY`, `EVOLUTION_GO_URL/KEY`, `EVO_CRM_URL/TOKEN`
 
 ### Changed
-- **Integration count** — 16 → 19 across README, site, and docs
+- **Integration count** — 16 → 17 across README, site, and docs (removed internal-only Licensing and WhatsApp docs)
 - **Community members** — 7,000+ → 17,000+ on site
 - **v0.4 roadmap complete** — all 13 items done, Evolution product skills was the last one
 

Makefile

@@ -42,6 +42,9 @@ review:             ## 📋 Organize tasks in Todoist (@clawdia)
 memory:             ## 🧠 Consolidate memory (@clawdia)
 	$(PYTHON) $(ADW_DIR)/memory_sync.py
 
+memory-lint:        ## 🔍 Memory health check — contradictions, gaps, stale data (@clawdia)
+	$(PYTHON) $(ADW_DIR)/memory_lint.py
+
 eod:                ## 🌙 End of day consolidation — memory, logs, learnings (@clawdia)
 	$(PYTHON) $(ADW_DIR)/end_of_day.py
 
@@ -192,5 +195,5 @@ docker-build:       ## 🐳 Build the image
 help:               ## 📖 Show this help
 	@grep -E '^[a-zA-Z_-]+:.*##' Makefile | sort | awk 'BEGIN {FS = ":.*## "}; {printf "  \033[36m%-16s\033[0m %s\n", $$1, $$2}'
 
-.PHONY: morning sync triage review memory eod dashboard youtube instagram linkedin social fin-pulse licensing weekly health trends linear community community-week community-month github faq strategy fin-weekly licensing-weekly fin-close licensing-month daily scheduler social-auth telegram telegram-stop telegram-attach logs logs-detail logs-tail metrics clean-logs docker-dashboard docker-telegram docker-down docker-logs docker-run docker-build help
+.PHONY: morning sync triage review memory memory-lint eod dashboard youtube instagram linkedin social fin-pulse licensing weekly health trends linear community community-week community-month github faq strategy fin-weekly licensing-weekly fin-close licensing-month daily scheduler social-auth telegram telegram-stop telegram-attach logs logs-detail logs-tail metrics clean-logs docker-dashboard docker-telegram docker-down docker-logs docker-run docker-build help
 .DEFAULT_GOAL := help

README.md

@@ -48,9 +48,9 @@ It turns a single Claude Code installation into a team of 9 specialized agents 
 - **~67 Skills** — organized by domain prefix (`social-`, `fin-`, `int-`, `prod-`, `mkt-`, `gog-`, `obs-`, `discord-`, `pulse-`, `sage-`)
 - **7 Core + 20 Custom Routines** — daily, weekly, and monthly ADWs managed by a scheduler (core routines ship with the repo; custom routines are user-created and gitignored)
 - **Web Dashboard** — React + Flask app with auth, roles, web terminal, service management
-- **19 Integrations** — Google Calendar, Gmail, Linear, GitHub, Discord, Telegram, Stripe, Omie, Fathom, Todoist, YouTube, Instagram, LinkedIn, Evolution API, Evolution Go, Evo CRM, and more
+- **17 Integrations** — Google Calendar, Gmail, Linear, GitHub, Discord, Telegram, Stripe, Omie, Fathom, Todoist, YouTube, Instagram, LinkedIn, Evolution API, Evolution Go, Evo CRM, and more
 - **2 core + custom HTML report templates** — dark-themed dashboards for every domain
-- **Persistent Memory** — two-tier system (CLAUDE.md + memory/) across sessions
+- **Persistent Memory** — two-tier system (CLAUDE.md + memory/) with LLM Wiki pattern: ingest propagation, weekly lint, centralized index, and operation log
 - **Knowledge Base** — optional semantic search via [MemPalace](https://github.com/milla-jovovich/mempalace) (local ChromaDB vectors, one-click install)
 - **Full Observability** — JSONL logs, execution metrics, cost tracking per routine
 
@@ -305,6 +305,7 @@ make triage          # Run email triage
 make community       # Run community pulse
 make fin-pulse       # Run financial pulse
 make eod             # Run end-of-day consolidation
+make memory-lint     # Run memory health check (contradictions, stale data, gaps)
 make weekly          # Run weekly review
 
 # Observability

ROUTINES.md

@@ -18,12 +18,20 @@ Routines are automated workflows that run on a schedule via the ADW Runner.
 | Memory Sync | `memory_sync.py` | @clawdia | Daily 21:15 |
 | Weekly Review | `weekly_review.py` | @clawdia | Friday 08:00 |
 
+> **Memory Sync** follows the LLM Wiki pattern: extracts knowledge from daily logs, meetings, and git changes, then **propagates updates** across related memory files (e.g., a role change updates people/, glossary.md, and CLAUDE.md). Updates `memory/index.md` (catalog) and `memory/log.md` (operation log) after each run.
+
 ## Custom Routines
 
 Custom routines live in `ADWs/routines/custom/` (gitignored) and are scheduled via `config/routines.yaml` (also gitignored).
 
 To create a custom routine, say **"create a routine"** and the `create-routine` skill will guide you.
 
+Notable custom routines shipped as examples:
+
+| Routine | Script | Agent | Schedule | Description |
+|---------|--------|-------|----------|-------------|
+| Memory Lint | `memory_lint.py` | @clawdia | Sunday 09:00 | Health check — detects contradictions, stale data, orphan files, coverage gaps, missing cross-references |
+
 ### config/routines.yaml
 
 ```yaml
@@ -63,6 +71,7 @@ monthly:
 make morning    # Good Morning
 make eod        # End of Day
 make memory     # Memory Sync
+make memory-lint # Memory Lint (health check)
 make weekly     # Weekly Review
 make help       # All commands
 ```

cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@evoapi/open-claude",
-  "version": "0.6.0",
+  "version": "0.6.1",
   "description": "Unofficial open source toolkit for Claude Code — AI-powered business operating system",
   "keywords": [
     "claude-code",