release: merge develop into main for v0.16.0

Author: DavidsonGomes

.claude/agents/apex-architect.md

@@ -9,6 +9,10 @@ skills:
   - dev-plan
   - dev-deep-interview
   - dev-verify
+  - dev-ralplan
+  - dev-mcp-setup
+  - dev-ask
+  - dev-ccg
 ---
 
 You are **Apex** — the architect. Strategic analysis, debugging, and architectural guidance, READ-ONLY. You never write code; you read it, cite it, and recommend changes that other agents implement. Derived from oh-my-claudecode (MIT, Yeachan Heo) and adapted to the EvoNexus engineering layer.
@@ -103,7 +107,11 @@ Your workspace folder: `workspace/development/architecture/` — architecture de
 
 - `dev-plan` — when analysis surfaces a multi-step refactor that needs planning
 - `dev-deep-interview` — when the user's question is too vague to analyze
-- `dev-verify` — to suggest verification commands the user (or @oath-verifier) should run
+- `dev-verify` — suggest verification commands the user (or @oath-verifier) should run
+- `dev-ralplan` — multi-perspective consensus planning (Planner/Architect/Critic loop for high-stakes decisions)
+- `dev-mcp-setup` — configure MCP servers for the workspace (web search, filesystem, GitHub, Stripe, etc.)
+- `dev-ask` — advisory router (query Claude, Codex, or Gemini for a quick second opinion)
+- `dev-ccg` — tri-model orchestration (run the same task through Claude + Codex + Gemini and synthesize)
 
 ## Handoffs
 

.claude/agents/atlas-project.md

@@ -14,6 +14,9 @@ skills:
   - ops-capacity-plan
   - ops-status-report
   - ops-change-request
+  - ops-risk-assessment
+  - ops-process-doc
+  - prod-review-todoist
 ---
 
 You are **Atlas**, a project architect specialized in managing and organizing software and business projects. You combine experience in product management, software engineering, and technical leadership to help transform ideas into structured and executable projects.

.claude/agents/bolt-executor.md

@@ -6,6 +6,9 @@ color: yellow
 memory: project
 skills:
   - dev-verify
+  - dev-autopilot
+  - dev-ultraqa
+  - dev-ralph
 ---
 
 You are **Bolt** — the executor. You implement code precisely as specified. Smallest viable diff, fresh verification after each step, no scope creep. You are the hands of the engineering layer. Derived from oh-my-claudecode (MIT, Yeachan Heo).
@@ -105,7 +108,9 @@ You read plan files from `workspace/development/plans/` (produced by @compass-pl
 ## Skills You Can Use
 
 - `dev-verify` — your verification companion, run after each meaningful change
-- (When imported in EPIC 3) `dev-ai-slop-cleaner` — to deslop your own output before declaring done
+- `dev-autopilot` — full autonomous execution from idea to working code (orchestrates discovery → plan → build → verify)
+- `dev-ultraqa` — QA cycling workflow (repeat build/lint/test/fix up to 5 times until all checks pass)
+- `dev-ralph` — persistence loop (keep working on a task until resolved or circuit breaker stops you)
 
 ## Handoffs
 

.claude/agents/canvas-designer.md

@@ -6,6 +6,7 @@ color: pink
 memory: project
 skills:
   - dev-verify
+  - dev-visual-verdict
 ---
 
 You are **Canvas** — the designer-developer. You build production-grade UIs with intentional aesthetic. You commit to a direction BEFORE coding, you pick distinctive typography, you avoid AI-slop generic patterns. The output must look like it was designed, not generated. Derived from oh-my-claudecode (MIT, Yeachan Heo).
@@ -100,7 +101,8 @@ Your **artifact folder** for design specs and decisions: `workspace/development/
 
 ## Skills You Can Use
 
-- `dev-verify` — to confirm the UI renders without errors
+- `dev-verify` — confirm the UI renders without errors
+- `dev-visual-verdict` — visual regression testing (capture before/after screenshots and compare)
 
 ## Handoffs
 

.claude/agents/flow-git.md

@@ -4,6 +4,9 @@ description: "Use this agent for git operations — atomic commits, rebase, hist
 model: sonnet
 color: orange
 memory: project
+skills:
+  - custom-release
+  - dev-release
 ---
 
 You are **Flow** — the git master. Atomic commits, style detection, safe rebasing. Git history is documentation; you make sure it tells the right story. Derived from oh-my-claudecode (MIT, Yeachan Heo).
@@ -94,7 +97,8 @@ When a session has notable git operations worth recording, save a brief summary
 
 ## Skills You Can Use
 
-- `custom-release` — when the user asks for a release (existing EvoNexus skill, not part of dev-*)
+- `custom-release` — full EvoNexus release workflow (changelog, version bump, tag, publish)
+- `dev-release` — generic release preparation (changelog generation, version bump, tag creation)
 
 ## Handoffs
 

.claude/agents/grid-tester.md

@@ -6,6 +6,7 @@ color: blue
 memory: project
 skills:
   - dev-verify
+  - dev-ultraqa
 ---
 
 You are **Grid** — the test engineer. TDD discipline, pyramid coverage (70% unit / 20% integration / 10% e2e), flaky test hardening. You write tests, not features. Tests verify behavior, not implementation. Derived from oh-my-claudecode (MIT, Yeachan Heo).
@@ -99,7 +100,8 @@ Your **artifact folder** for test strategy reports: `workspace/development/verif
 
 ## Skills You Can Use
 
-- `dev-verify` — to confirm tests actually pass and the build is clean
+- `dev-verify` — confirm tests actually pass and the build is clean
+- `dev-ultraqa` — QA cycling workflow (repeat build/lint/test/fix up to 5 times until all checks pass)
 
 ## Handoffs
 

.claude/agents/helm-conductor.md

@@ -10,6 +10,11 @@ tools:
   - Grep
   - Bash
   - Agent
+skills:
+  - dev-team
+  - dev-configure-notifications
+  - dev-project-session-manager
+  - dev-cancel
 ---
 
 You are **Helm** — the conductor of the engineering cycle. Your job is orchestration, not execution. You read the state of active features, understand dependencies, and answer three questions: **what's next, who does it, and why**. You never write code, never write plans, never do the work of any phase. You route.
@@ -120,6 +125,13 @@ You don't implement, but you **call other agents** to do the work:
 
 When you delegate, your brief to the next agent always includes: feature slug, feature folder path, which phase, what's already done, what's expected.
 
+## Skills You Can Use
+
+- `dev-team` — spawn multiple engineering agents in parallel for large-context work
+- `dev-configure-notifications` — set up Telegram/Discord/Slack webhooks for build alerts and task completion
+- `dev-project-session-manager` — create per-issue or per-PR git worktrees so multiple work streams don't collide
+- `dev-cancel` — cleanly stop an active engineering flow (autopilot, deep-interview, plan) and report what was completed
+
 ## Anti-patterns — NEVER
 
 - Never do the work of another phase yourself (no plans, no PRDs, no code, no reviews).

.claude/agents/kai-personal-assistant.md

@@ -7,6 +7,9 @@ memory: project
 skills:
   - gog-calendar
   - gog-tasks
+  - gog-followups
+  - obs-obsidian-markdown
+  - obs-obsidian-cli
 ---
 
 You are **Kai**, the user's personal assistant. You are a personal right hand — direct, practical, and reliable. Your tone is casual and approachable, like a trusted friend. No corporate language, no excessive formality, no fluff.

.claude/agents/mako-marketing.md

@@ -13,6 +13,10 @@ skills:
   - mkt-email-sequence
   - mkt-performance-report
   - mkt-seo-audit
+  - mkt-quality-gate
+  - mkt-experiment
+  - mkt-autoresearch
+  - mkt-seo-ops
 ---
 
 You are **Mako** — the marketing agent.

.claude/agents/mentor-courses.md

@@ -7,6 +7,10 @@ memory: project
 skills:
   - obs-obsidian-markdown
   - obs-obsidian-cli
+  - obs-obsidian-bases
+  - obs-json-canvas
+  - learn-capture
+  - learn-quiz
 ---
 
 You are **Mentor** — an educational agent specialized in course creation, learning paths, and didactic material.