@eltonssouza/development-utility-kit 0.10.0 → 0.10.1

package/.claude/skills/README.md

@@ -1,6 +1,6 @@
 # Skills — Cowork + Claude Code
 
-> **Breaking change (2026-05-25)**: command layer deleted. Architecture is now 100% Skills + Agents. The `project-manager` skill is the catch-all entry point that routes prompts to the appropriate specialist agent. Specific skills (run-sprint, auto-test-guard, prd-ready-check, grill-me, scaffold, pair-debug, api-integration-test, brain-keeper, test-coverage-auditor, update-template, active-project, caveman) still take priority via keyword match. Standard sprint flow: `analyst` (plan) → `architect` (ADR) → `tech-lead` (approve) → `sprint-runner` (executes Sprint N delegating to `backend-developer` + `frontend-developer` + `database-engineer` in parallel) → `gate-keeper` (gate senior+) → `code-reviewer` → `tech-lead` (merge).
+> **Breaking change (2026-05-25)**: command layer deleted. Architecture is now 100% Skills + Agents. The `project-manager` skill is the **front-controller** entry point (ADR-041): it intercepts every prompt, enforces the flow order, and routes/orchestrates to the appropriate specialist agent(s). Specific skills (run-sprint, auto-test-guard, prd-ready-check, grill-me, scaffold, pair-debug, api-integration-test, brain-keeper, test-coverage-auditor, update-template, active-project, caveman) still take priority via keyword match. Standard sprint flow: `analyst` (plan) → `tech-lead` (ADR + approve) → `sprint-runner` (executes Sprint N delegating to `backend-developer` + `frontend-developer` + `database-engineer` in parallel) → `gate-keeper` (gate senior+) → `code-reviewer` → `tech-lead` (merge).
 
 This directory contains the **Skills** that Cowork and Claude Code use to develop fullstack software Java 25+ / Spring Boot 4.0+ / Angular 21+ with this template's standard flow.
 
@@ -15,7 +15,7 @@ When the user describes a task, Cowork must **deliver it 100% production-ready f
 | Skill | Purpose | Triggers with |
 |---|---|---|
 | [`scaffold`](scaffold/SKILL.md) | Unified scaffold entry point — reads `## Project Identity` from CLAUDE.md, runs the appropriate pipeline: fullstack monorepo (Spring Boot 4 + Angular 21 + Docker Compose), backend-only, or frontend-only | "scaffold the project", "scaffold backend", "scaffold frontend", "bootstrap fullstack", "monta o esqueleto", "scaffolda o projeto" |
-| [`sprint-runner`](run-sprint/SKILL.md) | Runs a sprint from the plan — task by task, with checkpoints | "run sprint X", "execute the sprint" |
+| [`run-sprint`](run-sprint/SKILL.md) | Thin trigger → dispatches the `sprint-runner` agent (single execution contract, ADR-042) | "run sprint X", "execute the sprint" |
 | [`api-integration-test`](api-integration-test/SKILL.md) | Boots backend + frontend, validates integration with curl + Chrome MCP | "test integration", "smoke", "validate flow" |
 | [`gate-keeper`](auto-test-guard/SKILL.md) | At the end of each task: **generates** the automated tests for the new code (JUnit+Mockito+Testcontainers, Jest+Testing Library, Playwright) and **runs the full project regression suite**. Blocks the task if any test breaks. | "run the tests", "generate the tests", "test everything", "full suite", "ensure nothing broke", "auto-test" |
 | [`test-coverage-auditor`](test-coverage-auditor/SKILL.md) | Audits test coverage, flags technical debt from manual verification, updates `tech-debt.md`. Mandatory gate inside `prd-ready-check`. | "audit the tests", "test debt?", "coverage ok?", "list what has no test" |
@@ -28,7 +28,7 @@ When the user describes a task, Cowork must **deliver it 100% production-ready f
 | [`caveman`](caveman/SKILL.md) | Telegraphic output style — drops articles, filler, pleasantries. 65-75% fewer tokens. Always active; adjustable via "caveman lite\|full\|ultra" or "stop caveman". | Passive (always active); "caveman lite", "caveman ultra", "stop caveman" |
 | [`to-prd`](to-prd/SKILL.md) | Transforms a `DISCOVERY_*.md` into a Product Requirements Document. Requires `grill-me` to have run first. Produces `docs/prd/PRD_*.md` with six required sections: Overview, Goals, User Stories (prose), Functional Requirements, Non-functional Requirements, Out of scope. Idempotent. Opt-in only — never auto-triggered. | "to-prd", "gera PRD", "cria PRD", "generate PRD", "create PRD" |
 | [`to-issues`](to-issues/SKILL.md) | Decomposes a `PRD_*.md` into trackable GitHub issues. Requires `to-prd` to have run first. Produces `docs/issues/ISSUES_*.md` with `[ISSUE-N]` blocks (Labels, Body, Acceptance criteria) ready for `gh issue create`. Idempotent. Opt-in only — never auto-triggered. | "to-issues", "quebra em issues", "gera issues", "break into issues", "generate issues" |
-| [`project-manager`](project-manager/SKILL.md) | **Catch-all fallback router + orchestrator** (per ADR-033). Three modes: **ROUTE** (1 domain -> 1 specialist via Task tool), **ORCHESTRATE** (2-5 domains -> mini-plan inline + parallel Task calls, no PLAN_*.md), **ESCALATE** (>5 subtasks or formal plan needed -> grill-me -> analyst -> sprint-runner). Covers the 17 specialist agents (`analyst`, `tech-lead`, `backend-developer`, `frontend-developer`, `code-reviewer`, `database-engineer`, `devops-engineer`, `mobile-developer`, `n8n-specialist`, `product-owner`, `qa-engineer`, `security-engineer`, `ux-designer`, `migrator`, `release-engineer`, `auditor`). | "create endpoint", "review my code", "dockerize", "audit security", "design DB", "create mobile app", "n8n workflow", "wireframe", "migrate spring boot 2", ad-hoc multi-domain <=5 subtasks ("CRUD products", "back + front pequenos"), any task without a more specific skill |
+| [`project-manager`](project-manager/SKILL.md) | **Front-controller router + orchestrator** (ADR-041 + ADR-033). Intercepts every prompt and enforces the flow order. Three modes: **ROUTE** (1 domain -> 1 specialist via Task tool), **ORCHESTRATE** (2-5 domains -> mini-plan inline + parallel Task calls, no PLAN_*.md), **ESCALATE** (>5 subtasks or formal plan needed -> grill-me -> analyst -> sprint-runner). Covers the 17 specialist agents (`analyst`, `tech-lead`, `backend-developer`, `frontend-developer`, `code-reviewer`, `database-engineer`, `devops-engineer`, `mobile-developer`, `n8n-specialist`, `product-owner`, `qa-engineer`, `security-engineer`, `ux-designer`, `migrator`, `release-engineer`, `auditor`). | "create endpoint", "review my code", "dockerize", "audit security", "design DB", "create mobile app", "n8n workflow", "wireframe", "migrate spring boot 2", ad-hoc multi-domain <=5 subtasks ("CRUD products", "back + front pequenos"), any task without a more specific skill |
 
 ## Where the code is generated
 
@@ -139,7 +139,7 @@ There is no need to call explicitly — just describe the task. If you want to f
 
 ## Canonical precedence — skill ↔ agent
 
-Two-layer architecture. Commands layer was deleted on 2026-05-25 (replaced by the `project-manager` skill catch-all).
+Two-layer architecture. Commands layer was deleted on 2026-05-25 (replaced by the `project-manager` skill, now the front-controller per ADR-041).
 
 | Layer | Role | Trigger | Owns what |
 |---|---|---|---|
@@ -166,7 +166,7 @@ USER MESSAGE
   │         caveman, pair-debug, project-manager, active-project,
   │         prd-ready-check, api-integration-test, test-coverage-auditor
   │
-  └─ no match → PROJECT-MANAGER SKILL (catch-all fallback)
+  └─ no specific skill → PROJECT-MANAGER SKILL (front-controller, ADR-041)
                   ↓ analyzes prompt, picks ONE specialist
                   ↓ Task(subagent_type="<agent>")
                  AGENT (executor)
@@ -256,7 +256,7 @@ A skill with **no companion agent**. It executes its logic inline (Bash, Read, W
 | Category | Description | Examples |
 |---|---|---|
 | **Mode/style** | Changes the output style of the parent session, not a task | `caveman` |
-| **Router** | Catch-all dispatcher — by definition has no fixed agent target | `project-manager` |
+| **Router/front-controller** | Intercepts every prompt, enforces flow order, dispatches (no fixed agent target) | `project-manager` |
 | **Inline transform** | Short-lived transformation that doesn't warrant a dedicated agent | `active-project` |
 | **Interview / generation** | Multi-turn interview + file write, no persistent agent needed | `pair-debug`, `to-prd`, `to-issues`, `grill-me`* |
 
@@ -268,7 +268,7 @@ A skill with **no companion agent**. It executes its logic inline (Bash, Read, W
 |---|---|
 | `caveman` | Mode — output style toggle |
 | `pair-debug` | Inline transform — hypothesis loop, no persistent executor |
-| `project-manager` | Router — catch-all; fixed agent target undefined by design |
+| `project-manager` | Router/front-controller (ADR-041) — intercepts every prompt; fixed agent target undefined by design |
 | `active-project` | Inline transform — fast-lane adoption, no dedicated agent |
 | `prd-ready-check` | Inline gate — production checklist executed in the calling session (per ADR-037); needs Chrome MCP + Bash inline, would lose tools if dispatched to a child |
 | `api-integration-test` | Inline probes — docker compose + curl + Chrome MCP run in the calling session (per ADR-037); dispatch to a child would lose Chrome MCP access |
@@ -289,7 +289,7 @@ When a skill+agent pair shares a name (Pattern 1), the split between skill (inte
 
 ### D3 — Defer promotion (specialist agents stay agent-only)
 
-Specialist agents (`release-engineer`, `migrator`, `code-reviewer`, `security-engineer`, etc.) remain **agent-only** — routed via `project-manager` catch-all. Promote a specialist to a paired skill only when **both** conditions are met:
+Specialist agents (`release-engineer`, `migrator`, `code-reviewer`, `security-engineer`, etc.) remain **agent-only** — routed via the `project-manager` front-controller. Promote a specialist to a paired skill only when **both** conditions are met:
 
 1. Telemetry or repeated session history shows direct keyword invocation for this specialist that bypasses `project-manager`.
 2. The specialist has gained a ceremony of **three or more distinct phases** that benefit from a named orchestration entry point.
@@ -313,7 +313,7 @@ A new standalone skill (Pattern 3) MUST declare its justification category from
 
 ## Claude Code (terminal) usage
 
-Skills auto-trigger via `description` keywords. To force a specific skill, type `/skill <name>` (Claude Code) or mention by name ("use the `analyst` skill"). The `project-manager` skill catches anything that did not match a more specific skill.
+Skills auto-trigger via `description` keywords. To force a specific skill, type `/skill <name>` (Claude Code) or mention by name ("use the `analyst` skill"). The `project-manager` skill is the front-controller (ADR-041): it intercepts every prompt and enforces the flow order, and also catches anything that did not match a more specific skill.
 
 ## Conventions of each SKILL.md
 

package/README.md

@@ -10,9 +10,14 @@
 [![issues](https://img.shields.io/github/issues/eltonssouza/development-utility-kit)](https://github.com/eltonssouza/development-utility-kit/issues)
 [![roadmap](https://img.shields.io/badge/roadmap-public-blue)](ROADMAP.md)
 [![comparisons](https://img.shields.io/badge/comparisons-honest-orange)](docs/COMPARISONS.md)
+[![release](https://img.shields.io/github/v/release/eltonssouza/development-utility-kit)](https://github.com/eltonssouza/development-utility-kit/releases/latest)
 
 CLI binary: `duk` · Node `>=18` · License: MIT
 
+```bash
+npx @eltonssouza/development-utility-kit install
+```
+
 ---
 
 ## What it is
@@ -92,7 +97,7 @@ to-issues         → docs/issues/ISSUES_<NAME>.md   (gh issue create-ready)
    ↓
 analyst           → docs/plans/PLAN_<NAME>.md       (goal-ready DoD)
    ↓
-run-sprint        → sprint-runner (mandatory TDD, Stage 0 stack-resolver)
+run-sprint (thin) → sprint-runner (single execution contract; mandatory TDD, Stage 0 stack-resolver)
    ↓
 gate-keeper       → Senior+ gate (coverage, mutation, a11y, lighthouse, pyramid)
    ↓
@@ -277,7 +282,7 @@ Reference: ADR-007 (a11y + Lighthouse + pyramid), ADR-027 (pack `## Security` ma
 ```
 development-utility-kit/
 ├── .claude/
-│   ├── skills/      # 20 skills (catch-all, run-sprint, stack-discovery, create-stack-pack, ...)
+│   ├── skills/      # 20 skills (project-manager front-controller, run-sprint, stack-discovery, ...)
 │   ├── agents/      # 21 agents (Opus/Sonnet/Haiku per matrix)
 │   ├── stacks/      # 5 stack packs (java/spring-boot-3, spring-boot-4; typescript/angular-18,19,21)
 │   │   ├── _template.md

package/bin/cli.js

@@ -415,6 +415,26 @@ function adoptProject(opts) {
   process.stdout.write(`Harness version: ${version}\n`);
   process.stdout.write('Written        : .claude/ (+ HARNESS_VERSION, .MANIFEST, local/)\n');
   process.stdout.write('Written        : CLAUDE.md\n');
+
+  // Auto-install duk globally when running via npx (duk not yet in PATH).
+  const dukCheck = spawnSync('duk', ['--version'], {
+    shell: process.platform === 'win32',
+    stdio: 'ignore',
+  });
+  if (dukCheck.error) {
+    process.stdout.write('\nInstalling duk CLI globally...\n');
+    const globalInstall = spawnSync(
+      'npm',
+      ['install', '-g', '@eltonssouza/development-utility-kit'],
+      { stdio: 'inherit', shell: process.platform === 'win32' }
+    );
+    if (globalInstall.status === 0) {
+      process.stdout.write('duk installed globally. Run: duk help\n');
+    } else {
+      process.stdout.write('\nNote: global install failed. Run manually:\n');
+      process.stdout.write('  npm install -g @eltonssouza/development-utility-kit\n');
+    }
+  }
 }
 
 // ─── newProject (duk new <name>) ──────────────────────────────────────────────

package/dashboard/public/content/docs/architecture-overview.en.md

@@ -2,7 +2,7 @@
 
 The development-utility-kit is a harness for fullstack development with Claude Code and Cowork. The architecture is **deliberately simple**: two functional layers (Skills + Agents), a single entry point (the Skill that matches the prompt), and a cross-cutting Hooks layer that intercepts tools and prompts.
 
-There is no command layer. The `commands/` layer was removed on 2026-05-25 and replaced by the catch-all Skill `project-manager`, which routes any prompt without a specific skill to the correct specialist agent.
+There is no command layer. The `commands/` layer was removed on 2026-05-25 and replaced by the **front-controller** Skill `project-manager` (ADR-041): it intercepts every prompt, enforces the flow order (discovery → plan → sprint → gate → brain), and then routes or orchestrates to the correct specialist agent(s).
 
 This document describes the mental model you need to understand why a prompt about "create endpoint" ends up executing code in `backend-developer`, or why a request to "run sprint 3" dispatches `qa-engineer`, `backend-developer`, `frontend-developer`, and `gate-keeper` in parallel.
 
@@ -17,8 +17,8 @@ This document describes the mental model you need to understand why a prompt abo
                                      ▼
             ┌────────────────────────────────────────────┐
             │ UserPromptSubmit hook                      │
-            │ scripts/hooks/prompt-gate-reminder.sh      │
-            │ gate reminders   │
+            │ scripts/hooks/flow-guard.js                │
+            │ injects [FLOW STATE] + blocks/nudges       │
             └────────────────────┬───────────────────────┘
                                  │
                                  ▼
@@ -33,7 +33,7 @@ This document describes the mental model you need to understand why a prompt abo
                 ▼                                 ▼
    specific skill matched          no specific skill matched
    e.g. run-sprint, grill-me,      ▼
-   bootstrap-fullstack             project-manager (catch-all)
+   scaffold                        project-manager (front-controller)
                 │                  3 modes (per ADR-033):
                 │                  · ROUTE     → 1 specialist (1 domain)
                 │                  · ORCHESTRATE → 2–5 specialists in parallel
@@ -86,8 +86,8 @@ To force a specific skill, use `/skill <name>` in Claude Code or mention it expl
 
 ### Skill types
 
-- **Orchestration skills**: `run-sprint`, `grill-me`, `bootstrap-fullstack`, `auto-test-guard`, `prd-ready-check`. They have multiple stages with checkpoints (⏸️) and map each stage to an agent.
-- **Routing skills**: `project-manager`. Catch-all fallback that analyzes the prompt and dispatches to ONE specialist agent via Task tool.
+- **Orchestration skills**: `run-sprint` (thin trigger → `sprint-runner` agent, ADR-042), `grill-me`, `scaffold`, `auto-test-guard`, `prd-ready-check`. They have multiple stages with checkpoints (⏸️) and map each stage to an agent.
+- **Front-controller skill**: `project-manager` (ADR-041). Intercepts **every** prompt, enforces the flow order, then dispatches: ROUTE (1 specialist) | ORCHESTRATE (≤5 parallel, shared `run_group_id`) | ESCALATE (`grill-me → analyst → sprint-runner`).
 - **Passive skills**: `caveman` (telegraphic style, always active).
 - **Product skills**: `to-prd`, `to-issues`. Convert artifacts between pipeline stages.
 - **Adoption skills**: `update-template`, `active-project`. Synchronize projects with the latest harness version.
@@ -198,7 +198,7 @@ project/
 
 Follow what happens when you type `"create endpoint for product signup"`:
 
-2. **Skill matcher** analyzes the enriched prompt. No specific orchestrator skill keyword → falls into `project-manager` (catch-all).
+2. **Skill matcher** analyzes the enriched prompt. No specific orchestrator skill keyword → `project-manager` (front-controller) takes the prompt and enforces the flow order.
 3. **project-manager** reads the prompt, consults the routing table, decides: "backend implementation" → picks `backend-developer`.
 4. **Task tool** dispatches `backend-developer` (Sonnet 4.6 model) with the full prompt + PLAN/PRD context if any.
 5. **backend-developer** executes: reads CLAUDE.md, consults the PLAN, picks the package (`com.company.product.web`), generates controller + DTOs + service + Flyway migration.
@@ -206,7 +206,7 @@ Follow what happens when you type `"create endpoint for product signup"`:
 7. **PostToolUse hooks** run on each Edit/Write: prettier formats the file; `post-edit-test-reminder` reminds the agent to invoke `qa-engineer`.
 8. **gate-keeper** (called by the `auto-test-guard` skill at the end) runs JaCoCo coverage, PIT mutation, ESLint, Lighthouse. If any threshold fails, it blocks.
 9. **Stop hook** fires `stop-brain-reminder.sh` reminding `brain-keeper` to record the feature in the Obsidian vault.
-10. **SubagentStop hook** (future/optional) records telemetry per agent in `dashboard/data/telemetry.json` via `telemetry-writer.js`.
+10. **SubagentStop hook** records telemetry per agent (incl. `run_group_id` and project) via `telemetry-writer.js`, feeding the dashboard's per-project **Processes** view (ADR-045).
 
 ## Cowork and Claude Code CLI integration
 
@@ -220,7 +220,7 @@ Rule of thumb: **if Cowork alone covers it, use Cowork**. If you need bash hooks
 
 ## Telemetry
 
-Subagent telemetry is recorded via the `SubagentStop` hook (not configured by default — opt-in). The flow:
+Subagent telemetry is recorded via the `SubagentStop` hook. Each run carries a `run_group_id` (correlating a parallel orchestration fan) and the project path, powering the dashboard's per-project **Processes** view (ADR-045, Phase A). The flow:
 
 ```
 agent ends → SubagentStop hook → subagent-telemetry.sh
@@ -234,7 +234,7 @@ Captured metrics: agent name, model used, tokens in/out, duration, success/failu
 ## Design principles
 
 1. **Two layers, no more**. Skill (entry) + Agent (executor). End of story. Adding a third layer requires an ADR approved by `tech-lead`.
-2. **Specific skill wins over catch-all**. If `run-sprint` matched, `project-manager` does not run.
+2. **Front-controller is the front door** (ADR-041). `project-manager` intercepts every prompt and enforces the flow order; a specific skill keyword (e.g. `run-sprint`) still dispatches directly, and the `flow-guard` hook guarantees the order either way.
 3. **Hooks are for policy, not logic**. Hooks block dangerous actions, format code, inject memory. Business logic lives in agents.
 4. **Each agent declares its model**. Opus is expensive and rare. Sonnet is the default. Haiku for mechanical work.
 5. **Everything is a file on disk**. `.claude/` is versioned. Harness changes are commits.

package/dashboard/public/content/docs/skills-reference.en.md

@@ -30,7 +30,7 @@ This document covers the 18 official skills of the harness, grouped by purpose.
 
 ---
 
-## Catch-all router
+## Front-controller router (ADR-041)
 
 ### project-manager
 
@@ -38,7 +38,7 @@ This document covers the 18 official skills of the harness, grouped by purpose.
 
 **EN triggers**: "create endpoint", "implement controller", "create component", "review my code", "security audit", "design the database", "optimize query", "dockerize", "setup CI", "create mobile app", "n8n workflow", "refine backlog", "write tests", "wireframe", "migrate from spring boot 2", "release prep", "architecture decision", "analyze this task".
 
-**When to fire**: any development request that does **not** match a specific skill. It is the default entry point — the wildcard that covers the 17 specialist agents without a dedicated skill.
+**When to fire**: `project-manager` is the **front-controller** (ADR-041) — it intercepts every prompt, enforces the flow order (discovery → plan → sprint → gate → brain), and covers the specialist agents without a dedicated skill. A specific skill keyword still dispatches directly; `project-manager` plus the `flow-guard` hook guarantee the order either way.
 
 **What it does**: reads the intent, decides one of three modes (per ADR-033), and dispatches accordingly:
 
@@ -52,9 +52,9 @@ Reference: **ADR-033** — orchestrate mode fills the fast-lane gap acknowledged
 
 **Output / artifacts**: ROUTE → single `Task(subagent_type="<agent>", description="...", prompt="...")` call. ORCHESTRATE → inline mini-plan table + multiple `Task` calls in the same content block. Final artifacts (code, ADR, report) come from the chosen specialist(s).
 
-**Prerequisites**: none — it is the catch-all.
+**Prerequisites**: none — it is the front door. It runs the `flow-guard` precondition checks (DISCOVERY/PLAN present for qualified work) before dispatching.
 
-**When NOT to fire**: when a specific skill matches (`run-sprint`, `auto-test-guard`, `prd-ready-check`, `grill-me`, `bootstrap-*`, `pair-debug`, `api-integration-test`, `brain-keeper`, `test-coverage-auditor`, `update-template`, `active-project`, `caveman`). Specific skills always win by specificity. For formal sprint execution (with `PLAN_*.md`), use `run-sprint`. For tasks that need a persisted plan or discovery, escalate to `grill-me` → `analyst` first.
+**When NOT to fire**: when a specific skill matches (`run-sprint`, `auto-test-guard`, `prd-ready-check`, `grill-me`, `scaffold`, `pair-debug`, `api-integration-test`, `brain-keeper`, `test-coverage-auditor`, `update-template`, `active-project`, `caveman`). Specific skills always win by specificity. For formal sprint execution (with `PLAN_*.md`), use `run-sprint`. For tasks that need a persisted plan or discovery, escalate to `grill-me` → `analyst` first.
 
 **Mode selection heuristic (deterministic)**: skill counts distinct domains touched (backend, frontend, mobile, database, devops, ux, security, n8n, product, tests, architecture, release). 1 domain → ROUTE. 2–5 domains, independent paths → ORCHESTRATE. >5 or any subtask needs further decomposition → ESCALATE.
 

package/dashboard/public/content/docs/troubleshooting.en.md

@@ -24,8 +24,8 @@ Each item follows the pattern:
 
 ### Specific skill overridden by `project-manager`
 
-- **Symptom**: when asking "review code", `project-manager` (catch-all) answers instead of the more specific skill.
-- **Cause**: no specific skill matched the exact phrase; the catch-all takes over.
+- **Symptom**: when asking "review code", `project-manager` (front-controller) answers instead of the more specific skill.
+- **Cause**: no specific skill matched the exact phrase; the front-controller takes over.
 - **Solution**: prefer the canonical phrase from the skill (see the "Skills" table in `CLAUDE.md`). E.g., for PR review use "review the PR" or "audit this change". A more specific skill always wins on match.
 
 ### `caveman` cutting too much substance

package/dashboard/public/content/manual/backend.en.md

@@ -194,7 +194,7 @@ tests, produce ADRs) and return to the skill, which returns to you.
 | `brain-keeper` | `record in the brain`, `update brain`, `daily log`, `save ADR to vault` |
 | `active-project` | `/active-project <path>`, `activate project at <path>` |
 | `update-template` | `update the template`, `sync with development-utility-kit`, `pull the new skills` |
-| `project-manager` | catch-all — any prompt without a more specific skill |
+| `project-manager` | front-controller — intercepts every prompt, enforces flow order, routes/orchestrates |
 | `caveman` | `caveman lite`, `caveman ultra`, `stop caveman` |
 
 ---

package/dashboard/public/content/manual/frontend.en.md

@@ -233,7 +233,7 @@ The harness exposes skills that trigger by **keyword** in Claude Code/Cowork con
 | `prd-ready-check` | GO/NO-GO for production | `is it production ready?`, `DoD` |
 | `brain-keeper` | Record history in Obsidian | `record in brain`, `update brain` |
 | `caveman` | Telegraphic mode (default ON) | `caveman lite/full/ultra`, `stop caveman` |
-| `project-manager` | Catch-all (default) | Any prompt without a specific skill |
+| `project-manager` | Front-controller | Intercepts every prompt; enforces flow order |
 
 ### Detailed cards
 
@@ -302,7 +302,7 @@ The harness exposes skills that trigger by **keyword** in Claude Code/Cowork con
 - **Trigger**: `caveman lite/full/ultra` or `stop caveman`.
 - **Effect**: responses ~65-75% shorter.
 
-#### `project-manager` (catch-all)
+#### `project-manager` (front-controller)
 
 - **When**: any prompt that doesn't match a specific skill.
 - **Output**: routes to ONE specialist agent via Task tool (`frontend-developer`, `ux-designer`, `qa-engineer`, etc.).

package/dashboard/public/content/manual/fullstack.en.md

@@ -243,7 +243,7 @@ conversational.
 | `brain-keeper` | `record in brain`, `update the brain` | `docs/brain/` vault |
 | `active-project` | `/active-project <path>`, `adopt project at <path>` | Non-interactive adoption |
 | `update-template` | `update the template` | Sync `.claude/` + `CLAUDE.md` (merge) |
-| `project-manager` | catch-all | Routes to 1 agent |
+| `project-manager` | front-controller | Intercepts all; ROUTE / ORCHESTRATE / ESCALATE |
 
 ### 5.1. `bootstrap-fullstack`
 
@@ -352,8 +352,7 @@ overwritten. A backup is created (`CLAUDE.md.bak-<timestamp>`).
 
 ### 5.13. `project-manager`
 
-Catch-all. Any prompt without a specific skill falls here and is routed to
-**one** agent.
+Front-controller (ADR-041): it intercepts every prompt, enforces the flow order, and routes or orchestrates to the right specialist(s).
 
 ### 5.15. Impeccable — visual polish
 
@@ -1180,7 +1179,7 @@ Big table, ordered by intent.
 | Record in vault | `record in brain` | `brain-keeper` |
 | Migrate stack | `migrate from <X> to <Y>` | `migrator` agent |
 | Update template | `update the template` | `update-template` |
-| Catch-all | any prompt without a keyword | `project-manager` |
+| Front-controller | every prompt (enforces flow order) | `project-manager` |
 
 CLI (terminal, outside chat):
 

package/dashboard/public/content/manual/mobile.en.md

@@ -33,7 +33,7 @@ duk update                        # alias for `duk install`
 
 ## 5-min onboarding
 
-Mobile has no `bootstrap-mobile` skill. Scaffolding is the responsibility of the `mobile-developer` agent via `project-manager` (catch-all skill). Step by step:
+Mobile has no `bootstrap-mobile` skill. Scaffolding is the responsibility of the `mobile-developer` agent via `project-manager` (front-controller skill). Step by step:
 
 ```bash
 # 1. Create Expo project (manual, outside the harness)
@@ -127,7 +127,7 @@ Claude (project-manager -> mobile-developer):
 
 ## Skills applicable to mobile
 
-Mobile uses the harness's general skill catalog. There is no mobile-specific skill. `project-manager` does the catch-all routing to `mobile-developer`.
+Mobile uses the harness's general skill catalog. There is no mobile-specific skill. `project-manager` (front-controller) routes to `mobile-developer`.
 
 | Skill | EN trigger | Output |
 |---|---|---|
@@ -144,7 +144,7 @@ Mobile uses the harness's general skill catalog. There is no mobile-specific ski
 | `update-template` | "update template" | Sync `.claude/` + `CLAUDE.md` |
 | `caveman` | always-on, "stop caveman" | Telegraphic output |
 
-### `project-manager` (catch-all — replaces bootstrap-mobile)
+### `project-manager` (front-controller — replaces bootstrap-mobile)
 
 Since there is NO `bootstrap-mobile`, all scaffolding or structural changes go through `project-manager`:
 

package/dashboard/public/content/manual/quickstart.en.md

@@ -151,7 +151,7 @@ If you adopt the harness on a real project and ship something with it, please co
 |---|---|---|
 | `duk doctor` reports Node < 18 | Old Node installed | Install Node 18+ from nodejs.org or your package manager |
 | `duk install` aborts with "drift detected" | You modified `.claude/` after the previous install | Move your changes to `.claude/local/` (preserved across installs) OR run `duk install --force` (overwrite + backup) |
-| Chat does not seem to trigger any skill | Keywords do not match any skill's `description` | Try a more explicit phrasing OR fall through to `project-manager` (catch-all) by phrasing as a normal dev request like "create endpoint POST /api/v1/foo" |
+| Chat does not seem to trigger any skill | Keywords do not match any skill's `description` | Try a more explicit phrasing OR fall through to `project-manager` (front-controller) by phrasing as a normal dev request like "create endpoint POST /api/v1/foo" |
 | `duk dashboard` says "port 4242 in use" | Another process holds the port | Pass `--port 5000` (or any free port) |
 | RTK widget shows no data | RTK not on PATH (intentional fallback) | Install rtk separately if you want the metric; otherwise ignore |
 | `duk lint` reports ERRORs in skills you did not touch | Frontmatter incomplete in the harness | Open an issue with the lint output — likely a regression |

package/dashboard/public/favicon.svg

@@ -0,0 +1,39 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 32 32">
+  <defs>
+    <linearGradient id="bg" x1="0%" y1="0%" x2="100%" y2="100%">
+      <stop offset="0%" stop-color="#0f2847"/>
+      <stop offset="100%" stop-color="#0a1628"/>
+    </linearGradient>
+    <linearGradient id="core" x1="0%" y1="0%" x2="100%" y2="100%">
+      <stop offset="0%" stop-color="#1a6bff"/>
+      <stop offset="100%" stop-color="#ff6b2b"/>
+    </linearGradient>
+    <radialGradient id="glow" cx="50%" cy="50%" r="50%">
+      <stop offset="0%" stop-color="#6db3ff" stop-opacity="0.3"/>
+      <stop offset="100%" stop-color="#6db3ff" stop-opacity="0"/>
+    </radialGradient>
+  </defs>
+
+  <!-- Background -->
+  <rect width="32" height="32" rx="7" fill="url(#bg)"/>
+
+  <!-- Glow halo around center -->
+  <circle cx="16" cy="16" r="10" fill="url(#glow)"/>
+
+  <!-- Connection lines -->
+  <line x1="16" y1="16" x2="7"  y2="7"  stroke="#1a6bff" stroke-width="1.2" stroke-opacity="0.55" stroke-linecap="round"/>
+  <line x1="16" y1="16" x2="25" y2="7"  stroke="#1a6bff" stroke-width="1.2" stroke-opacity="0.55" stroke-linecap="round"/>
+  <line x1="16" y1="16" x2="7"  y2="25" stroke="#ff6b2b" stroke-width="1.2" stroke-opacity="0.55" stroke-linecap="round"/>
+  <line x1="16" y1="16" x2="25" y2="25" stroke="#ff6b2b" stroke-width="1.2" stroke-opacity="0.55" stroke-linecap="round"/>
+
+  <!-- Satellite nodes -->
+  <circle cx="7"  cy="7"  r="2.2" fill="#4d9aff" opacity="0.85"/>
+  <circle cx="25" cy="7"  r="2.2" fill="#4d9aff" opacity="0.85"/>
+  <circle cx="7"  cy="25" r="2.2" fill="#ff9a5c" opacity="0.85"/>
+  <circle cx="25" cy="25" r="2.2" fill="#ff9a5c" opacity="0.85"/>
+
+  <!-- Center node — gradient ring -->
+  <circle cx="16" cy="16" r="5.5" fill="url(#core)"/>
+  <!-- Center node — white core -->
+  <circle cx="16" cy="16" r="2.8" fill="#f0f4fa"/>
+</svg>

package/dashboard/public/index.html

@@ -4,6 +4,7 @@
   <meta charset="UTF-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
   <title>development-utility-kit dashboard</title>
+  <link rel="icon" type="image/svg+xml" href="favicon.svg" />
   <link rel="preconnect" href="https://fonts.googleapis.com" />
   <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
   <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700;800&family=JetBrains+Mono:wght@400;500;700&display=swap" rel="stylesheet" />

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@eltonssouza/development-utility-kit",
-  "version": "0.10.0",
+  "version": "0.10.1",
   "description": "npx installer for the development-utility-kit harness",
   "bin": {
     "duk": "bin/cli.js"