stagent 0.11.0 → 0.11.2

package/README.md

@@ -4,7 +4,7 @@
 
 [![AI Business Operating System](https://img.shields.io/badge/AI_Business-Operating_System-6366F1)](https://stagent.io) [![npm](https://img.shields.io/npm/v/stagent)](https://www.npmjs.com/package/stagent) [![Next.js 16](https://img.shields.io/badge/Next.js-16-black)](https://nextjs.org/) [![React 19](https://img.shields.io/badge/React-19-61DAFB)](https://react.dev/) [![TypeScript](https://img.shields.io/badge/TypeScript-strict-3178C6)](https://www.typescriptlang.org/) [![Claude Agent SDK](https://img.shields.io/badge/Claude-Agent_SDK-D97706)](https://docs.anthropic.com/) [![OpenAI Codex App Server](https://img.shields.io/badge/OpenAI-Codex_App_Server-10A37F)](https://developers.openai.com/codex/app-server) [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
 
-**[stagent.io](https://stagent.io)** · **[GitHub](https://github.com/navam-io/stagent)**
+**[stagent.io](https://stagent.io)** · **[GitHub](https://github.com/manavsehgal/stagent)**
 
 ## Quick Start
 
@@ -16,13 +16,13 @@ Open [localhost:3000](http://localhost:3000). That's it — zero config, local S
 
 **Profiles & Policies** · **Blueprints & Schedules** · **Built-in Playbook** · **Open Source**
 
-<img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/home-list.png" alt="Stagent home workspace" width="1200" />
+<img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/home-list.png" alt="Stagent home workspace" width="1200" />
 
 | Home Workspace | Reusable Profiles | Workflow Blueprints | Governed Execution |
 |:-:|:-:|:-:|:-:|
 | Workspace briefing with active work, pending review, project signals, and live activity | Specialist definitions with prompts, tool policy, and runtime tuning you can reuse | Pre-configured templates with dynamic forms, YAML editing, and lineage tracking | Human-in-the-loop approvals, tool permissions, and ambient supervision |
 
-<img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/home-below-fold.png" alt="Stagent home workspace below fold — projects, activity feed, and signals" width="1200" />
+<img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/home-below-fold.png" alt="Stagent home workspace below fold — projects, activity feed, and signals" width="1200" />
 
 ---
 
@@ -39,6 +39,51 @@ The AI agent stack is broken for business operators. You can spin up an agent in
 
 ---
 
+## About Author
+
+<!-- ABOUT:BEGIN source=https://stagent.io/about/ -->
+
+### Manav Sehgal
+
+Solutions Leader, AWS Frontier AI.
+
+Author, AI Native open book. 2M+ Kaggle views. Ex Amazon AGI.
+
+#### A personal research project
+
+Stagent & AI Native — Free and open source. Building AI Native over weekends, using personal laptop and capped AI plans.
+
+#### Executive Credentials
+
+- Harvard — Disruptive Strategy
+- MIT Sloan — Design Thinking
+- Berkeley Haas — Leading Innovative Change
+
+#### Short version
+
+> "Stagent is a personal research project exploring what it takes to build AI-native on a shoestring budget over weekends." The AI Native open book serves as its 14-chapter playbook expanding this research.
+
+### Bio
+
+Manav is a solutions leader at AWS Frontier AI, collaborating with Anthropic, NVIDIA, and Disney on production AI and agentic systems. His 25-year career spans Xerox PARC (1996), HCL's digital practice, Daily Mail, Amazon AGI, and AWS, where he has delivered scale AI programs for Amazon Retail and Alexa. He led AWS pandemic response which was honored by President of India award for the customer. He holds credentials from Harvard, MIT Sloan, Berkeley Haas. He has studied Computer Engineering and Lean Management.
+
+### Research Premise
+
+"Stagent is a personal research project exploring what an AI-native operating system looks like." The AI Native book is its 14-chapter playbook for building autonomous business systems with AI agents.
+
+### Attribution
+
+Stagent and AI Native are personal works of Manav Sehgal created in own personal time and resources. While they may refer to AWS technologies which enable the AI Native promise, the opinions expressed in the website are author's personal opinions and not that of the employer.
+
+### Previously published
+
+- Data Science Solutions (2017)
+- React Speed Coding (2015)
+
+<!-- ABOUT:END -->
+
+---
+
 ## Runtime Bridge
 
 Run the same business process on different AI providers without changing a line of configuration. Stagent's shared runtime registry routes tasks, schedules, and workflow steps through **Claude Code** (Anthropic Claude Agent SDK) and **OpenAI Codex App Server**, landing everything in the same inbox, monitoring, and cost surfaces. Switching providers is a settings change, not a rewrite.
@@ -86,9 +131,9 @@ Run the same business process on different AI providers without changing a line
 ## Architecture
 
 <picture>
-  <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/architecture-dark.svg">
-  <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/architecture-light.svg">
-  <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/architecture-light.svg" alt="Stagent architecture diagram" width="900" />
+  <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/architecture-dark.svg">
+  <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/architecture-light.svg">
+  <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/architecture-light.svg" alt="Stagent architecture diagram" width="900" />
 </picture>
 
 **Key design decisions:**
@@ -115,18 +160,18 @@ Workspace-level briefing with active work, pending review, failed items, project
 #### Task Execution
 Status-driven execution board with five columns: Planned → Queued → Running → Completed → Failed. Filter across projects, create tasks inline, and open task detail to inspect status, description, and runtime state without leaving the board.
 
-<img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/dashboard-list.png" alt="Stagent kanban board" width="1200" />
+<img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/dashboard-list.png" alt="Stagent kanban board" width="1200" />
 
 | Table View |
 |:-:|
-| <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/dashboard-table.png" alt="Dashboard table view" width="580" /> |
+| <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/dashboard-table.png" alt="Dashboard table view" width="580" /> |
 
 #### Projects
 Create and organize projects as containers for related tasks. Each project can specify a working directory — agent tasks resolve `cwd` from the project's path, enabling agents to operate on external codebases. Server-rendered project cards with task counts, status badges, and a detail view at `/projects/[id]`.
 
 | Project Cards | Project Detail |
 |:-:|:-:|
-| <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/projects-list.png" alt="Project cards overview" width="580" /> | <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/projects-detail.png" alt="Project detail view" width="580" /> |
+| <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/projects-list.png" alt="Project cards overview" width="580" /> | <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/projects-detail.png" alt="Project detail view" width="580" /> |
 
 ### Agent
 
@@ -146,7 +191,7 @@ OpenAI Codex App Server is integrated as Stagent's second governed runtime. Code
 #### Agent Profiles
 Profile-backed execution with specialist definitions for different job types. Each profile packages instructions, allowed tools, max turns, and output format so teams can reuse behavior intentionally instead of relying on ad hoc prompts. Profile cards display role-based icon circles with keyword-inferred colors (blue for work, purple for personal), alongside domain tags, runtime badges, and tool counts. Workflow steps and schedules can reference profiles directly, and runtimes can be selected independently when provider support differs.
 
-<img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/profiles-list.png" alt="Stagent agent profiles with role-based icon circles" width="1200" />
+<img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/profiles-list.png" alt="Stagent agent profiles with role-based icon circles" width="1200" />
 
 #### Workflows
 Multi-step task orchestration with six patterns:
@@ -190,11 +235,11 @@ Curated agent profiles across work and personal domains, built as portable Claud
 #### Workflow Blueprints
 Pre-configured workflow templates across work and personal domains. Browse blueprints in a gallery with pattern-colored icon circles, domain tags, and difficulty badges. Preview steps and required variables, fill in a dynamic form, and create draft workflows with resolved prompts and profile assignments. Create custom blueprints via YAML or import from GitHub URLs. Lineage tracking connects workflows back to their source blueprint.
 
-<img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/workflows-list.png" alt="Stagent workflows with keyword-inferred icon circles" width="1200" />
+<img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/workflows-list.png" alt="Stagent workflows with keyword-inferred icon circles" width="1200" />
 
 | Workflow Detail |
 |:-:|
-| <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/workflows-detail.png" alt="Workflow detail with steps and status" width="580" /> |
+| <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/workflows-detail.png" alt="Workflow detail with steps and status" width="580" /> |
 
 ### Documents
 
@@ -203,7 +248,7 @@ Full document browser at `/documents` with table and grid views. Upload files wi
 
 | Table View | Grid View |
 |:-:|:-:|
-| <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/documents-list.png" alt="Documents table view" width="580" /> | <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/documents-grid.png" alt="Documents grid view" width="580" /> |
+| <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/documents-list.png" alt="Documents table view" width="580" /> | <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/documents-grid.png" alt="Documents grid view" width="580" /> |
 
 #### Document Preprocessing
 Automatic text extraction on upload for five file types: text, PDF (pdf-parse), images (image-size), Office documents (mammoth/jszip), and spreadsheets (xlsx). Extracted text, processed paths, and processing errors are tracked per document.
@@ -216,11 +261,11 @@ Airtable-like structured data system at `/tables` with 14 features. Create table
 
 | Table List | Spreadsheet Editor |
 |:-:|:-:|
-| <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/tables-list.png" alt="Tables list view" width="580" /> | <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/tables-detail.png" alt="Table spreadsheet editor" width="580" /> |
+| <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/tables-list.png" alt="Tables list view" width="580" /> | <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/tables-detail.png" alt="Table spreadsheet editor" width="580" /> |
 
 | Charts | Template Gallery |
 |:-:|:-:|
-| <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/tables-detail-charts.png" alt="Table charts tab" width="580" /> | <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/tables-templates.png" alt="Table template gallery" width="580" /> |
+| <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/tables-detail-charts.png" alt="Table charts tab" width="580" /> | <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/tables-templates.png" alt="Table template gallery" width="580" /> |
 
 - **Charts** — Bar, line, pie, and scatter charts with configurable X/Y axes and aggregation
 - **Workflow triggers** — Automated actions fired when row data matches conditions
@@ -234,7 +279,7 @@ Airtable-like structured data system at `/tables` with 14 features. Create table
 #### Playbook
 Built-in documentation system at `/playbook` with usage-stage awareness that adapts content to your experience level (new, early, active, power user). Browse feature reference docs and guided learning journeys organized by persona (Personal, Work, Power User, Developer). Adoption heatmap tracks which features you've explored, while journey cards show progress through multi-step learning paths. Markdown rendering with automatic internal link resolution, table of contents, related docs, and screengrab embedding.
 
-<img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/playbook-list.png" alt="Stagent playbook documentation" width="1200" />
+<img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/playbook-list.png" alt="Stagent playbook documentation" width="1200" />
 
 #### Living Book
 AI-native book reader at `/book` with 9 chapters across 3 parts (Foundation, Intelligence, Autonomy). Each chapter is generated from Stagent's own source code and feature docs by the document-writer agent — making this a book that writes itself.
@@ -263,7 +308,7 @@ Stagent doubles as a **control plane for AI coding environments** — scanning,
 - **Environment Health Scoring** — composite health score based on configuration completeness and freshness
 - **Agent Profile from Environment** — auto-generate agent profiles from detected environment capabilities
 
-<img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/environment-list.png" alt="Stagent environment dashboard" width="1200" />
+<img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/environment-list.png" alt="Stagent environment dashboard" width="1200" />
 
 #### Browser Tools
 Enable browser automation in chat and task execution through two MCP integrations: **Chrome DevTools MCP** (29 tools for connecting to a running Chrome instance via CDP) and **Playwright MCP** (50+ tools for headless browser automation). Configure both from Settings with independent toggles and permission tiering — read-only operations auto-approve while mutations are gated through the inbox approval flow.
@@ -285,7 +330,7 @@ Hourly poller checks the upstream `origin/main` for new commits and surfaces the
 #### Schedules
 Time-based scheduling for agent tasks with human-friendly intervals (`5m`, `2h`, `1d`) and raw 5-field cron expressions. One-shot and recurring modes with pause/resume lifecycle, expiry limits, and max firings. Each firing creates a child task through the shared execution pipeline, and schedules can now target a runtime explicitly. Scheduler runs as a poll-based engine started via Next.js instrumentation hook.
 
-<img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/schedules-list.png" alt="Stagent schedules" width="1200" />
+<img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/schedules-list.png" alt="Stagent schedules" width="1200" />
 
 #### Micro-Visualizations
 Pure SVG chart primitives (Sparkline, MiniBar, DonutRing) with zero charting dependencies. Integrated into: homepage stats cards (7-day trends), activity feed (24h bar chart), project cards (completion donuts), monitor overview (success rate), and project detail (stacked status + 14-day sparkline). Full accessibility with `role="img"` and `aria-label`.
@@ -293,27 +338,27 @@ Pure SVG chart primitives (Sparkline, MiniBar, DonutRing) with zero charting dep
 #### Cost & Usage
 Provider-normalized metering tracks token and spend activity across tasks, resumes, workflow child tasks, schedules, task assist, and profile tests. The dedicated `Cost & Usage` surface adds summary cards, trend views, provider/model breakdowns, and budget-aware audit visibility on top of the usage ledger.
 
-<img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/cost-usage-list.png" alt="Stagent cost and usage dashboard" width="1200" />
+<img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/cost-usage-list.png" alt="Stagent cost and usage dashboard" width="1200" />
 
 ### UI & DevEx
 
 #### Inbox & Human-in-the-Loop
 When an agent needs approval or input, a notification appears in your inbox. Review tool permission requests with "Allow Once" / "Always Allow" / "Deny" buttons, answer agent questions, and see task completion summaries. Supports bulk dismiss and 10s polling.
 
-<img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/inbox-list.png" alt="Stagent inbox approval flow" width="1200" />
+<img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/inbox-list.png" alt="Stagent inbox approval flow" width="1200" />
 
 | Expanded Notification |
 |:-:|
-| <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/inbox-expanded.png" alt="Inbox notification expanded" width="580" /> |
+| <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/inbox-expanded.png" alt="Inbox notification expanded" width="580" /> |
 
 #### Chat
 Conversational control plane for all workspace primitives — projects, tasks, workflows, documents, and profiles are all reachable from the chat surface. The chat interface is organized as a **tool catalog** with five categories (Explore, Create, Debug, Automate, Smart Picks) that help discover workspace capabilities. Progressive 5-tier context injection (~53K token budget) builds workspace awareness from lightweight summaries up to full document content. **@ mentions** let you reference documents and entities directly in prompts with fuzzy search autocomplete, injecting their content as context. **Slash commands** (`/`) provide quick access to tools and actions. Multi-provider model selection with cost tiers ($, $$, $$$) spans Claude Haiku through Opus and GPT-5.x models. Browser automation via Chrome DevTools and Playwright MCP enables screenshot capture and web interaction from chat. Quick Access navigation pills in responses provide entity deep-linking. Stagent CRUD tools let you create, update, and delete workspace entities through natural language.
 
-<img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/chat-conversation.png" alt="Stagent chat conversation with @ document context" width="1200" />
+<img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/chat-conversation.png" alt="Stagent chat conversation with @ document context" width="1200" />
 
 | Tool Catalog | Model Selector | Create Tab |
 |:-:|:-:|:-:|
-| <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/chat-list.png" alt="Chat tool catalog with category tabs" width="380" /> | <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/chat-model-selector.png" alt="Chat model selector with cost tiers" width="380" /> | <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/chat-create-tab.png" alt="Chat Create category prompts" width="380" /> |
+| <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/chat-list.png" alt="Chat tool catalog with category tabs" width="380" /> | <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/chat-model-selector.png" alt="Chat model selector with cost tiers" width="380" /> | <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/chat-create-tab.png" alt="Chat Create category prompts" width="380" /> |
 
 #### Skill Composition
 Activate up to three skills in a single conversation with conflict detection and runtime-aware capability gates. The Skills tab in the chat popover surfaces `+ Add` buttons on inactive skills, active badges with deactivate actions, and an "N of M active" indicator. When two skills issue polarity-divergent directives on shared keywords, a conflict dialog previews the excerpts and lets you confirm with `force:true` or back out. Composition honors the runtime capability matrix — Claude Code and Codex App Server support up to 3 active skills, while Ollama stays at 1. Conversations persist active skills through an additive `active_skill_ids` column that preserves legacy single-skill reads.
@@ -324,7 +369,7 @@ Structured `#key:value` filter grammar across chat, documents, and the `⌘K` pa
 #### Monitoring
 Real-time agent log streaming via Server-Sent Events. Filter by task or event type, click entries to jump to task details, and auto-pause polling when the tab is hidden (Page Visibility API).
 
-<img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/monitor-list.png" alt="Stagent monitoring dashboard" width="1200" />
+<img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/monitor-list.png" alt="Stagent monitoring dashboard" width="1200" />
 
 #### Content Handling
 File upload with drag-and-drop in task creation. Type-aware content preview for text, markdown (via react-markdown), code, and JSON. Copy-to-clipboard and download-as-file for task outputs.
@@ -332,11 +377,11 @@ File upload with drag-and-drop in task creation. Type-aware content preview for
 #### Settings
 Configuration hub with provider-aware sections: Claude authentication (API key or OAuth), OpenAI Codex runtime API-key management, chat defaults (model selection), **browser tools** (Chrome DevTools and Playwright MCP toggles), runtime configuration (SDK timeout and max turns), tool permissions (saved "Always Allow" patterns with revoke), permission presets, budget guardrails, **database snapshots** (automatic backups with configurable retention and one-click restore), and data management.
 
-<img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/settings-list.png" alt="Stagent settings" width="1200" />
+<img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/settings-list.png" alt="Stagent settings" width="1200" />
 
 | Browser Tools | Permission Presets | Budget Configuration |
 |:-:|:-:|:-:|
-| <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/settings-browser-tools.png" alt="Browser tools MCP toggles" width="380" /> | <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/settings-presets.png" alt="Tool permission presets" width="380" /> | <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/settings-budget.png" alt="Budget configuration" width="380" /> |
+| <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/settings-browser-tools.png" alt="Browser tools MCP toggles" width="380" /> | <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/settings-presets.png" alt="Tool permission presets" width="380" /> | <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/settings-budget.png" alt="Budget configuration" width="380" /> |
 
 #### CLI
 The `npx stagent` entry point boots a Next.js server from the published npm package. It is built from `bin/cli.ts` into `dist/cli.js` using tsup, and serves as the primary distribution channel — no clone required.
@@ -349,7 +394,7 @@ Global `⌘K` command palette for fast navigation and search across tasks, proje
 
 | Empty Palette | Search Results |
 |:-:|:-:|
-| <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/command-palette-empty.png" alt="Command palette empty state" width="580" /> | <img src="https://raw.githubusercontent.com/navam-io/stagent/main/public/readme/command-palette-search.png" alt="Command palette search results" width="580" /> |
+| <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/command-palette-empty.png" alt="Command palette empty state" width="580" /> | <img src="https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme/command-palette-search.png" alt="Command palette search results" width="580" /> |
 
 #### App Shell
 Responsive sidebar with collapsible icon-only mode, custom Stagent logo, tooltip navigation, dark/light/system theme, and OKLCH hue 250 blue-indigo color palette. Built on shadcn/ui (New York style) with PWA manifest and app icons. Routes: Home, Dashboard, Inbox, Chat, Projects, Workflows, Documents, Monitor, Profiles, Schedules, Cost & Usage, AI Native Book, User Guide, Environment, Settings.
@@ -552,7 +597,7 @@ All 14 features shipped across three layers:
 ### Contributor Setup
 
 ```bash
-git clone https://github.com/navam-io/stagent.git && cd stagent && npm install
+git clone https://github.com/manavsehgal/stagent.git && cd stagent && npm install
 
 # Set up one or both runtime credentials
 cat > .env.local <<'EOF'
@@ -580,4 +625,4 @@ See `AGENTS.md` for architecture details and development conventions.
 
 Licensed under the [Apache License 2.0](LICENSE).
 
-Copyright 2025-2026 [Navam](https://navam.io)
+Copyright 2025-2026 [Manav Sehgal](https://github.com/manavsehgal)

package/docs/getting-started.md

@@ -28,7 +28,7 @@ This downloads and launches Stagent on [localhost:3000](http://localhost:3000).
 For contributors or developers who want full control:
 
 ```bash
-git clone https://github.com/navam-io/stagent.git
+git clone https://github.com/manavsehgal/stagent.git
 cd stagent && npm install
 npm run dev
 ```

package/docs/superpowers/plans/2026-04-07-instance-bootstrap.md

@@ -255,7 +255,7 @@ describe("isPrivateInstance", () => {
   });
 
   it("returns true when STAGENT_DATA_DIR is a custom path", async () => {
-    vi.stubEnv("STAGENT_DATA_DIR", "/Users/navam/.stagent-wealth");
+    vi.stubEnv("STAGENT_DATA_DIR", "/Users/manavsehgal/.stagent-wealth");
     const { isPrivateInstance } = await loadDetect();
     expect(isPrivateInstance()).toBe(true);
   });
@@ -1605,7 +1605,7 @@ git commit -m "feat(instance): wire ensureInstance into instrumentation hook"
 Run these commands and verify expected output:
 
 ```bash
-cd /Users/navam/Developer/stagent
+cd /Users/manavsehgal/Developer/stagent
 grep "STAGENT_DEV_MODE=true" .env.local && echo "env gate: OK"
 ls .git/stagent-dev-mode && echo "sentinel gate: OK"
 ```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "stagent",
-  "version": "0.11.0",
+  "version": "0.11.2",
   "description": "AI Business Operating System — run your business with AI agents. Local-first, multi-provider, governed.",
   "keywords": [
     "ai",
@@ -38,10 +38,10 @@
   ],
   "repository": {
     "type": "git",
-    "url": "https://github.com/navam-io/stagent.git"
+    "url": "https://github.com/manavsehgal/stagent.git"
   },
   "bugs": {
-    "url": "https://github.com/navam-io/stagent/issues"
+    "url": "https://github.com/manavsehgal/stagent/issues"
   },
   "homepage": "https://stagent.io",
   "scripts": {

package/src/components/book/content-blocks.tsx

@@ -143,7 +143,7 @@ function CodeBlockView({
 
 /* ─── ImageBlock ─── */
 
-const BOOK_IMAGE_BASE = "https://raw.githubusercontent.com/navam-io/stagent/main/book/images";
+const BOOK_IMAGE_BASE = "https://raw.githubusercontent.com/manavsehgal/stagent/main/book/images";
 
 function ImageBlockView({
   src,

package/src/components/playbook/playbook-detail-view.tsx

@@ -130,7 +130,7 @@ export function PlaybookDetailView({
 
     // Resolve image paths to GitHub raw URLs (public/readme/ excluded from npm package)
     const GITHUB_RAW_BASE =
-      "https://raw.githubusercontent.com/navam-io/stagent/main/public/readme";
+      "https://raw.githubusercontent.com/manavsehgal/stagent/main/public/readme";
     let resolvedSrc = src;
     if (src.includes("screengrabs/")) {
       resolvedSrc = `${GITHUB_RAW_BASE}/${src.split("screengrabs/").pop()}`;

package/src/lib/agents/profiles/registry.ts

@@ -11,6 +11,7 @@ import { invalidateLatestScan, getLatestScan } from "@/lib/environment/data";
 import { db } from "@/lib/db";
 import { environmentArtifacts } from "@/lib/db/schema";
 import { eq, and } from "drizzle-orm";
+import { getStagentProfilesDir } from "@/lib/utils/stagent-paths";
 
 /**
  * Builtins ship inside the repo at src/lib/agents/profiles/builtins/.
@@ -36,6 +37,12 @@ const SKILLS_DIR = path.join(
   "skills"
 );
 
+/**
+ * Auto-promoted profiles (from environment discovery) are written here
+ * instead of SKILLS_DIR to avoid colliding with Claude Code's skill namespace.
+ */
+const PROMOTED_PROFILES_DIR = getStagentProfilesDir();
+
 // ---------------------------------------------------------------------------
 // Cache
 // ---------------------------------------------------------------------------
@@ -43,37 +50,44 @@ const SKILLS_DIR = path.join(
 let profileCache: Map<string, AgentProfile> | null = null;
 let profileCacheSignature: string | null = null;
 
-function getSkillsDirectorySignature(): string {
-  if (!fs.existsSync(SKILLS_DIR)) {
-    return "missing";
-  }
+function getDirectorySignatureParts(baseDir: string): string[] {
+  if (!fs.existsSync(baseDir)) return [];
 
   const entries = fs
-    .readdirSync(SKILLS_DIR, { withFileTypes: true })
+    .readdirSync(baseDir, { withFileTypes: true })
     .filter((entry) => entry.isDirectory())
     .sort((a, b) => a.name.localeCompare(b.name));
 
-  const signatureParts: string[] = [];
+  const parts: string[] = [];
 
   for (const entry of entries) {
-    const dir = path.join(SKILLS_DIR, entry.name);
+    const dir = path.join(baseDir, entry.name);
     const yamlPath = path.join(dir, "profile.yaml");
     const skillPath = path.join(dir, "SKILL.md");
 
-    signatureParts.push(entry.name);
+    parts.push(entry.name);
 
     if (fs.existsSync(yamlPath)) {
       const stats = fs.statSync(yamlPath);
-      signatureParts.push(`yaml:${stats.mtimeMs}:${stats.size}`);
+      parts.push(`yaml:${stats.mtimeMs}:${stats.size}`);
     }
 
     if (fs.existsSync(skillPath)) {
       const stats = fs.statSync(skillPath);
-      signatureParts.push(`skill:${stats.mtimeMs}:${stats.size}`);
+      parts.push(`skill:${stats.mtimeMs}:${stats.size}`);
     }
   }
 
-  return signatureParts.join("|");
+  return parts;
+}
+
+function getSkillsDirectorySignature(): string {
+  const skillsParts = getDirectorySignatureParts(SKILLS_DIR);
+  const promotedParts = getDirectorySignatureParts(PROMOTED_PROFILES_DIR);
+
+  if (skillsParts.length === 0 && promotedParts.length === 0) return "missing";
+
+  return [...skillsParts, "||promoted||", ...promotedParts].join("|");
 }
 
 // ---------------------------------------------------------------------------
@@ -156,15 +170,16 @@ function ensureBuiltins(): void {
 // scanProfiles — read .claude/skills/*/profile.yaml, validate, pair w/ SKILL.md
 // ---------------------------------------------------------------------------
 
-function scanProfiles(): Map<string, AgentProfile> {
-  const profiles = new Map<string, AgentProfile>();
-
-  if (!fs.existsSync(SKILLS_DIR)) return profiles;
+function scanProfilesFromDir(
+  baseDir: string,
+  profiles: Map<string, AgentProfile>
+): void {
+  if (!fs.existsSync(baseDir)) return;
 
-  for (const entry of fs.readdirSync(SKILLS_DIR, { withFileTypes: true })) {
+  for (const entry of fs.readdirSync(baseDir, { withFileTypes: true })) {
     if (!entry.isDirectory()) continue;
 
-    const dir = path.join(SKILLS_DIR, entry.name);
+    const dir = path.join(baseDir, entry.name);
     const yamlPath = path.join(dir, "profile.yaml");
     const skillPath = path.join(dir, "SKILL.md");
 
@@ -232,6 +247,12 @@ function scanProfiles(): Map<string, AgentProfile> {
     }
   }
 
+}
+
+function scanProfiles(): Map<string, AgentProfile> {
+  const profiles = new Map<string, AgentProfile>();
+  scanProfilesFromDir(SKILLS_DIR, profiles);
+  scanProfilesFromDir(PROMOTED_PROFILES_DIR, profiles);
   return profiles;
 }
 
@@ -317,6 +338,28 @@ export function createProfile(config: ProfileConfig, skillMd: string): void {
   invalidateLatestScan();
 }
 
+/**
+ * Create an auto-promoted profile in ~/.stagent/profiles/ (not ~/.claude/skills/).
+ * This avoids colliding with Claude Code's skill discovery namespace.
+ */
+export function createPromotedProfile(config: ProfileConfig, skillMd: string): void {
+  const result = ProfileConfigSchema.safeParse(config);
+  if (!result.success) {
+    throw new Error(`Invalid profile: ${result.error.issues.map(i => i.message).join(", ")}`);
+  }
+
+  const dir = path.join(PROMOTED_PROFILES_DIR, config.id);
+  if (fs.existsSync(path.join(dir, "profile.yaml"))) {
+    throw new Error(`Profile "${config.id}" already exists`);
+  }
+
+  fs.mkdirSync(dir, { recursive: true });
+  fs.writeFileSync(path.join(dir, "profile.yaml"), yaml.dump(config));
+  fs.writeFileSync(path.join(dir, "SKILL.md"), skillMd);
+  reloadProfiles();
+  invalidateLatestScan();
+}
+
 /** Update an existing custom profile (rejects builtins) */
 export function updateProfile(id: string, config: ProfileConfig, skillMd: string): void {
   if (isBuiltin(id)) {
@@ -328,8 +371,15 @@ export function updateProfile(id: string, config: ProfileConfig, skillMd: string
     throw new Error(`Invalid profile: ${result.error.issues.map(i => i.message).join(", ")}`);
   }
 
-  const dir = path.join(SKILLS_DIR, id);
-  if (!fs.existsSync(dir)) {
+  const skillsDir = path.join(SKILLS_DIR, id);
+  const promotedDir = path.join(PROMOTED_PROFILES_DIR, id);
+  const dir = fs.existsSync(skillsDir)
+    ? skillsDir
+    : fs.existsSync(promotedDir)
+      ? promotedDir
+      : null;
+
+  if (!dir) {
     throw new Error(`Profile "${id}" not found`);
   }
 
@@ -339,14 +389,21 @@ export function updateProfile(id: string, config: ProfileConfig, skillMd: string
   invalidateLatestScan();
 }
 
-/** Delete a custom profile (rejects builtins) */
+/** Delete a custom profile (rejects builtins). Checks both user and promoted dirs. */
 export function deleteProfile(id: string): void {
   if (isBuiltin(id)) {
     throw new Error("Cannot delete built-in profiles");
   }
 
-  const dir = path.join(SKILLS_DIR, id);
-  if (!fs.existsSync(dir)) {
+  const skillsDir = path.join(SKILLS_DIR, id);
+  const promotedDir = path.join(PROMOTED_PROFILES_DIR, id);
+  const dir = fs.existsSync(skillsDir)
+    ? skillsDir
+    : fs.existsSync(promotedDir)
+      ? promotedDir
+      : null;
+
+  if (!dir) {
     throw new Error(`Profile "${id}" not found`);
   }
 

package/src/lib/environment/__tests__/auto-promote.test.ts

@@ -17,19 +17,19 @@ vi.mock("../data", () => ({
 
 vi.mock("@/lib/agents/profiles/registry", () => ({
   listProfiles: vi.fn(() => []),
-  createProfile: vi.fn(),
+  createPromotedProfile: vi.fn(),
 }));
 
 import { autoPromoteUnlinkedSkills } from "../profile-generator";
 import { getSettingSync } from "@/lib/settings/helpers";
 import { linkArtifactsToProfiles } from "../profile-linker";
 import { getArtifacts } from "../data";
-import { createProfile } from "@/lib/agents/profiles/registry";
+import { createPromotedProfile } from "@/lib/agents/profiles/registry";
 
 const mockGetSettingSync = getSettingSync as ReturnType<typeof vi.fn>;
 const mockLinker = linkArtifactsToProfiles as ReturnType<typeof vi.fn>;
 const mockGetArtifacts = getArtifacts as ReturnType<typeof vi.fn>;
-const mockCreateProfile = createProfile as ReturnType<typeof vi.fn>;
+const mockCreateProfile = createPromotedProfile as ReturnType<typeof vi.fn>;
 
 function unlinkedSkill(name: string) {
   return {

package/src/lib/environment/profile-generator.ts

@@ -4,7 +4,7 @@
 
 import { getArtifacts } from "./data";
 import { evaluateRules, generateTier2Suggestions, type ProfileSuggestion } from "./profile-rules";
-import { listProfiles, createProfile } from "@/lib/agents/profiles/registry";
+import { listProfiles, createPromotedProfile } from "@/lib/agents/profiles/registry";
 import type { ProfileConfig } from "@/lib/validators/profile";
 import { getSettingSync } from "@/lib/settings/helpers";
 import { SETTINGS_KEYS } from "@/lib/constants/settings";
@@ -126,7 +126,7 @@ export function createProfileFromSuggestion(
     skillMd = skillMd.replace(suggestion.systemPrompt, overrides.systemPrompt);
   }
 
-  createProfile(config, skillMd);
+  createPromotedProfile(config, skillMd);
 
   // Note: the created profile will have author "stagent-env" which,
   // combined with the env- prefix on the ID, identifies it as environment-originated.

package/src/lib/instance/__tests__/detect.test.ts

@@ -83,7 +83,7 @@ describe("isPrivateInstance", () => {
   });
 
   it("returns true when STAGENT_DATA_DIR is a custom path", async () => {
-    vi.stubEnv("STAGENT_DATA_DIR", "/Users/navam/.stagent-wealth");
+    vi.stubEnv("STAGENT_DATA_DIR", "/Users/manavsehgal/.stagent-wealth");
     const { isPrivateInstance } = await loadDetect();
     expect(isPrivateInstance()).toBe(true);
   });

package/src/lib/instance/fingerprint.ts

@@ -8,7 +8,7 @@
  *
  * The fingerprint is derived from:
  *   1. os.hostname() — e.g., "macbook-pro.local"
- *   2. os.userInfo().username — e.g., "navam"
+ *   2. os.userInfo().username — e.g., "manavsehgal"
  *   3. SHA-256 of the first non-internal MAC address
  *
  * The MAC is hashed before it leaves the process so the raw network identifier

package/src/lib/utils/stagent-paths.ts

@@ -52,3 +52,7 @@ export function getStagentCodexConfigPath(): string {
 export function getStagentCodexAuthPath(): string {
   return join(getStagentCodexDir(), "auth.json");
 }
+
+export function getStagentProfilesDir(): string {
+  return join(getStagentDataDir(), "profiles");
+}