{
  "markdown": "# BABOK Analyst - AI-Powered Business Analysis Agent\n\n[![Release](https://img.shields.io/github/v/release/GSkuza/BABOK_ANALYST)](https://github.com/GSkuza/BABOK_ANALYST/releases)\n[![Lint Stage Prompts](https://github.com/GSkuza/BABOK_ANALYST/actions/workflows/lint-prompts.yml/badge.svg)](https://github.com/GSkuza/BABOK_ANALYST/actions/workflows/lint-prompts.yml)\n\nAn AI agent for professional business analysis compliant with **BABOK v3** (International Institute of Business Analysis) standard. Guides the analyst through a structured **9-stage** flow - from Stage 0 project charter to Stage 8 business case and ROI.\n\n**Current version:** 2.2.8 | **Plugin install:** Claude Code, Codex, Copilot CLI\n\n## What is BABOK Analyst?\n\nBABOK Analyst is a set of system prompts for AI models (Claude, ChatGPT, other LLMs) that transforms them into business analysis experts. The agent:\n\n- Conducts a structured analysis process in **9 stages** (Stage 0 charter gate + Stages 1-8)\n- Uses **Short Rationale + Evidence** methodology (concise conclusions with cited evidence)\n- Requires **human approval** at each stage (human-in-the-loop)\n- Generates complete **project documentation** in Markdown format\n- Manages **project lifecycle** with unique Project IDs, save/load, and persistent journal logs\n- Specializes in IT projects for **mid-market** companies (€10-100M revenue, 50-500 employees)\n\n## Repository Structure\n\n```\nBABOK_ANALYST/\n|\n|-- BABOK_AGENT/                          # Agent files\n|   |-- BABOK_Agent_System_Prompt.md      # Main system prompt (modular, references stage files)\n|   |-- BABOK_Agent_Quick_Start_Guide.md  # Quick start guide\n|   |-- BABOK_Project_Structure_Template.md # Generic project folder structure template\n|   |-- stages/                           # Individual stage instruction files\n|   |   |-- BABOK_agent_stage_0.md        # Stage 0: Project Charter\n|   |   |-- BABOK_agent_stage_1.md        # Stage 1: Project Initialization\n|   |   |-- BABOK_agent_stage_2.md        # Stage 2: Current State Analysis\n|   |   |-- BABOK_agent_stage_3.md        # Stage 3: Problem Domain Analysis\n|   |   |-- BABOK_agent_stage_4.md        # Stage 4: Solution Requirements\n|   |   |-- BABOK_agent_stage_5.md        # Stage 5: Future State Design\n|   |   |-- BABOK_agent_stage_6.md        # Stage 6: Gap Analysis & Roadmap\n|   |   |-- BABOK_agent_stage_7.md        # Stage 7: Risk Assessment\n|   |   |-- BABOK_agent_stage_8.md        # Stage 8: Business Case & ROI\n|   |-- agents/                           # Multi-agent orchestration layer (NEW v2.1.0)\n|   |   |-- orchestrator_config.json      # Pipeline: model routing, handoff, retry rules\n|   |   |-- stage1_config.json … stage8_config.json  # Per-stage model & prompt config\n|   |   |-- quality_audit_agent.md        # Automated post-stage quality review agent\n|   |   |-- quality_scoring_rubric.json   # Scoring rubric (completeness/SMART/consistency)\n|   |   |-- context_schema_v2.json        # Extended context schema v2\n|   |-- LLM_BABOK_AGENT/                  # Standalone prompt for LLM chat\n|   |   |-- BABOK_Agent_LLM_Prompt.md     # Self-contained prompt (all stages inline)\n|\n|-- cli/                                  # Node.js CLI tool\n|   |-- bin/babok.js                      # CLI entry point\n|   |-- src/commands/                     # Command implementations\n|   |   |-- ingest.js                     # babok ingest <file> (NEW v2.1.0)\n|   |-- src/quality/                      # Quality scoring engine (NEW v2.1.0)\n|   |   |-- scorer.js                     # scoreStage() / scoreAll()\n|   |   |-- checks/completeness.js        # Section completeness checker\n|   |   |-- checks/smart.js               # SMART criteria heuristics\n|   |   |-- checks/consistency.js         # Cross-stage consistency checks\n|   |-- src/validation/                   # Validation engine (NEW v2.1.0)\n|   |   |-- cross-stage-validator.js      # validateProject() — 6 built-in rules\n|   |-- src/reasoning/                    # AI reasoning engine (NEW v2.1.0)\n|   |   |-- process-mapper.js             # generateProcessDiagram() — Mermaid output\n|   |   |-- prompts/                      # LLM prompt templates\n|   |-- src/lib/document-parser.js        # PDF/DOCX/XLSX/CSV/TXT/MD parser (NEW v2.1.0)\n|   |-- src/lock.js                       # File-locking for team collaboration\n|   |-- src/llm.js                        # Multi-provider LLM integration & keystore\n|   |-- src/journal.js                    # Project journal management\n|   |-- src/project.js                    # Project ID generation\n|   |-- src/display.js                    # Terminal output formatting\n|   |-- package.json                      # npm package configuration\n|   |-- README.md                         # CLI Quick Start Guide\n|\n|-- babok-mcp/                            # MCP Server (v2.2.x)\n|   |-- bin/babok-mcp.js                  # Entry point (npx babok-mcp)\n|   |-- src/server.js                     # MCP server — 19 tools + 9 resources\n|   |-- src/lib/project.js                # Project ID & path resolution\n|   |-- src/lib/journal.js                # Journal CRUD + stage transitions\n|   |-- src/test/smoke.js                 # 10-assertion smoke test suite\n|   |-- setup.bat                         # One-click MCP installer (Windows)\n|   |-- package.json                      # npm package (babok-mcp)\n|   |-- README.md                         # Setup guide for Claude/Cursor/VS Code\n|   |-- babok-mcp-user-manual.md          # Full user manual (EN)\n|\n|-- web/                                  # Web UI — Next.js 15 App Router\n|   |-- app/                              # App Router pages & API routes\n|   |   |-- page.tsx                      # Dashboard — server-rendered project overview\n|   |   |-- projects/                     # Project detail, stage review, export page\n|   |   |-- api/                          # REST API routes (projects, stages, export)\n|   |-- components/                       # Reusable React components + UI primitives\n|   |-- lib/project-store.ts              # Shared server-side project/stage readers\n|   |-- lib/babok-client.ts               # Typed API client helpers\n|   |-- next.config.js\n|   |-- package.json\n|\n|-- docs/                                 # Architecture & reference docs (NEW v2.1.0)\n|   |-- L2_L3_ARCHITECTURE.md             # L2/L3 agent layer design with sequence diagrams\n|   |-- MCP_TOOLS_SPECIFICATION.md        # Full MCP tools API reference\n|   |-- MIGRATION_GUIDE_L1_to_L2.md       # CLI → MCP migration guide\n|   |-- workflows.md                      # End-to-end workflow diagrams\n|   |-- agent-portability.md              # Plugin marketplace adapter matrix (NEW v2.1.0)\n|\n|-- templates/                            # BABOK deliverable templates (NEW v2.1.0)\n|   |-- BRD_Template.md                   # Business Requirements Document\n|   |-- Risk_Register_Template.md         # Risk Register with probability/impact matrix\n|   |-- Stakeholder_Analysis_Template.md  # Stakeholder Analysis + RACI matrix\n|   |-- User_Story_Template.md            # User Story with Given/When/Then criteria\n|   |-- project_context.example.json      # Reference context file for babok run\n|\n|-- knowledge/                            # BABOK knowledge base (NEW v2.1.0)\n|   |-- benchmarks/                       # Industry benchmark data\n|   |-- industries/                       # Industry-specific reference data\n|   |-- regulations/                      # Regulatory requirements by jurisdiction\n|   |-- anti_patterns/                    # Known BA anti-patterns\n|   |-- technology/                       # Technology reference data\n|   |-- schema/\n|   |-- README.md\n|\n|-- tests/                                # Automated test suite (NEW v2.1.0)\n|   |-- unit/                             # Unit tests (project, journal, scoring, validation)\n|   |-- integration/                      # Integration tests (CLI workflow)\n|   |-- plugin-manifest.test.cjs          # Plugin marketplace smoke tests (NEW v2.1.0)\n|   |-- hooks.test.cjs                    # Lifecycle hook tests (NEW v2.1.0)\n|   |-- uninstall.test.cjs                # Uninstall script tests (NEW v2.1.0)\n|   |-- fixtures/                         # Sample deliverable files for testing\n|   |-- helpers/                          # mock-llm.js, temp-project.js\n|\n|-- evaluation/                           # Gold standard evaluation suite (NEW v2.1.0)\n|\n|-- .claude-plugin/                       # Claude Code marketplace manifests (NEW v2.1.0)\n|-- .codex-plugin/                        # Codex plugin manifest\n|-- .github/plugin/                       # Copilot CLI plugin manifest\n|-- .mcp.json                             # Portable MCP wiring (${CLAUDE_PLUGIN_ROOT})\n|-- hooks/                                # Lifecycle hooks (Claude/Codex/Copilot)\n|-- skills/                               # Bundled agent skills\n|-- commands/                             # Slash commands: *.md (Claude), *.toml (Copilot/Codex)\n|-- agents/                               # Subagent definitions (orchestrator + stages 0–8)\n|-- AGENTS.md                             # Always-on rules for generic agents\n|-- scripts/                              # check-versions.cjs, uninstall.cjs\n|\n|-- setup.bat                             # One-click installer (Windows)\n|-- setup.sh                              # One-click installer (Linux/macOS)\n|-- generate_manual.py                    # DOCX/PDF manual generator (NEW v2.1.0)\n|-- babok-mcp-podrecznik uzytkownika.md   # Full MCP user manual (PL)\n|-- babok-mcp-user-manual.md              # Full MCP user manual (EN)\n|-- BABOK_AGENT_SYSTEM_PROMPT.md          # Consolidated root-level system prompt (NEW v2.1.0)\n|\n|-- .github/\n|   |-- copilot-instructions.md           # Configuration for GitHub Copilot / VS Code (1,600 lines)\n|   |-- prompts/                          # Stage-specific Copilot Chat prompt files (NEW v2.1.0)\n|   |-- workflows/\n|   |   |-- lint-prompts.yml              # CI: validates stage files on every push\n|\n|-- .gitignore                            # Excludes local analysis files\n|-- README.md                             # This file\n```\n\n## Stages\n\n| Stage | Name | What You Get |\n|------|-------|----------------|\n| **Stage 0** ⭐ | Project Charter | Business trigger, sponsor sign-off, scope boundary, Go/No-Go gate |\n| **Stage 1** | Project Initialization & Stakeholder Mapping | Project scope, stakeholder register, success criteria |\n| **Stage 2** | Current State Analysis (AS-IS) | Process maps, cost baseline, system analysis |\n| **Stage 3** | Problem Domain Analysis | Problem categorization, root cause analysis, prioritization |\n| **Stage 4** | Solution Requirements Definition | Functional/non-functional requirements, user stories, MoSCoW |\n| **Stage 5** | Future State Design (TO-BE) | Target architecture, TO-BE processes |\n| **Stage 6** | Gap Analysis & Implementation Roadmap | Gap analysis, implementation roadmap |\n| **Stage 7** | Risk Assessment & Mitigation Strategy | Risk register, mitigation plans |\n| **Stage 8** | Business Case & ROI Model | Financial model, ROI, NPV, payback period |\n\n### Pipeline profiles\n\nThe table above is the default **`babok`** profile. A project can instead run the **`consulting`** profile (`babok new --profile consulting`, `/babok-new-consulting`, or `babok_new_project { profile: \"consulting\" }`) — a leaner, non-IT advisory pipeline with project IDs prefixed `BC-`:\n\n| Stage | Name | What You Get |\n|------|-------|----------------|\n| **Stage 0** ⭐ | Engagement Charter & Mandate | Sponsor & mandate, scope with explicit no-IT exclusion, fee & budget ceiling, Go/No-Go |\n| **Stage 1** | Stakeholder & Governance Mapping | Power/interest grid, steering committee, RACI, success KPIs, communication plan |\n| **Stage 2** | Current State Diagnostic & Root Cause Analysis | Operating model canvas, KPI baseline, findings, 5-Whys/Fishbone root causes, value at stake |\n| **Stage 3** | Strategic Options & Recommendation | Options (OPT-NN), weighted evaluation matrix, recommendation, risks of inaction |\n| **Stage 4** | Target Operating Model & Change Roadmap | Target model by dimension, org-design changes, phased roadmap, ADKAR/Kotter change plan |\n| **Stage 5** | Risk, Governance & Change Readiness | Risk register with owners, readiness per stakeholder group, escalation cadence |\n| **Stage 6** | Business Case & Value Realization Plan | CBA, ROI/NPV/payback, benefits tracker, budget alignment, value governance |\n\nProfiles are plain data under `profiles/<id>/` (see `profiles/profile.schema.json`); the same CLI, MCP server, hooks and web UI serve every profile.\n\n---\n\n## Web UI Highlights\n\nThe bundled Next.js UI provides a lightweight review layer over the shared project files in `projects/<project_id>/`.\n\n- **Dashboard**: server-rendered project cards with progress bars and approval counts\n- **Project view**: stage list, overall progress, and ZIP export\n- **Stage view**: rendered deliverables, Mermaid diagrams, quality score badge, and approve/reject controls\n- **Export endpoint**: project ZIP download via `web/app/api/projects/[id]/export/route.ts`, with Windows-compatible archive creation\n\nRun locally:\n\n```bash\ncd web\nnpm install\nnpm run build\nnpm run start\n```\n\nOpen `http://localhost:3000`.\n\n---\n\n## Modular Architecture (v2.0)\n\nThe agent system uses a **modular architecture** where each analysis stage has its own detailed instruction file:\n\n```\nBABOK_AGENT/\n|-- BABOK_Agent_System_Prompt.md          # Core prompt (references stage files)\n|-- stages/\n|   |-- BABOK_agent_stage_0.md            # Stage 0: Project Charter gate\n|   |-- BABOK_agent_stage_1.md            # Detailed Stage 1 instructions\n|   |-- BABOK_agent_stage_2.md            # Detailed Stage 2 instructions\n|   |-- ...                               # Stages 3-7\n|   |-- BABOK_agent_stage_8.md            # Detailed Stage 8 instructions\n|-- LLM_BABOK_AGENT/\n|   |-- BABOK_Agent_LLM_Prompt.md         # All-in-one prompt for LLM chat windows\n```\n\n**Two usage variants:**\n\n| Variant | File | Use When |\n|---------|------|----------|\n| **Modular** | `BABOK_Agent_System_Prompt.md` + `stages/*.md` | VS Code, Claude Code, IDE-based workflows (agent can load stage files as needed) |\n| **Standalone** | `LLM_BABOK_AGENT/BABOK_Agent_LLM_Prompt.md` | Direct paste into LLM chat (Claude.ai, ChatGPT, etc.) — all stages inline, self-contained |\n\nEach stage file contains: step-by-step process, questions for human, deliverable template, quality checklist, and CLI command references.\n\n---\n\n## How to Get Started\n\n### Plugin Marketplace Install (recommended) — v2.2+\n\nInstall the full BABOK Analyst stack (skills, agents, hooks, MCP, slash commands) in Claude Code, Codex, or Copilot CLI.\n\n**Claude Code (3 steps):**\n\n```\n/plugin marketplace add GSkuza/BABOK_ANALYST\n/plugin install babok_analyst@babok_analyst\n/reload-plugins\n```\n\nThen open `/hooks` and authorize lifecycle hooks. Start a **new session**.\n\n**Update to latest release:**\n\n```\n/plugin marketplace update babok_analyst\n/plugin install babok_analyst@babok_analyst\n/reload-plugins\n```\n\n**Codex** (run in **PowerShell / cmd**, not inside the Codex chat — the in-app sandbox cannot write to `~/.codex`):\n\n```\ncodex plugin marketplace add GSkuza/BABOK_ANALYST\ncodex plugin add babok_analyst@babok_analyst\n```\n\nThen open `/plugins` to confirm **babok_analyst@babok_analyst** is listed, and authorize hooks in `/hooks`.\n\n**Update:**\n\n```\ncodex plugin marketplace upgrade babok_analyst\ncodex plugin add babok_analyst@babok_analyst\n```\n\n**GitHub Copilot CLI:**\n\n```\ncopilot plugin marketplace add GSkuza/BABOK_ANALYST\ncopilot plugin install babok_analyst@babok_analyst\n```\n\n#### What the plugin includes\n\n| Component | Location | Purpose |\n|-----------|----------|---------|\n| Marketplace manifest | `.claude-plugin/` (Claude), `.agents/plugins/` (Codex) | Plugin registry per host |\n| MCP wiring | `.mcp.json` | 19 tools + 9 stage resources (`${CLAUDE_PLUGIN_ROOT}`) |\n| Lifecycle hooks | `hooks/` | Session activation + `babok-mcp` dependency install |\n| Skills | `skills/babok-analyst/`, `skills/eu-pl-law-tracker/` | BABOK operating rules + EU/PL legal tracking workflow |\n| Agents | `agents/` | Orchestrator + per-stage subagents (12) |\n| Commands | `commands/babok-*.md` | `/babok-new`, `/babok-new PL`, `/babok-new ENG`, `/babok-new-pl`, `/babok-new-eng`, `/babok-status`, `/babok-help` |\n| Always-on rules | `AGENTS.md` | Generic agents / Gemini CLI fallback |\n\nProjects are stored in **`projects/<project_id>/`** under your workspace (not `BABOK_Analysis/`).\n\n**Uninstall external state:** `node scripts/uninstall.cjs`\n\nSee [`docs/agent-portability.md`](docs/agent-portability.md) for the full adapter matrix.\n\n#### Troubleshooting\n\n| Error | Fix |\n|-------|-----|\n| `marketplace \"babok_analyst\" not found` | Run `/plugin marketplace add GSkuza/BABOK_ANALYST` **before** install |\n| `agents: Invalid input` | Update to **v2.2.0+** (`/plugin marketplace update babok_analyst`) — fixed manifest |\n| MCP tools missing | `/reload-plugins`, ensure Node.js ≥18; hook runs `npm install` in `babok-mcp/` |\n| Codex: MCP `babok` handshake failed | Update to **v2.2.4+** — uses `hooks/babok-mcp-launcher.cjs` with `cwd: \".\"` (Codex does not expand `${CLAUDE_PLUGIN_ROOT}`) |\n| Stale plugin cache | `/plugin marketplace update babok_analyst` then reinstall |\n| Codex: empty plugin list / sandbox write error | Run `codex plugin marketplace add` in a **normal terminal** (v2.2.4+); update marketplace if on older tag |\n\n**Local checkout (no GitHub fetch):**\n\n```\n/plugin marketplace add C:/AI_WORKSPACE/CURSOR_PROJECTS/CURSOR_PROJECTS_BIZ/BABOK_ANALYST/BABOK_ANALYST\n/plugin install babok_analyst@babok_analyst\n/reload-plugins\n```\n\n---\n\n### Quick Start (non-technical users)\n\n**Windows:**\n```bat\nsetup.bat\n```\n\n**Linux / macOS:**\n```bash\nchmod +x setup.sh && ./setup.sh\n```\n\nThe setup script automatically:\n- checks for Node.js (with download link if missing)\n- runs `npm install`\n- optionally adds `babok` to PATH\n- launches the **interactive setup wizard** (`babok setup`) for API key entry and language selection — no JSON editing required\n\n---\n\n### Method 1: Claude.ai (Projects)\n\n1. **Clone or download the repository** (see section below)\n2. Go to [claude.ai](https://claude.ai) and create a new **Project**\n3. In project settings, click **\"Project Instructions\"** (Custom Instructions)\n4. Copy the **entire** content of `BABOK_AGENT/LLM_BABOK_AGENT/BABOK_Agent_LLM_Prompt.md` file and paste it into the Project Instructions field\n5. Start a new conversation in the project and type:\n   ```\n   BEGIN NEW PROJECT\n   ```\n\n### Method 2: VS Code with Claude Code (CLI)\n\n1. Clone the repository:\n   ```bash\n   git clone https://github.com/GSkuza/BABOK_ANALYST.git\n   cd BABOK_ANALYST\n   ```\n2. Install [Claude Code](https://docs.anthropic.com/en/docs/claude-code) (requires Node.js 18+):\n   ```bash\n   npm install -g @anthropic-ai/claude-code\n   ```\n3. Launch Claude Code in the project directory:\n   ```bash\n   claude\n   ```\n4. Claude will automatically load the configuration from `.github/copilot-instructions.md`\n5. Type:\n   ```\n   BEGIN NEW PROJECT\n   ```\n\n### Method 3: VS Code with GitHub Copilot Chat\n\n1. Clone the repository and open in VS Code:\n   ```bash\n   git clone https://github.com/GSkuza/BABOK_ANALYST.git\n   code BABOK_ANALYST\n   ```\n2. Make sure you have the **GitHub Copilot Chat** extension installed\n3. Copilot will automatically load instructions from `.github/copilot-instructions.md`\n4. Open Copilot Chat (Ctrl+Shift+I) and type:\n   ```\n   BEGIN NEW PROJECT\n   ```\n\n### Method 4: ChatGPT or other LLM\n\n1. Download the content of `BABOK_AGENT/LLM_BABOK_AGENT/BABOK_Agent_LLM_Prompt.md` file\n2. In ChatGPT: Settings -> \"Custom Instructions\" or \"System Prompt\"\n3. Paste the file content as system instructions\n4. Start a new conversation and type:\n   ```\n   BEGIN NEW PROJECT\n   ```\n\n### Method 5: API (Anthropic, OpenAI, others)\n\nUse the content of `BABOK_Agent_LLM_Prompt.md` as the `system` parameter in the API call:\n\n```python\nimport anthropic\n\nclient = anthropic.Anthropic()\n\nwith open(\"BABOK_AGENT/LLM_BABOK_AGENT/BABOK_Agent_LLM_Prompt.md\") as f:\n    system_prompt = f.read()\n\nmessage = client.messages.create(\n    model=\"claude-sonnet-4-6\",\n    max_tokens=8192,\n    system=system_prompt,\n    messages=[{\"role\": \"user\", \"content\": \"BEGIN NEW PROJECT\"}]\n)\n```\n\n---\n\n## BABOK CLI Tool\n\nThe repository includes a **cross-platform CLI tool** for managing project lifecycle directly from the terminal. The CLI handles project creation, state tracking via journal files, stage management, and **interactive AI chat** with multiple LLM providers — independently of any specific AI platform.\n\n### Installation\n\nRequires **Node.js 18+**.\n\n**Option A — one-click installer (recommended for non-technical users):**\n```bat\n# Windows\nsetup.bat\n\n# Linux / macOS\nchmod +x setup.sh && ./setup.sh\n```\n\n**Option B — manual:**\n```bash\ngit clone https://github.com/GSkuza/BABOK_ANALYST.git\ncd BABOK_ANALYST/cli\nnpm install\nnpm link        # Makes 'babok' command available globally\n```\n\nAfter manual install, run the setup wizard for first-time configuration:\n```bash\nbabok setup\n```\n\n### CLI Commands\n\n| Command | Description |\n|---------|-------------|\n| `babok setup` | **First-time setup wizard** — API keys, language, optional first project |\n| `babok new [--name \"Name\"]` | Create a new project with unique ID and timestamp |\n| `babok list` | List all projects with current status |\n| `babok status [id]` | Show detailed project status (all stages) |\n| `babok load <id>` | Load project context (generates text to paste into AI chat) |\n| `babok save <id>` | Save current project state snapshot |\n| `babok rename <id> [new-name]` | Rename a project |\n| `babok delete <id>` | Permanently delete a project with confirmation |\n| `babok approve <id> <stage>` | Mark a stage as approved, advance to next (stages 0–8) |\n| `babok reject <id> <stage> -r \"reason\"` | Reject a stage with reason |\n| `babok diff <id> [--stage N]` | Show stage history and deliverable preview |\n| `babok diff <id1> <id2> [--stage N]` | Line diff between two projects' deliverables |\n| `babok export <id>` | Export project deliverables to output directory |\n| `babok chat <id>` | **Interactive AI chat** for current stage |\n| `babok run [--context file.json]` | **Automated 8-stage pipeline** (interactive or `--auto`) |\n| `babok run --diagram` | Run pipeline with auto-generated Mermaid process diagrams (NEW v2.1.0) |\n| `babok ingest <file>` | **Ingest a document** (PDF/DOCX/XLSX/CSV/TXT/MD) into the project (NEW v2.1.0) |\n| `babok score <id> <stage\\|all>` | **Quality score** for a stage or all stages (NEW v2.1.0) |\n| `babok validate <id>` | **Cross-stage consistency validation** — 6 built-in rules (NEW v2.1.0) |\n| `babok make docx <id>` | Generate DOCX document(s) from stage files |\n| `babok make pdf <id>` | Generate PDF document(s) from stage files |\n| `babok make all <id>` | Generate DOCX + PDF in one run |\n| `babok llm list` | List all available AI models |\n| `babok llm change` | Interactively switch AI provider/model |\n| `babok lang [EN\\|PL]` | Set or show interface language |\n\n### Stage diff\n\nInspect and compare deliverables directly from the terminal:\n\n```bash\n# Show stage history + deliverable preview for a single project\nbabok diff K7M3\nbabok diff K7M3 --stage 3\n\n# Line-by-line diff between two project versions (e.g. rejected vs reworked)\nbabok diff K7M3 R9TN\nbabok diff K7M3 R9TN --stage 4 --context 5\n```\n\nThe two-project diff uses LCS to produce colored `+` / `-` output — no external tools needed.\n\n---\n\n### Document export (DOCX/PDF)\n\nIn addition to raw Markdown exports, the CLI can generate **CEO-ready DOCX and PDF** documents directly from stage files:\n\n```bash\n# DOCX only\nbabok make docx <project_id>\nbabok make docx <project_id> --stage 1      # only Stage 1\n\n# PDF only\nbabok make pdf <project_id>\n\n# DOCX + PDF in one run\nbabok make all <project_id>\n```\n\n- Works on `STAGE_XX_*.md` files generated by the agent\n- Applies professional corporate styling (tables, headings, headers/footers)\n- Default output directory: `<project_dir>/exports` (configurable via `--output`)\n\n### Quick Example\n\n```bash\n# First-time setup\nbabok setup\n\n# Create a new project\nbabok new --name \"ERP Integration\"\n# Output: Project ID: BABOK-20260208-K7M3\n\n# Check all projects\nbabok list\n\n# Approve Stage 1 after completing it in AI chat\nbabok approve K7M3 1\n\n# View detailed status\nbabok status K7M3\n\n# Load context for AI chat (copy & paste the output)\nbabok load K7M3\n\n# Start interactive AI chat for current stage\nbabok chat K7M3\n\n# Rename a project\nbabok rename K7M3 \"ERP Integration v2\"\n\n# Delete a project (prompts confirmation)\nbabok delete K7M3\n\n# Export deliverables when done\nbabok export K7M3\n```\n\nPartial IDs work — `babok status K7M3` matches `BABOK-20260208-K7M3`.\n\nFor the full CLI guide, see: [`cli/README.md`](cli/README.md)\n\n---\n\n## Document Ingestion (`babok ingest`) — NEW in v2.1.0\n\nThe `babok ingest` command allows you to feed existing documents into a project so the AI agent can use them as context during analysis. Supported formats: **PDF, DOCX, XLSX, CSV, TXT, MD**.\n\n```bash\n# Ingest a supplier contract into a project\nbabok ingest path/to/contract.pdf --project K7M3\n\n# Ingest an Excel data export\nbabok ingest data_export.xlsx --project K7M3\n```\n\n- Documents are parsed and classified by the LLM automatically\n- Ingested files are listed in `babok status` output\n- Source: `cli/src/commands/ingest.js` + `cli/src/lib/document-parser.js`\n\n---\n\n## Quality Scoring & Cross-Stage Validation — NEW in v2.1.0\n\n### `babok score` — Stage Quality Scorer\n\nScores a deliverable (or all stages) against a rubric with three dimensions:\n\n| Dimension | Weight | What It Checks |\n|-----------|--------|----------------|\n| **Completeness** | 40% | All required sections present |\n| **SMART quality** | 30% | Numeric targets, dates, currencies, ROI present |\n| **Consistency** | 30% | Cross-references match within the stage |\n\n```bash\nbabok score K7M3 1          # Score Stage 1 only\nbabok score K7M3 all        # Score all completed stages\n```\n\nOutput: color-coded score card in the terminal (chalk).\n\n### `babok validate` — Cross-Stage Consistency Validator\n\nValidates that all approved stages are internally consistent. Six built-in rules:\n\n| Rule | What It Checks |\n|------|----------------|\n| FR Traceability | All FR IDs in Stage 4 appear in the RTM |\n| Budget Ceiling | Stage 8 cost ≤ budget ceiling set in Stage 1 |\n| Integration Coverage | Every system in Stage 2 addressed in Stage 5 TO-BE |\n| KPI Coverage | Every KPI from Stage 1 measured in Stage 2 baseline |\n| Critical Risk Owner | Every HIGH risk in Stage 7 has an assigned owner |\n| Roadmap Date | Stage 6 go-live date does not precede Stage 1 hard deadline |\n\n```bash\nbabok validate K7M3         # Validates all approved stages; exits with code 1 on errors\n```\n\n---\n\n## Web UI (`web/`) — NEW in v2.1.0\n\nThe repository now ships a **Next.js 15 App Router** web interface for teams who prefer a browser-based workflow.\n\n### Features\n\n- **Dashboard** — lists all projects with stage progress bars\n- **New project form** — name + language selection\n- **Project detail view** — stage pipeline with status indicators\n- **Stage view** — renders deliverable Markdown + Approve / Reject buttons\n- **Export page** — one-click ZIP download of all stage deliverables\n- **Mermaid diagram viewer** — inline rendering of auto-generated process maps\n\n### Running the Web UI\n\n```bash\ncd web\nnpm install\nnpm run dev        # http://localhost:3000\n```\n\n### API Routes\n\n| Route | Method | Description |\n|-------|--------|-------------|\n| `/api/projects` | GET / POST | List or create projects |\n| `/api/projects/[id]` | GET | Get project detail + stage list |\n| `/api/projects/[id]/stages/[n]` | GET / POST | Read or save a stage deliverable |\n| `/api/projects/[id]/export` | GET | Download all deliverables as ZIP |\n\n---\n\n## Team Collaboration & File Locking\n\nWhen multiple analysts work on the **same project directory** (e.g. on a shared network drive), concurrent edits to the same stage can overwrite each other. v2.0.1 introduces **automatic file locking**:\n\n- When `babok chat` or `babok run` starts working on a stage, a lock file is created:\n  `<project_dir>/.stage_N.lock`\n- The lock file records: `locked_by`, `hostname`, `pid`, `locked_at`\n- If another user tries to open the same stage, they get a clear error:\n  ```\n  ⛔ Stage 3 is currently locked by another user:\n     anna@WORKSTATION-02 (PID 14872), locked 12 min ago\n  ```\n- Locks older than **2 hours** are automatically treated as stale and removed\n- Lock files are excluded from git (`.gitignore`)\n\n> **Recommendation:** Store the `projects/` directory on a shared network drive or sync folder for team use. Each analyst works on separate stages to avoid contention.\n\n---\n\n## MCP Server — `babok-mcp` (v2.2.x)\n\n> **The biggest differentiator.** Claude and other MCP-compatible AI assistants can now manage your BABOK project lifecycle _without leaving the chat interface_.\n\nThe `babok-mcp` package is a [Model Context Protocol](https://modelcontextprotocol.io) server that exposes **19 tools** and 9 resources to any compatible AI client.\n\n### Setup (Plugin install — recommended)\n\nIf you installed via the plugin marketplace (see above), MCP is wired automatically\nvia `.mcp.json` with `${CLAUDE_PLUGIN_ROOT}` paths. Run `/reload-plugins` after install.\n\n### Setup (Claude Desktop / manual Claude Code)\n\n**Windows (one-click):**\n```bat\ncd BABOK_ANALYST/babok-mcp\nsetup.bat\n```\n\n**Manual:**\n```bash\ncd BABOK_ANALYST/babok-mcp\nnpm install\n```\n\nAdd to `claude_desktop_config.json` (or `.claude/mcp.json` for Claude Code):\n\n```json\n{\n  \"mcpServers\": {\n    \"babok\": {\n      \"command\": \"node\",\n      \"args\": [\"D:/BABOK_ANALYST/babok-mcp/bin/babok-mcp.js\"],\n      \"env\": {\n        \"BABOK_PROJECTS_DIR\": \"D:/BABOK_ANALYST/projects\",\n        \"BABOK_AGENT_DIR\": \"D:/BABOK_ANALYST/BABOK_AGENT/stages\"\n      }\n    }\n  }\n}\n```\n\nRestart Claude Desktop — a 🔧 tool icon confirms the server is connected.\n\n### Available Tools\n\n| Tool | What it does |\n|------|-------------|\n| `babok_new_project` | Create a new project, get ID |\n| `babok_list_projects` | List all projects with stage + status |\n| `babok_get_stage` | Full stage context: prompt + journal + existing deliverable |\n| `babok_get_stage_template` | Load stage template skeleton (with optional modules) |\n| `babok_approve_stage` | Approve stage, advance to next |\n| `babok_submit_for_review` | Submit deliverable snapshot for human review (Two-Key key 1) |\n| `babok_open_revision` | Re-open an approved stage for edits |\n| `babok_get_deliverable` | Read a completed stage MD file |\n| `babok_save_deliverable` | Persist AI-generated content to project dir |\n| `babok_search` | Full-text search across all project files |\n| `babok_export` | Copy all deliverables to an export directory |\n| `babok_rename_project` | Rename a project |\n| `babok_delete_project` | Delete a project with explicit confirmation |\n| `babok_get_stage_artifact` | Read stage artefact file |\n| `babok_quality_check` | Score deliverable quality |\n| `babok_sync_stage_artifact` | Sync artefact to project |\n| `babok_create_jira_epic` | Create Jira epic from roadmap |\n| `babok_create_github_issues` | Create GitHub issues from roadmap |\n| `babok_read_external_context` | Read external context files |\n\n### Example flow in Claude\n\n```\nYou:    \"Start a new BABOK project for SAP integration at Acme Corp\"\n\nClaude: [babok_new_project → BABOK-20260316-K7M3]\n        [babok_get_stage stage_n=0 → loads Stage 0 Charter prompt]\n        → asks 3 questions about business trigger, sponsor, scope\n\nYou:    [answers]\n\nClaude: [babok_save_deliverable stage_n=0 content=\"...\"]\n        [babok_approve_stage stage_n=0]\n        → \"Stage 0 approved. Moving to Stage 1: Stakeholder Mapping.\"\n```\n\nFor the full MCP guide, see: [`babok-mcp/README.md`](babok-mcp/README.md)\n\n---\n\n## AI Chat in Terminal (`babok chat`)\n\nThe `babok chat` command starts an interactive AI conversation in the terminal, contextually aware of your project stage. It supports **5 LLM providers** — choose the one you prefer.\n\n### Supported Providers\n\n| Provider | Models | Get API Key |\n|----------|--------|-------------|\n| **Google Gemini** | `gemini-2.0-flash`, `gemini-2.0-flash-lite`, `gemini-1.5-flash` | [aistudio.google.com](https://aistudio.google.com/app/apikey) |\n| **OpenAI** | Models available to your API key (current fallback: `gpt-6-astra`, `gpt-5.6`, `gpt-5.6-terra`, `gpt-5.6-luna`) | [platform.openai.com](https://platform.openai.com/api-keys) |\n| **Anthropic Claude** | Models available to your API key (current fallback: `claude-fable-5-1`, `claude-opus-5`, `claude-sonnet-5`, `claude-haiku-4-5`) | [console.anthropic.com](https://console.anthropic.com/settings/keys) |\n| **Hugging Face** | `Qwen2.5-72B`, `Llama-3.3-70B`, `DeepSeek-R1`, `Bielik-11B` | [huggingface.co](https://huggingface.co/settings/tokens) |\n| **Google Vertex AI** | `gemini-2.5-pro-exp`, `gemini-2.0-flash` | [cloud.google.com](https://cloud.google.com/vertex-ai) |\n\n### Usage\n\n```bash\n# Interactive provider selection (first run)\nbabok chat K7M3\n\n# Specify provider and stage\nbabok chat K7M3 --provider openai --stage 3\n\n# Specify custom model\nbabok chat K7M3 --provider anthropic --model claude-sonnet-5\n\n# Use Hugging Face\nbabok chat K7M3 -p huggingface -m \"Qwen/Qwen2.5-72B-Instruct\"\n```\n\n### Chat Commands (inside session)\n\n| Command | Description |\n|---------|-------------|\n| `/exit`, `/quit` | End chat session (auto-saves, releases stage lock) |\n| `/save` | Save conversation to project |\n| `/clear` | Clear conversation history |\n| `/stage N` | Switch to stage N (1-8) |\n| `/status` | Show project status |\n| `/provider` | Show current provider & model |\n| `/llm` | Change AI provider/model mid-session |\n| `/key` | API key management info |\n| `/key clear [provider]` | Remove stored key(s) |\n| `/help` | Show all commands |\n\n### Features\n\n- **Streaming responses** — real-time output from LLM\n- **Stage context** — system prompt includes project info, stage instructions, decisions, and history\n- **Auto-save** — conversation saved every 5 messages and on exit\n- **Conversation history** — resume where you left off per stage\n- **Switch stages** — `/stage N` to jump between stages mid-session\n- **File locking** — stage locked on start, released on exit (prevents team conflicts)\n\n---\n\n## API Key Security\n\nAll API keys are secured and **never committed to the repository**.\n\n### Key Storage Hierarchy\n\n| Priority | Source | Security Level |\n|----------|--------|----------------|\n| 1 | Environment variable (`GEMINI_API_KEY`, `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `HF_API_KEY`) | Session-only, in memory |\n| 2 | `.env` file | Gitignored, plaintext local file |\n| 3 | `.babok_keystore` | Gitignored, **encrypted** with machine-specific key |\n| 4 | `babok setup` wizard | Prompted interactively, saved to keystore |\n\n### How It Works\n\n1. **First run**: run `babok setup` (or `setup.bat` / `setup.sh`) — wizard guides you through provider selection and key entry\n2. **Key encryption**: The key is XOR-encrypted using a SHA-256 hash derived from `hostname + username + working directory` — the encrypted file is **useless on another machine or repo clone**\n3. **Gitignored**: `.babok_keystore`, `.env`, and `.env.*` are all in `.gitignore`\n4. **No keys in config**: `agent_config.json` (tracked by git) contains **zero API keys**\n5. **Per-provider storage**: Each provider's key is stored independently — you can have keys for all 5 providers\n\n### Setting Up API Keys\n\n**Option A: Setup wizard (recommended)**\n```bash\nbabok setup\n# → Select language → select provider → paste key → test connection\n```\n\n**Option B: Environment variables**\n```bash\n# Windows PowerShell\n$env:OPENAI_API_KEY = \"sk-...\"\n$env:GEMINI_API_KEY = \"AI...\"\n$env:ANTHROPIC_API_KEY = \"sk-ant-...\"\n$env:HF_API_KEY = \"hf_...\"\n\n# Linux/macOS\nexport OPENAI_API_KEY=\"sk-...\"\n```\n\n**Option C: `.env` file** (gitignored)\n```env\nGEMINI_API_KEY=AI...\nOPENAI_API_KEY=sk-...\nANTHROPIC_API_KEY=sk-ant-...\nHF_API_KEY=hf_...\n```\n\n### Removing Stored Keys\n\n```bash\n# Inside chat session:\n/key clear              # Remove all stored keys\n/key clear openai       # Remove only OpenAI key\n\n# Or delete the keystore file directly:\n# Windows: del .babok_keystore\n# Linux:   rm .babok_keystore\n```\n\n---\n\n## Cloning the Repository\n\n### Requirements\n\n- **Git** installed on your computer ([installation guide](https://git-scm.com/downloads))\n- Optional: **VS Code** or other code editor\n\n### Cloning via HTTPS\n\n```bash\ngit clone https://github.com/GSkuza/BABOK_ANALYST.git\n```\n\n### Cloning via SSH\n\n```bash\ngit clone git@github.com:GSkuza/BABOK_ANALYST.git\n```\n\n### Cloning via GitHub CLI\n\n```bash\ngh repo clone GSkuza/BABOK_ANALYST\n```\n\n### Download ZIP (without Git)\n\n1. Go to https://github.com/GSkuza/BABOK_ANALYST\n2. Click the green **\"Code\"** button\n3. Select **\"Download ZIP\"**\n4. Extract the archive to your chosen location\n\n---\n\n## How to Work with the Agent\n\n### Communication Format\n\nThe agent asks questions in a structured format:\n\n```\nRATIONALE: [Concise conclusion with key assumptions]\nEVIDENCE: [Data source: Stage N, stakeholder input, industry standard]\n\nQUESTIONS FOR HUMAN:\n1. [Question 1]\n2. [Question 2]\n...\n\nWAIT FOR HUMAN INPUT.\n```\n\n### Sequential questions\n\nThe agent uses a **sequential questioning protocol** inside each stage:\n\n- Questions are asked **one-by-one** with a progress indicator (e.g. `STAGE 1 - QUESTION 1/5`, then `QUESTION 2/5`, etc.)\n- After each answer the agent shows a short confirmation, e.g. `✅ Answer recorded: [summary]`\n- Before generating the stage deliverable, the agent presents a **summary of all your answers** for that step/stage\n\nYou can control the flow using high-level commands:\n\n- `Next question` – skip current question and move to the next\n- `Previous question` – go back to the previous question (within the same step)\n- `Skip questions` – show all remaining questions at once (batch mode)\n\n### How to Respond\n\nRespond specifically, using question numbering:\n\n```\n1. YES - all documents in scope: invoices, delivery notes, orders\n2. ERP: SAP Business One v10.0\n3. Accounting: Comarch ERP Optima v2024.1\n4. We don't currently have a DMS\n5. KSeF deadline: July 1, 2026\n```\n\nIf you don't know something:\n\n```\nI DON'T KNOW - I need to check with [person/department]\n```\n\n### Control Commands\n\n| Command | Action |\n|---------|--------|\n| `BEGIN NEW PROJECT` | Start a new project with unique ID and timestamp |\n| `SAVE PROJECT` | Save project state (available after completing a stage) |\n| `LOAD PROJECT [project_id]` | Resume a saved project at the last active stage |\n| `Approve [N]` | Approve stage N and proceed to next |\n| `Reject [N] [reason]` | Reject stage N with reason |\n| `Status` | Display progress of all stages for current project |\n| `Pause` | Pause current session (auto-saves to journal) |\n| `Export all` | Export all completed stage deliverables |\n| `Deep analysis [topic]` | Activate deep reasoning for critical decisions |\n| `Help` | Show all available commands |\n\n---\n\n## Output Files\n\nEach project gets its own directory identified by a unique **Project ID** (e.g., `BABOK-20260208-M3R1`). The agent generates Markdown documents for each stage plus a persistent journal log.\n\n**Canonical storage (MCP, CLI, plugin):** `projects/<project_id>/`\n\n**Legacy CLI export default:** `BABOK_Analysis/` — only when using `babok run -o BABOK_Analysis`\n\n```\nprojects/\n└── BABOK-20260208-M3R1/                    # Project directory (unique per project)\n    ├── PROJECT_JOURNAL_BABOK-20260208-M3R1.json  # State tracking journal\n    ├── STAGE_00_Project_Charter.md\n    ├── STAGE_01_Project_Initialization.md\n    ├── STAGE_02_Current_State_Analysis.md\n    ├── STAGE_03_Problem_Domain_Analysis.md\n    ├── STAGE_04_Solution_Requirements.md\n    ├── STAGE_05_Future_State_Design.md\n    ├── STAGE_06_Gap_Analysis_Roadmap.md\n    ├── STAGE_07_Risk_Assessment.md\n    └── STAGE_08_Business_Case_ROI.md\n```\n\nThe **Project Journal** (`PROJECT_JOURNAL_*.json`) tracks all stage transitions, approvals, decisions, and assumptions — enabling exact state restoration with `LOAD PROJECT`.\n\n---\n\n## Estimated Timeline\n\n| Stage | Work with Agent | Internal Consultations | Total |\n|------|----------------|----------------------|-------|\n| Stage 1 | 30-45 min | 1-2 days | 1-2 days |\n| Stage 2 | 1-2 hours | 3-5 days | ~1 week |\n| Stage 3 | 45-60 min | 1-2 days | 2-3 days |\n| Stage 4 | 2-3 hours | 3-5 days | ~1 week |\n| Stage 5 | 1-2 hours | 2-3 days | 3-4 days |\n| Stage 6 | 1 hour | 1 day | 1-2 days |\n| Stage 7 | 45 min | 1 day | 1-2 days |\n| Stage 8 | 1-2 hours | 2-3 days | 3-5 days |\n| **TOTAL** | **8-12 hours** | **2-3 weeks** | **3-4 weeks** |\n\nMost of the time is not spent working with the agent, but gathering data from stakeholders and internal consultations.\n\n---\n\n## Best Practices\n\n**Do:**\n- Read RATIONALE + EVIDENCE sections - you'll understand the agent's logic\n- Be specific - \"average 50 invoices/month\" instead of \"a lot\"\n- Approve sections progressively - you don't have to wait for the entire stage\n- Correct immediately if the agent makes an error\n\n**Don't:**\n- Don't guess - say \"I DON'T KNOW\" if you don't know the answer\n- Don't skip questions - each one has a justification\n- Don't approve documents without reading them\n- Don't mix stages - complete one before moving to the next\n\n---\n\n## Troubleshooting\n\n| Problem | Solution |\n|---------|----------|\n| Agent doesn't understand response | Rephrase more specifically, provide example |\n| Agent asks about something you don't know | Respond \"I DON'T KNOW\" or mark as OPEN QUESTION |\n| Error in earlier response | `CORRECTION in [Section X.Y]: [error description and fix]` |\n| Document too technical | \"Simplify section [X] for non-technical audience\" |\n| Change requirement priority | \"Change requirement FR-015 from MUST to SHOULD. Reasoning: [...]\" |\n| Stage locked by another user | Wait for them to finish, or remove stale lock file after 2 h |\n| `babok` command not found | Run `setup.bat` (Windows) or `npm link` in `cli/` |\n\n---\n\n## Security and Privacy\n\n**Agent DOES NOT store:** passwords, API keys, bank account numbers, personal data (except roles).\n\n**Agent MAY store:** organizational structure, business processes, aggregated metrics, system names.\n\nThe agent is designed in compliance with GDPR, BABOK Code of Conduct, and ISO 27001 principles.\n\n---\n\n## Test Suite\n\nThe repository currently runs **106 automated tests** (native `node:test` runner, ESM) covering CLI workflow, templates, Two-Key gate, plugin manifests, hooks, and uninstall flow:\n\n| File | Tests | What It Covers |\n|------|-------|----------------|\n| `tests/unit/project.test.js` | 15 | Project ID generation, path resolution |\n| `tests/unit/journal.test.js` | 16 | Journal CRUD, stage transitions |\n| `tests/unit/two-key-gate.test.js` | 7 | Two-Key attestation guard and SHA checks |\n| `tests/unit/scoring.test.js` | 14 | Quality scorer rubric logic |\n| `tests/unit/validation.test.js` | 18 | Cross-stage validation rules |\n| `tests/unit/templates.test.js` | 13 | Stage template manifest and rubric alignment |\n| `tests/integration/cli-workflow.test.js` | 10 | End-to-end CLI workflow steps |\n| `tests/plugin-manifest.test.cjs` | 12 | Marketplace/plugin manifest integrity |\n| `tests/hooks.test.cjs` | 1 | Lifecycle hook wiring checks |\n| `tests/uninstall.test.cjs` | 1 | External state uninstall behavior |\n\nRun the tests:\n\n```bash\nnpm test\n```\n\n---\n\n## Additional Resources\n\n- [IIBA BABOK Guide v3](https://www.iiba.org/babok-guide/)\n- [IIBA Agile Extension](https://www.iiba.org/agile-extension/)\n- [BABOK Glossary](https://www.iiba.org/babok-guide/glossary/)\n- [`docs/`](docs/) — L2/L3 architecture, MCP tools specification, migration guide, workflow diagrams\n- [`templates/`](templates/) — Ready-to-use BRD, Risk Register, Stakeholder Analysis, User Story templates\n- [`knowledge/`](knowledge/) — 16 JSON benchmark, industry, regulatory, and anti-pattern reference files\n- [`CHANGELOG.md`](CHANGELOG.md) — full version history\n- [`RELEASE_NOTES.md`](RELEASE_NOTES.md) — detailed release notes per version\n\n---\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\nBABOK® is a registered trademark of the International Institute of Business Analysis (IIBA®).\nThis project is not officially endorsed by IIBA.\n\n---\n\n## Contributing\n\nContributions are welcome! Please feel free to submit:\n- Bug reports and feature requests via GitHub Issues\n- Pull requests for documentation improvements\n- Sample analysis templates (anonymized)\n- Translations to other languages\n\n---\n\n## Author\n\n**Grzegorz Skuza**\n- GitHub: [@GSkuza](https://github.com/GSkuza)\n- Repository: [BABOK_ANALYST](https://github.com/GSkuza/BABOK_ANALYST)\n\n---\n\n**Version:** 2.2.8  \n**Release Date:** July 2, 2026  \n**Last Updated:** 2026-07-02\n",
  "bytes": 45032,
  "sha": "df8b9b3e93636128fd763ea55b31b7b7a7780a37d3d3dcf7a62bb8d8bd24b952",
  "repo_slug": "gskuza/babok_analyst",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_gskuza_babok_analyst_b12dd562/readme"
}