{"id":"562508a0-73ef-44e4-9f69-a3fc5ce33826","slug":"vision-driven-design","kind":"skill","name":"vision-driven-design","summary":"Spec-driven development MCP server for AI coding agents — 8 phases, bi-directional traceability, and 7 quality gates, 15 tools over Streamable HTTP (MIT)","owner":"simonmak-ascent","repoUrl":"https://github.com/simonmak-ascent/vision-driven-design","license":"MIT","licenseTier":"permissive","trust":"community","stars":1,"match":null,"fewStars":true,"format":"skill","createdAt":"2026-08-09T13:44:13.000Z","addedAt":"2026-10-14T06:04:10.823Z","logoUrl":"https://avatars.githubusercontent.com/u/246365505?u=24fc19ed666de5b309728533facb9e38f71b5429&v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["cloud-infra","data-analytics","design-media"],"tags":["opencode-skill","sdd","software-methodology","spec-driven-development","bi-directional-traceability","vision-driven-design","ai-agents","audit"],"runtime":"binary","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-15T00:54:33.277Z","sample":false,"url":"https://conduits.dev/tools/vision-driven-design","language":"TypeScript","transports":["stdio"],"install":{},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"# Vision Driven Design\n\n<!-- mcp-name: com.ascent-partners/vision-driven-design -->\n\n> **From vision to verified impact** — an AI-native, fully autonomous software development methodology.\n\n[![VDD Quality Gates](https://github.com/simonmak-ascent/vision-driven-design/actions/workflows/vdd-quality-gates.yml/badge.svg)](https://github.com/simonmak-ascent/vision-driven-design/actions/workflows/vdd-quality-gates.yml)\n[![MCP Tool Definition Quality](https://github.com/simonmak-ascent/vision-driven-design/actions/workflows/tdqs.yml/badge.svg)](https://github.com/simonmak-ascent/vision-driven-design/actions/workflows/tdqs.yml)\n[![MCP Registry](https://img.shields.io/badge/MCP%20Registry-com.ascent-partners%2Fvision-driven-design-4CAF50)](https://registry.modelcontextprotocol.io/v0/servers?search=com.ascent-partners/vision-driven-design)\n[![Glama MCP](https://glama.ai/mcp/servers/simonmak-ascent/vision-driven-design/badges/score.svg)](https://glama.ai/mcp/servers/simonmak-ascent/vision-driven-design)\n[![Agent Status](https://wdmisgfkoimdpvvduebj.supabase.co/functions/v1/mcp-badge?slug=vdd)](https://agentstatus.dev/mcp-index/vdd)\n[![Version](https://img.shields.io/badge/version-1.9.2-blue)](https://github.com/simonmak-ascent/vision-driven-design/releases)\n[![MCP tools](https://img.shields.io/badge/MCP-15%20tools-4CAF50)](https://vdd.simonmak.com/api/mcp)\n[![API](https://img.shields.io/badge/API-vdd.simonmak.com-006b7d)](https://vdd.simonmak.com)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n\n## Overview\n\nProvide a human vision statement. The AI autonomously researches, audits your codebase, generates specs and plans, implements, and validates — with **bi-directional verification** at every junction to ensure nothing is missed or invented.\n\n---\n\n```mermaid\ngraph LR\n    V[1. Vision<br/>Human Input] -->|<-->| S[2. Strategy<br/>AI Research]\n    S -->|<-->| T[3. Tactics<br/>AI Audit]\n    T -->|<-->| SP[4. Specs<br/>SDD]\n    SP -->|<-->| PL[5. Plan]\n    PL -->|<-->| TK[6. Tasks]\n    TK -->|<-->| IM[7. Implement]\n    IM -->|<-->| VS[8. Validate<br/>Impact Verified]\n\n    style V fill:#4CAF50,color:#fff\n    style S fill:#2196F3,color:#fff\n    style T fill:#FF9800,color:#fff\n    style SP fill:#9C27B0,color:#fff\n    style VS fill:#4CAF50,color:#fff\n```\n\n---\n\n## Table of Contents\n\n- [Quick Start](#quick-start)\n- [How It Works](#how-it-works)\n- [Commands](#commands)\n- [Installation](#installation)\n- [MCP API](#mcp-api)\n- [Domains Covered](#domains-covered)\n- [Best-Practice Benchmark](#best-practice-benchmark)\n- [Documentation](#documentation)\n- [Repository Structure](#repository-structure)\n- [Credits](#credits)\n- [License](#license)\n\n---\n\n## Quick Start (≤ 5 minutes)\n\n**Fastest path:** no install — connect an MCP client to the hosted endpoint\n`https://vdd.simonmak.com/api/mcp` (Streamable HTTP); or run the one-line install below.\n\n```bash\n# One-line install\ncurl -sSL https://raw.githubusercontent.com/simonmak-ascent/vision-driven-design/main/scripts/install.sh | bash\n```\n\nThen in your project:\n\n```bash\n/vdd:init                          # Generate project constitution\n/vdd:vision \"your vision here\"     # The only human input required\n\n# Or run end-to-end in one command:\n/vdd:e2e \"your vision here\"        # Full chain: init→vision→...→validate\n```\n\nThe AI handles the rest — researching, auditing, generating specs, planning, implementing, and validating — with self-gating at 7 bi-directional verification junctions.\n\n**[Skill reference →](SKILL.md)** — commands, the 8-phase chain, and the quality gates.\n\n```bash\n# Want human gates? Add to constitution.md:\n## VDD Mode: Gated\n```\n\n---\n\n## How It Works\n\nVDD follows Goldratt's **recursive Strategy-Tactic decomposition**: every phase is simultaneously the **Tactic** for its parent and the **Strategy** for its child.\n\n| Phase | S&T Role | Output |\n|-------|----------|--------|\n| **0. Constitution** | (pre-chain) | `constitution.md` — Immutable project rules |\n| **1. Vision** | L1 Strategy: What impact? | `vision.md` — Impact model, success metrics |\n| **2. Strategy** | L1 Tactic → L2 Strategy | `strategy.md` — Research, 12 pillars, risk register |\n| **3. Tactics** | L2 Tactic → L3 Strategy | `tactics.md` — Codebase audit, 38 action items |\n| **4. Specs** | L3 Tactic → L4 Strategy | `spec.md` — MoSCoW acceptance criteria |\n| **5. Plan** | L4 Tactic → L5 Strategy | `plan.md`, `data-model.md`, `contracts/` |\n| **6. Tasks** | L5 Tactic → L6 Strategy | `tasks.md` — Test-first atomic tasks |\n| **7. Implement** | L6 Tactic → L7 Strategy | Code — Per-task commits with full traceability |\n| **8. Validate** | L7 Tactic — Did it work? | `impact-report.md` — Drift + impact verification |\n\n**7 bi-directional gates** verify both directions at every junction (108 total checks). Each gate validates 4 S&T assumptions: Necessity, Achievability, Sufficiency, Warnings.\n\nEvery code commit traces back to the original vision statement:\n```\nV-001 → S-002 → T-003 → SP-004 → PL-005 → TK-006 → commit\n```\n\n### The pipeline and its 7 gates\n\n```mermaid\nflowchart TB\n    C[\"Phase 0 · Constitution<br/>constitution.md\"] --> V[\"Phase 1 · Vision<br/>vision.md\"]\n    V -.->|G1| S[\"Phase 2 · Strategy<br/>strategy.md\"]\n    S -.->|G2| T[\"Phase 3 · Tactics<br/>tactics.md\"]\n    T -.->|G3| SP[\"Phase 4 · Specs<br/>spec.md\"]\n    SP -.->|G4| PL[\"Phase 5 · Plan<br/>plan.md · data-model · contracts\"]\n    PL -.->|G5| TK[\"Phase 6 · Tasks<br/>tasks.md\"]\n    TK -.->|G6| I[\"Phase 7 · Implement<br/>code + per-task commits\"]\n    I -.->|G7| VA[\"Phase 8 · Validate<br/>impact-report.md\"]\n```\n\n### Bi-directional traceability\n\nEach gate checks **forward** (parent → children) and **backward** (children → parent),\n108 checks in total.\n\n```mermaid\nflowchart LR\n    subgraph F[\"Forward: intent → code\"]\n      direction LR\n      V1[\"Vision V-*\"] --> S1[\"Strategy S-*\"] --> T1[\"Tactics T-*\"] --> SP1[\"Spec SP-*\"] --> PL1[\"Plan PL-*\"] --> TK1[\"Tasks TK-*\"] --> C1[\"Commit\"]\n    end\n    subgraph B[\"Backward: code → intent\"]\n      direction LR\n      C2[\"Commit\"] --> TK2[\"Tasks TK-*\"] --> PL2[\"Plan PL-*\"] --> SP2[\"Spec SP-*\"] --> T2[\"Tactics T-*\"] --> S2[\"Strategy S-*\"] --> V2[\"Vision V-*\"]\n    end\n```\n\n### Change cascade\n\n```mermaid\nflowchart TB\n    CH[\"Requirement change<br/>/vdd:amend\"] --> FIND[\"Find the highest affected level\"]\n    FIND --> U1[\"Update Vision\"] --> U2[\"Update Strategy\"] --> U3[\"Update Tactics\"] --> U4[\"Update Specs\"] --> U5[\"Update Plan\"] --> U6[\"Update Tasks\"]\n    U6 --> REG[\"Re-run affected gates G1–G7\"]\n    REG --> IMPL[\"Re-implement only the changed tasks\"]\n```\n\n---\n\n## Commands\n\n| Command | Phase | Action |\n|---------|-------|--------|\n| `/vdd:init` | 0 | Generate `constitution.md` from project context |\n| `/vdd:vision \"statement\"` | 1 | Expand freeform vision → structured `vision.md` |\n| `/vdd:strategize` | 2 | Load domain primers, spawn research subagents, synthesize `strategy.md` |\n| `/vdd:tactics` | 3 | Audit repo → gap analysis → `tactics.md` |\n| `/vdd:specify <ID \\| \"desc\">` | 4 | Generate `spec.md` (or freeform — skips V/S/T) |\n| `/vdd:clarify <feature>` | 4 | Clarification pass on a spec |\n| `/vdd:plan <feature>` | 5 | Generate `plan.md`, `data-model.md`, `contracts/` |\n| `/vdd:tasks <feature>` | 6 | Generate `tasks.md` |\n| `/vdd:get-next-task <feature>` | 7 | Extract next uncompleted task |\n| `/vdd:implement <task-id>` | 7 | Execute single task, verify, commit |\n| `/vdd:validate` | 8 | Full-chain traceability + drift + impact report |\n| `/vdd:trace` | any | Bidirectional traceability matrix |\n| `/vdd:analyze <feature>` | any | Cross-artifact consistency analysis |\n| `/vdd:amend \"what changed\"` | any | Cascade requirement change through full chain |\n| `/vdd:detect-environment` | any | Report per-phase tool/MCP requirements + available capabilities |\n| `/vdd:e2e \"vision statement\"` | 0–8 | **End-to-end**: run full 8-phase chain in one call, writes all 10+ template files |\n| `/vdd:e2e -clone <domain>` | 7 | **Clone**: crawl site (browserless/fetch) into a full dataset + exact UI/UX + rebuilt backend + generated schema + AI tools + deployable dynamic site (vdd/clone-site/) from a domain (https/http/www/bare) |\n\n---\n\n## Installation\n\n```bash\n# OpenCode\ngit clone https://github.com/simonmak-ascent/vision-driven-design.git \\\n  ~/.config/opencode/skills/vision-driven-design/\n\n# Claude Code\ngit clone https://github.com/simonmak-ascent/vision-driven-design.git \\\n  ~/.claude/skills/vision-driven-design/\n\n# Cursor\ngit clone https://github.com/simonmak-ascent/vision-driven-design.git \\\n  .cursor/skills/vision-driven-design/\n```\n\n### Local MCP (from source)\n\nTo run the MCP server locally (stdio) instead of the hosted endpoint:\n\n```bash\n# 1. Clone the repo\ngit clone https://github.com/simonmak-ascent/vision-driven-design.git\n\n# 2. Install deps + build the TypeScript packages\ncd vision-driven-design\npnpm install\npnpm -r build\n\n# 3. Point your agent at the built stdio entry point\n```\n\n**OpenCode** (`opencode.json`):\n```json\n\"vdd\": {\n  \"type\": \"local\",\n  \"command\": [\"node\", \"<repo>/packages/vdd-mcp/dist/stdio.js\"],\n  \"enabled\": true\n}\n```\n\n**Claude Desktop** (`claude_desktop_config.json`):\n```json\n\"vdd\": {\n  \"command\": \"node\",\n  \"args\": [\"<repo>/packages/vdd-mcp/dist/stdio.js\"],\n  \"type\": \"stdio\"\n}\n```\n\n---\n\n## MCP API\n\nVDD is available as a public MCP server at `https://vdd.simonmak.com` — 15 tools, no API key required — over the MCP **Streamable HTTP** transport at `https://vdd.simonmak.com/api/mcp` (also reachable at `/mcp`). The legacy SSE endpoint is retired: `https://vdd.simonmak.com/api/sse` now returns an HTTP 308 redirect to `/api/mcp`.\n\n### Agent Configuration\n\n**OpenCode** — add to `opencode.json`:\n```json\n\"vdd\": {\n  \"type\": \"remote\",\n  \"url\": \"https://vdd.simonmak.com/api/mcp\",\n  \"timeout\": 120000\n}\n```\n\n**Claude Desktop** — add to `claude_desktop_config.json`:\n```json\n\"vdd\": {\n  \"command\": \"npx\",\n  \"args\": [\"-y\", \"@simonmak-ascent/mcp\"],\n  \"type\": \"stdio\"\n}\n```\n\n**Cursor** — add MCP server URL: `https://vdd.simonmak.com/api/mcp`\n\n**Any Streamable HTTP client** (Smithery, Claude Code, …) — MCP server URL: `https://vdd.simonmak.com/api/mcp`\n\n### MCP Tools (15)\n\n`vdd_init`, `vdd_vision`, `vdd_strategize`, `vdd_tactics`, `vdd_specify`, `vdd_clarify`, `vdd_plan`, `vdd_tasks`, `vdd_get_next_task`, `vdd_implement`, `vdd_validate`, `vdd_inspect`, `vdd_amend`, `vdd_clone`, `vdd_detect_environment`.\n\nThe one-call `e2e` shortcut is not an MCP tool (it duplicates the phase sequence); use the CLI `vdd e2e \"vision\"` instead.\n\nEach tool advertises only the parameters it reads. Shared inputs include `statement`, `projectRoot`, `actionItemId`, `feature`, `taskId`, `description`, and `availableTools`/`capabilities` (aliases) plus `researchFindings`. Filesystem-dependent tools additionally accept `artifactFiles` (path→content) — and `vdd_tactics` accepts `codebaseAudit` — for the hosted endpoint.\n\n### Hosted vs local (filesystem)\n\nThe hosted endpoint (`https://vdd.simonmak.com/api/mcp`) is **stateless and has no filesystem**. It returns artifacts and, for filesystem-dependent phases, a **delegation envelope** for the calling agent to execute locally:\n\n- Artifact-producing phases (`vdd_init`, `vdd_vision`, `vdd_strategize`, `vdd_tactics`, `vdd_specify`, `vdd_plan`, `vdd_tasks`, `vdd_validate`, `vdd_clone`) return their content with `persisted: false` and a `writeTargets` list — the agent writes them.\n- Read phases (`vdd_tactics`, `vdd_clarify`, `vdd_get_next_task`, `vdd_inspect`, `vdd_validate`, `vdd_implement`) return a `delegation` envelope when given no content; re-call the **same tool** with `artifactFiles` (and `codebaseAudit` for tactics) to receive the real result.\n\nFor direct read/write of a local project, run the **local stdio server** instead — `npx -y @simonmak-ascent/mcp` (see [Local MCP](#local-mcp-from-source)). It performs real filesystem I/O and returns `mode: \"local\"`, `persisted: true`.\n\n\n### MCP Prompts (3)\n\n`start_vdd_project` (vision → validated task list), `implement_next_task` (one test-first task with traceability) and `change_requirement` (cascade a change and re-run the gates). Available on the stdio server and the hosted endpoint.\n\n### MCP Registry (Glama)\n\nThe server is listed on [Glama](https://glama.ai/mcp/servers/simonmak-ascent/vision-driven-design), which builds it from source and publishes a hosted remote endpoint plus a **Tool Definition Quality Score** and maintenance rating:\n\n<a href=\"https://glama.ai/mcp/servers/simonmak-ascent/vision-driven-design\"><img src=\"https://glama.ai/mcp/servers/simonmak-ascent/vision-driven-design/badges/card.svg\" alt=\"Glama quality and maintenance score\"></a>\n\nMaintainer notes:\n\n- `glama.json` (repo root) is Glama's registry file. Its [schema](https://glama.ai/mcp/schemas/server.json) consumes exactly one field — `maintainers`. Build/transport/description metadata belongs in `package.json` and this README, **not** here; Glama ignores it.\n- Glama generates its own container build from the stdio entrypoint (`packages/vdd-mcp/dist/stdio.js`), wrapped with `mcp-proxy`. The root `Dockerfile` is for **self-hosting** the Streamable HTTP server, not for Glama.\n- After tool-definition changes: sync the repository and run **Build & Release** in the Glama admin. Tool-level scores refresh on the next sweep; the server-level *coherence* score re-runs less often.\n- Also published to the [**Official MCP Registry**](https://registry.modelcontextprotocol.io) as `com.ascent-partners/vision-driven-design` (manifest: `server.json`) — PulseMCP and other directories ingest from there.\n- Listed in the [`awesome-mcp-servers`](https://github.com/punkpeye/awesome-mcp-servers) community list under Developer Tools.\n- Listed on [**Agent Status**](https://agentstatus.dev/mcp-index/vdd) — an outside-in MCP reliability index that probes reach, catalog, and tool calls from real hosts (Cursor, Claude, VS Code, ChatGPT). The submission created the Free dashboard account; the score populates after the first probe.\n\n  <a href=\"https://agentstatus.dev/mcp-index/vdd\"><img src=\"https://wdmisgfkoimdpvvduebj.supabase.co/functions/v1/mcp-badge?slug=vdd\" alt=\"Agent Status MCP reliability score\"></a>\n\n### API Reference\n\n| Method | Description |\n|--------|-------------|\n| POST `/api/mcp` | Streamable HTTP — JSON-RPC `initialize`, `tools/list`, `tools/call` (stateless) |\n| GET `/api/mcp` | HTML docs page for browsers; 405 for MCP clients (no server-initiated stream) |\n| DELETE `/api/mcp` | 204 — no session state to terminate |\n| `/api/sse` | Retired — HTTP 308 redirect to `/api/mcp` |\n\n```bash\n# Streamable HTTP call example\ncurl -X POST https://vdd.simonmak.com/api/mcp \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Accept: application/json, text/event-stream\" \\\n  -d '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"tools/list\"}'\n```\n\n```bash\n# tools/call example\ncurl -X POST https://vdd.simonmak.com/api/mcp \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"jsonrpc\":\"2.0\",\"method\":\"tools/call\",\"params\":{\"name\":\"vdd_validate\",\"arguments\":{\"projectRoot\":\".\"}},\"id\":1}'\n```\n\nThe full TypeScript engine (`packages/vdd-engine`, `packages/vdd-mcp`, `packages/vdd-cli`) is included in this repo.\n\n---\n\n## Domains Covered\n\nVDD loads domain-specific research patterns during the Strategy phase based on your vision:\n\n| Domain | What it covers |\n|--------|---------------|\n| **WebApp** | UX, accessibility (WCAG 2.2), performance budgets, framework evaluation |\n| **Data Storage** | Schema design, indexing strategy, data governance, ACID vs eventual |\n| **ETL** | Pipeline architecture, data quality, batch vs streaming |\n| **Infrastructure** | CI/CD, observability, security, scaling, disaster recovery |\n| **Human Factors** | Behavioral economics, cognitive load, habit formation, accessibility cognition |\n| **Verification Toolchain** | Playwright, Browserless, Sentry, CI/CD quality pipeline |\n| **Safety-Critical** | FMEA/FTA, DO-178C/IEC 62304 safety integrity levels |\n\n`human-factors.md` and `verification-toolchain.md` are loaded unconditionally for every project.\n\n---\n\n## Best-Practice Benchmark\n\nVDD is benchmarked against NASA SE, CMMI REQM, DO-178C, IEC 62304, DORA, ISO 29148, and GitHub Spec Kit:\n\n**47/47 criteria matched (100%), 11 exceeded, 0 gaps.**\n\n[Standards & compliance evidence →](references/compliance-evidence.md)\n\n---\n\n## Documentation\n\n| File | Contents |\n|------|----------|\n| [`SKILL.md`](SKILL.md) | Full command reference and workflow |\n| [`docs/deployment.md`](docs/deployment.md) | Local stdio / HTTP / hosted modes and the delegation contract |\n| [`references/workflow-phases.md`](references/workflow-phases.md) | Step-by-step phase instructions (authoritative) |\n| [`references/artifact-templates.md`](references/artifact-templates.md) | Copy-paste templates for all 11 artifacts |\n| [`references/quality-gates.md`](references/quality-gates.md) | 7 gates with 108 checks + CI/CD |\n| [`references/anti-patterns.md`](references/anti-patterns.md) | 24 failure modes and fixes |\n| [`references/compliance-evidence.md`](references/compliance-evidence.md) | DO-178C/IEC 62304/CMMI/ISO 29148 evidence maps |\n| [`references/clone-workflow.md`](references/clone-workflow.md) | Website cloning — crawl → dataset → deployable dynamic site |\n| [`references/quick-reference.md`](references/quick-reference.md) | One-page cheat sheet |\n\n---\n\n## Repository Structure\n\n```\n├── SKILL.md                         # Entry point — loaded by OpenCode\n├── README.md                        # This file\n├── AGENTS.md                        # Instructions for AI agents\n├── constitution.md                  # Project constitution (dogfooded)\n├── CHANGELOG.md                     # Versioned change history\n├── CONTRIBUTING.md                  # Contribution guidelines\n├── LICENSE                         # MIT\n├── index.html                       # Vercel landing page (en / zh / hk)\n├── pnpm-workspace.yaml              # Workspace config\n├── package.json                     # Root package (Vercel + workspace)\n├── vercel.json                      # Vercel deployment config\n├── Dockerfile                       # Self-host build — Streamable HTTP MCP server\n├── glama.json                       # Glama registry file (maintainers only)\n├── server.json                      # Official MCP Registry manifest\n├── domain-primers/                  # 7 domain research patterns\n│   ├── webapp.md\n│   ├── data-storage.md\n│   ├── etl.md\n│   ├── infrastructure.md\n│   ├── human-factors.md             # Loaded unconditionally\n│   ├── verification-toolchain.md    # Loaded unconditionally\n│   └── safety-critical.md           # FMEA/FTA, DO-178C/IEC 62304\n├── references/                      # 10 authoritative reference docs\n│   ├── INDEX.md                     # Navigation map\n│   ├── quick-reference.md           # 1-page cheat sheet\n│   ├── workflow-phases.md           # Phase order (authoritative)\n│   ├── artifact-templates.md        # 11 artifact templates (authoritative)\n│   ├── prompt-patterns.md           # AI prompts (authoritative)\n│   ├── quality-gates.md             # 7 gates + 108 checks (authoritative)\n│   ├── ai-agent-patterns.md         # Agent orchestration (authoritative)\n│   ├── anti-patterns.md             # 24 failure modes (authoritative)\n│   ├── traceability-matrix.md       # RTM format + CI/CD\n│   └── compliance-evidence.md       # Evidence maps\n├── vdd/                             # VDD chain artifacts\n│   ├── vision.md                    # Vision, impact model, 17 impacts\n│   ├── strategy.md                  # 12 strategic pillars\n│   ├── tactics.md                   # 38 action items (all DONE)\n│   ├── impact-report.md             # Full-chain traceability + drift\n│   ├── docs/                        # 16 guides and references\n│   └── specs/                       # 3 feature specs\n├── packages/                        # TypeScript monorepo\n│   ├── vdd-engine/                  # Shared core — 18 phase functions + meta.ts\n│   ├── vdd-mcp/                     # MCP server — 15 tools, stdio + Streamable HTTP\n│   └── vdd-cli/                     # CLI binary — 17 subcommands\n├── api/                             # Vercel MCP endpoint\n│   ├── mcp.js                       # Streamable HTTP MCP endpoint (15 tools)\n│   └── _vdd-rpc.js                  # Shared JSON-RPC core + browser docs page (not routed)\n├── scripts/                         # 4 installer/helper scripts\n└── .github/                         # GitHub config\n    ├── CODEOWNERS\n    ├── ISSUE_TEMPLATE/\n    └── workflows/\n```\n\n## Acknowledgements\n\nBuilt on:\n- **Goldratt's Strategy-and-Tactic Tree** — recursive decomposition at every phase\n- **Impact Mapping** (Gojko Adzic) — goal → actors → impacts → deliverables\n- **GitHub Spec Kit** — spec-driven development with AI agents\n- **NASA Systems Engineering** — bidirectional traceability and verification chains\n- **CMMI Requirements Management** — bidirectional traceability of requirements\n\n## Use with Context7\n\nUp-to-date Vision Driven Design documentation is indexed on [Context7](https://context7.com/simonmak-ascent/vision-driven-design), so coding agents can pull it into context on demand. With the Context7 MCP server or `ctx7` CLI installed, name the library in your prompt:\n\n```text\nuse library /simonmak-ascent/vision-driven-design for API and docs\n```\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n\n---\n\nBy [Simon Mak](https://github.com/simonmak-ascent).\n\nIf this saves you time, a ⭐ on GitHub helps others find it.\n"}