Stream Coding v3.5

The 10-20x Methodology for AI-Accelerated Software Development

📢 v3.5 Update: Phase 2.5 Adversarial Review added, internal gate renamed Spec Gate (structural), Clarity Gate is now a standalone epistemic tool. Re-download if using older version.

✅ This methodology built 7 production modules in 4.5 hours (5Levels Case Study, Git-verified)

"Stream coding isn't about faster coding. It's about documentation so clear that code writes itself."

The Problem: The Velocity Mirage

AI tools promise 10x productivity. GitHub Copilot, Cursor, Claude Code—they make coding 55% faster.

But projects still take the same time to ship.

Why? Because faster typing doesn't solve:

• Strategic decisions AI can't make for you
• Context that gets lost between prompts
• Technical debt created at 10x speed

This gap between task velocity and project velocity is the Velocity Mirage.

The Solution: Stream Coding

Stream Coding is a documentation-first methodology that makes AI-generated code deterministic.

The 40/40/5/10/5 Split:

• 40% Strategic Thinking (Phase 1) — Solve hard problems before coding
• 40% AI-Ready Documentation (Phase 2) — Specs so complete AI has zero decisions
• 5% Adversarial Review (Phase 2.5) — Different AI attacks the specs before coding
• 10% Execution (Phase 3) — Code streams out automatically
• 5% Quality (Phase 4) — Tests and verification

Real Results (5Levels Case Study):

• 7 production modules in 4.5 hours
• 46 intelligence endpoints (77 total backend API)
• Zero bugs in generated code, 21 minutes average per tested module

Note: The case study focuses on backend intelligence modules—Stream Coding's sweet spot. For frontend, use the methodology for behavior (components, state, logic) and complement with AI design tools for visuals. See Chapter 4 for details.

Quick Start

Option 1: Claude.ai / Claude Desktop

1. Download stream-coding.skill
2. Go to Settings → Features → Skills → Add
3. Upload the .skill file
4. Ask Claude: "Build a user authentication system"

Option 2: Claude Code

Clone the repo — Claude Code auto-detects skills in .claude/skills/:

git clone https://github.com/frmoretto/stream-coding
cd stream-coding
# Claude Code will automatically detect .claude/skills/stream-coding/SKILL.md

Or copy .claude/skills/stream-coding/ to your project's .claude/skills/ directory.

Ask Claude: "Build a user authentication system"

Option 3: Claude Projects

Add SKILL.md to project knowledge. Claude will search it when needed, though Skills provide better integration.

Option 4: OpenAI Codex / GitHub Copilot

Copy the canonical skill to the appropriate directory:

Use skills/stream-coding/SKILL.md (agentskills.io format).

Option 5: Manual / Other LLMs

For Cursor, Windsurf, or other AI tools:

• Extract core principles (Phases, Document Types, Spec Gate)
• Create a condensed version for .cursorrules or project settings
• Use the templates and Spec Gate Checklist as reference

The methodology is tool-agnostic—only SKILL.md is Claude-optimized.

Read the Manifesto

The /manifesto folder contains the complete methodology:

Use the Templates

The /templates folder contains ready-to-use frameworks:

The Core Insight

"When code fails, fix the spec—not the code."

Traditional development iterates on code. Stream Coding iterates on documentation.

Every manual code edit without updating the spec creates Divergence—technical debt that breaks the stream. The methodology works because it treats code as a compiled output of documentation, not the source of truth.

Who This Is For

• ✅ Technical founders building greenfield products
• ✅ Solo developers and small teams (1-5 people)
• ✅ Anyone tired of AI-generated spaghetti code
• ✅ Backend/business logic focused (see Chapter 4 for frontend approach)

• ❌ Not for large enterprises (see GitHub Spec-Kit, Kiro, Gemini Conductor)
• ❌ Not for teams who can't commit to documentation-first

Where Stream Coding Fits

┌─────────────────────────────────────────────────────────────────┐
│  AI-Assisted Development Landscape                              │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│  Layer 3: Enterprise SDD    GitHub Spec-Kit, Kiro, Conductor    │
│           (teams 50+)       Full lifecycle, heavy process       │
│                                                                 │
│  Layer 2: Founder SDD  ◄──  STREAM CODING                       │
│           (teams 1-5)       Documentation-first, AI-ready specs │
│                                                                 │
│  Layer 1: AI Assistants     Copilot, Cursor, Claude Code        │
│           (task-level)      Fast typing, no methodology         │
│                                                                 │
│  Layer 0: Manual Coding     Traditional development             │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

The Gap: Layer 1 tools make coding 55% faster but don't solve the methodology problem. Enterprise tools (Layer 3) are overkill for founders. Stream Coding fills the middle.

Competitive Positioning

Research Validation

Stream Coding aligns with industry research:

• McKinsey (2025): Top performers see 16-30% productivity gains through "end-to-end PDLC implementation" and "structured communication of specs"
• DORA (2025): 7.2% delivery instability increase for every 25% AI adoption without foundational systems
• METR (2025): Developers 19% slower with AI despite feeling 20% faster

The methodology isn't magic, it's systematic application of spec-driven development at founder scale.

Related

Clarity Gate — Pre-ingestion verification for epistemic quality (originated from Stream Coding's Clarity Gate concept) github.com/frmoretto/clarity-gate

Source of Truth Creator — Create epistemically calibrated documents github.com/frmoretto/source-of-truth-creator

Roadmap

Contributing

Stream Coding is open source under CC BY 4.0. You're free to use, adapt, and share with attribution.

Looking for:

1. Real-world case studies — Applied Stream Coding to your project?
2. Tool integrations — Cursor, Windsurf, other AI tools
3. Methodology feedback — Are the 5 phases the right split?
4. Template improvements — Better Strategic Blueprint, ADR formats

Open an issue or PR.

About

Created by Francesco Marinoni Moretto while building 5Levels, a LinkedIn relationship intelligence platform.

The methodology emerged from building 7 production modules in 4.5 hours, and documenting exactly how.

License

CC BY 4.0 — Use freely with attribution.

"Stream Coding methodology by Francesco Marinoni Moretto (github.com/frmoretto/stream-coding)"

In memory of my beloved father Guido