#spec-driven-development

Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deterministic spec passes, and there is no "done" without live acceptance evidence. Spec-first, verification-gated, forbidden-paths enforced.

Fast-ASDLC: 5x TTM with AI-native Agentic SDLC. Local-LLM first, Human-in-the-loop, Spec-driven. Built on DDD, Hexagonal Architecture, C4 Model & MCP. Features Meta-agents for self-improvement, Memory Bank for context persistence, and automated 100% test coverage. Everything-as-Code & Mermaid.js centric to save context window and slash token costs.

Spec-first, cross-harness SDLC skills framework — one director, AI agents, a living spec spine

A Spec-Driven State Machine for AI Agents. Enforces structured workflows, parallel worktrees, and zero-config GitHub sync for Agentic Software Engineering.

Fase Zero do Agent-Driven Protocol (ADP) — plugin de Claude Code: a IA te entrevista até o escopo ficar redondo e transforma a conversa num PRD, antes de qualquer linha de código. Grátis.

CLI + TUI that turns the GitHub Copilot CLI into a senior teammate: installs a curated catalog of skills, custom agents, a teaching persona, cross-session memory, and a native Spec-Driven Development engine. Pure Go — no LLM inside; capiko directs, Copilot executes.

The open standard for AI-ready software specifications

🧭 Find any agent asset for any agent. Host-neutral locator for skills, worktrees, instructions, and agent.3md across Claude, Grok, Codex, and Cursor.

Spec-driven development workflow for Claude Code — built around an approved design doc, where each stage waits for your approval.

Agent Skills that take a requirement — or a production alert — to a reviewed pull request: multi-agent TDD coding, a parallel review panel with severity-graded verdicts, living OpenSpec-compatible specs, and per-language guardrails.

Make agents prove their work. Independent verification, deterministic quality gates, and signed evidence for AI-generated code.

Guardrails for AI coding agents. EADOS generates a governed repo - agent contract, ADRs, CI gates, SemVer - for any of 19 languages, then enforces the rules with lint. Works with Claude Code, Codex, and Gemini.

Best AI-Powered Spec-Driven Development Tool 2026 - Multi-Agent Code Review & Automation

SPEC-First AI DevKit for Agentic Code 2026 — 24 Agents, 52 Skills, TDD/DDD Gates

Agent-agnostic merge bar and spec-driven Claude Code plugins for governed software delivery.

Run terminal tasks with this AI agent for Google Gemini and Antigravity. Features include MCP support, coding assistance, and cross-platform compatibility.

MCP server for the OneShot catalog: search receipt-verified agent build packs from inside your coding agent.

An agent skill: 43 machine-readable feature standards that resolve into a spec, acceptance criteria and a decision record — so the same product decisions are not re-explained on every project.

A committed-spec engineering lifecycle for Claude Code. The plugin ships law; your repo keeps shape in .agents/.

Deterministic proof that an AI coding agent built what the plan said it would.

⚽ Football manager RPG retro 8-bit. 30 specs SDD + 597 tests + 20 bugs fixed Akita protocol. Theme toggle Modern/8-bit. Built with Claude Code + Stitch (Gemini 3 Pro) + Google Flow.