Back to browse
GitHub Repository

Spec Driven Development Workflow

99 starsShell

Spec-Driven Development Workflow for Claude Code

by sermakarevich·May 22, 2026·20 points·12 comments

AI Analysis

●●SolidShip ItNiche Gem

Context clearing between steps cuts costs, but hallucinated 2026 citations hurt trust.

Strengths
  • Disk-based specs persist architecture decisions across sessions better than chat history.
  • Context clearing keeps model focus sharp and reduces token costs significantly.
  • Lightweight shell scripts avoid runtime dependencies compared to heavy orchestration frameworks.
Weaknesses
  • README cites research from 2026, signaling hallucinated stats or careless verification.
  • Tied strictly to Claude Code, limiting adoption versus editor-agnostic solutions.
Target Audience

Developers using Claude Code for medium-to-large projects

Similar To

Aider · Cursor · SweAgent

Post Description

Spec Driven Development approach allows to squeeze more from coding agents thanks to few strong concepts: - decomposition across two dimensions. first you generate specs in multiple steps (requirements, code analysis, design), than you split task into multiple subtasks and implement them one by one - you clear context between every step - after spec generation and after subtask implementation. this helps keep cost low and context clear and focused which boost performance - specs written to disk help with information persistency - delivering specs layer by layer help to catch early when agent got you wrong

Repo with claude plugin for spec driven development: https://github.com/sermakarevich/sddw

Similar Projects

Developer Tools●●Solid

SpecFact CLI – reverse engineer Python repos into enforceable specs

This repo actually wires the specfact CLI to a tiny, reproducible codebase so you can import-from-code, generate .specfact bundles, and run enforcement presets with one-liners. The backlog-sync adapter and a deliberately buggy sidecar demo make failure modes easy to exercise, and the README lists exact smoke commands and logs to verify results. Inferred specs will always risk false positives, but the project shows practical artifacts (change_tracking, results logs) rather than theory.

Niche GemSolve My Problem
noldai
114mo ago
Developer Tools●●Solid

Turn any OpenAPI spec into agent-callable skills

It extracts focused, executable operations from giant OpenAPI files (the GitHub REST YAML is shown) to shrink context and avoid sidecar adapter sprawl — a pragmatic answer to token bloat and brittle ad-hoc integrations. Useful and concrete: if it actually generates tidy, updateable skill units and runtime hooks it saves a lot of maintenance. That said, the idea competes with existing LangChain/openai-function patterns; the repo will need clear runtime, versioning, and update strategies to feel like more than a nicer converter.

Solve My ProblemNiche Gem
yz-yu
103mo ago