cskwork

Sdlc Kit — AI skill for Claude Code

AI community

Harness-neutral AI-native SDLC framework — intent grilling, sha256 tamper-evident approval gates, fresh-context adversarial review, bounded lessons memory.

How to install Sdlc Kit

This entry records only its repository, not the path inside it, so there is no exact command to give. Open cskwork/sdlc-kit and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Sdlc Kit does

Harness-neutral AI-native SDLC framework — intent grilling, sha256 tamper-evident approval gates, fresh-context adversarial review, bounded lessons memory. Plain files + shell; works with pi, Claude Code, Codex, Gemini CLI, Cursor.

Alternatives in AI

LongHorizon Harness — The long-horizon computer-use harness 1.3k ★
Engage.Scorecard — Calibrate model verdict trust (Wilson-bounded miss-rate) to short-circuit re-validation 348 ★
PromptEnhance — Rewrite the following prompt to be clearer, more specific, and more effective for an AI assistant 250 ★

README

sdlc-kit

Stop letting coding agents mark their own homework.

**A portable four-phase SDLC for AI coding agents, in any codebase and any domain.**

Intent → Plan → Build → Evidence. Parallel scouts before code, an adversarial reviewer after it, and a scored, routed proof at the end.

[![Release](https://img.shields.io/github/v/release/cskwork/sdlc-kit?style=flat-square&color=C79A55)](https://github.com/cskwork/sdlc-kit/releases/latest) [![GitHub Pages](https://img.shields.io/badge/live_site-open-C79A55?style=flat-square)](https://cskwork.github.io/sdlc-kit/) [![Harness neutral](https://img.shields.io/badge/harness-pi_%C2%B7_Claude_Code_%C2%B7_Codex_%C2%B7_Gemini-24211E?style=flat-square)](#quick-start)

[**See the live site**](https://cskwork.github.io/sdlc-kit/) · [**Quick start**](#quick-start) · [**Read the contract**](SKILL.md) · [**한국어**](README.ko.md)

Coding is fast now. **Being wrong is still expensive.** An agent that starts by writing code finds the side effects last, and an agent that checks its own work finds few. sdlc-kit puts understanding first and independent proof last, and keeps everything in between small.

It is adapted from [Anthropic's AI-Native SDLC playbook](https://claude.com/blog/the-ai-native-sdlc-playbook) and needs no particular harness: it is Markdown plus one shell script.

sdlc-kit is an independent project and is not affiliated with Anthropic.

The loop

flowchart LR
  I["1 Intent"] -->|you approve| P["2 Plan"]
  P -. gap found .-> P
  P -->|plan approved| B["3 Build"]
  B -. FAIL: fix, re-review .-> B
  B -->|review PASS| E["4 Evidence"]
  E -. plan was wrong, or same failure twice .-> P
  E -. code failed .-> B
  E -->|every must passes, 95%+ overall| D(["deliver"])
  E -->|no environment to run it| H(["you decide"])