SDLC enforcement plugin with hooks for TDD gates, planning workflow, confidence levels, and cross-model review
FAQ (answers come from our records)
How do I install it?
We did not find an install command for this repository (our install coverage is only about 4%). Check its README or releases page.
Who is it for?
We filed it under these tags: MCP 服务. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
first catalogued 2026-10-14;last seen 2026-10-16。There is no official certification or quality rating here — we record sources and dates only.
Claude Code SDLC Harness
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
A **self-evolving Software Development Life Cycle (SDLC) enforcement system for AI coding agents**. Makes Claude plan before coding, test before shipping, and escalate when uncertain. Measures itself getting better over time.
**Built on 15+ years of software engineering and founding engineering experience** — battle-tested patterns from real production systems, baked into an AI agent that follows tried-and-true software quality practices so you don't have to enforce them manually.
> **The Reliable lane is the recommended default.** Opus 4.6[1m] max + GPT-5.6 Sol xhigh + Fable 5.1 high — field-proven, actively dogfooded.
>
> The Frontier lane (@frontier, not yet published) uses Opus 5.5 xhigh + GPT-5.6 Sol xhigh + Fable 5.1 high and has cycle data from v1.88.0–v1.99.2 but is experimental.
> **Built for Claude Code.** Using OpenAI's Codex CLI instead? Check out codex-sdlc-wizard. Need privacy-first / any-backend (local Ollama, Azure OpenAI, hosted OSS)? See opencode-sdlc-wizard. (Full ecosystem.)
> **Two lanes.** Pick at install time:
>
> **Reliable** (@latest) — Opus 4.6[1m] max + GPT-5.6 Sol xhigh + Fable 5.1 high.
> Field-proven, stable. Use /model claude-opus-4-6[1m] (/effort max).
> The bare claude-opus-4-6 pin (without [1m]) gives only 200K.
> **Frontier** (@frontier, not yet published) — Opus 5.5 xhigh + GPT-5.6 Sol xhigh + Fable 5.1 high.
> Latest models, less field data. See AI_SETUP_LANES.md
> for full details.
> Known defect on **both** lanes: setup does not auto-invoke on a brand-new
> project (#698)
> — run it manually on first launch: type / plus the skill name.
Install
**Requires Claude Code** (Anthropic's CLI for Claude). Install it with the native installer — curl -fsSL https://claude.ai/install.sh | bash — which the official setup docs label *Recommended* and which keeps it auto-updating in the background. **Never** use sudo npm install -g @anthropic-ai/claude-code: sudo can leave the global module directory root-owned, which then breaks claude update *and* npm uninstall -g. Check for conflicting installs with which -a claude.
Run from your terminal or from inside Claude Code (! prefix):
The @latest pin forces npm to fetch the newest version. Without it, npx may serve a stale CLI from your local cache (#358); init also nudges if it detects a gap. Since v1.100.0, @latest is the **Reliable** lane (Opus 4.6[1m] + GPT-5.6 Sol + Fable 5.1).
Then start (or restart) Claude Code — type /exit then claude to reload hooks. Setup is meant to auto-invoke on first prompt — Claude reads the wizard doc, scans your project, and generates bespoke CLAUDE.md, SDLC.md, TESTING.md, and ARCHITECTURE.md. **Known defect:** on a brand-new project the auto-invoke does not fire (#698) — run the setup skill manually: type / plus the skill name.
**Claude Code plugin (skills + hooks, no npm needed):**
Or from the repo directly:
Other install methods
**curl (no npm install needed):**
**Homebrew:**
**GitHub CLI extension:**
**From GitHub (no npm registry needed):**
**Install CLI globally:**
**Stable lane — the last pre-Opus-5 release:**
The opus-4.6 dist-tag currently points at **v1.87.0** (2026-07-14), the
last release cut before Opus 5 entered this repo, from the era when the
recommended lanes were built around Opus 4.6 / Sonnet 5. The published
v1.87.0 package contents are immutable; the dist-tag itself is a mutable
registry pointer, so to guarantee that exact version regardless of where the
tag may later point, pin it directly: agentic-sdlc-wizard@1.87.0.
**Honest label:** its
known-goodness is the maintainer's recollection of daily use, not a recorded
end-to-end test — a lifecycle canary is tracked in
689, and
this label upgrades to "verified" only when that canary's verdict is recorded
there. Verified on 2026-08-26: npm install agentic-sdlc-wizard@opus-4.6
resolves and installs 1.87.0.
**Manual (advanced — partial, not an escape hatch):** Download CLAUDE_CODE_SDLC_WIZARD.md to your project and tell Claude Run the SDLC wizard setup. This skips the live-session auto-invoke and generates your bespoke CLAUDE.md, SDLC.md, TESTING.md and ARCHITECTURE.md. **It does not give you a working install.** The document no longer contains the SDLC skill — Step 6 installs it by running the CLI (GH #513) — and only 2 of the 8 hooks have hand-typed templates here. So this path still needs npx; there is no npx-free route to a complete install. The default human path is npx init → restart CC → first-prompt auto-setup.