#tdd

Route implementation to OpenCode, Antigravity, Cursor, Codex CLI or Claude Code CLI, with Claude Code or Codex as architect and judge. Committed acceptance tests and verified integration gate delivery.

Plumbline — a self-learning, customer-value-governed agile AI agent team for Claude Code. 87 subagents + skills, TDD defense-in-depth gates, Kaizen retros, a four-body adversarial council, and an empirically benchmarked QA harness. Does it hang true?

Fable 5 workflow Loop; A Claude Code skill: autonomous build / audit / verify loop that runs until a machine-checkable contract passes, with ▎ deterministic anti-spin stop conditions (no-progress, retry, oscillation, budget) and on-disk human escalation.

Recoverable engineering workflows for coding agents: issue claims, mission lists, validation, and delivery across eight runtimes and GitHub, GitLab, and Gitea. Pairs with Kaola Project Runner for cross-runtime collaboration.

Claude Code plugin marketplace: opinionated workflows for code (dev-workflow — Rails & Python, TDD + pre-commit gate) and non-code (craft-workflow — design, content, research).

Stop your AI agent from lying about tests. Hierarchical engineering loops with machine-checkable proof gates.

Cursor Agent workflow template with role definitions, TDD/SMART/MVP rules, Symphony-ready SOPs, and Git/PR handoff standards.

Claude Code marketplace and home of claude-engineer: an opinionated, design-system-first, plan-gated autonomous engineer for full greenfield React/Next and FastAPI projects.

Turn Claude Code into a team that has to prove it. 44 skills, 8 review agents, a validation router and a knowledge layer where nothing is claimed without a check that could have failed.

Claude Code harness — fewer tokens, fewer bugs, audit-ready. 11 engineering skills. Apache-2.0.

A Claude Code plugin for Java & Spring Boot backend engineers that turns one task into a gate-enforced 7-phase agentic workflow — Discover → Brainstorm → Spec → Plan → Implement → Review → Learn. Native hooks, 11 subagents, path-scoped rules, project memory & strict test-first TDD.

Evidence-gated (Implement, Check, Control, Audit) subagentic development: maker-checker-auditor separation, mechanical Claude Code enforcement, and ~40% more reach from an expensive-model subscription.

Engineering craft for Claude Code — TDD, verification, code quality, and SDLC discipline.

Personal open-source collection of Claude Code plugins & skills — starting with dev-flow, a resumable multi-phase / multi-PR engineering flow.

Agent Memory Kit System: Capture every correction and interaction to build your own SLM from day one

Portable, auditable, coverage-honest dev lifecycle plugin — spec→plan→build→review→test→merge with reviewer/QA handoff docs. Runs on Claude Code & Cursor.

Global 前端项目：Claude Agent 协作规范、前端验收流程、Symphony/Linear 工作流、OpenSpec/SDD 与 TDD/RAG 验证门禁。

GitHub Markdown Translator 后端：通过 GitHub App 扫描仓库 Markdown、调用翻译模型生成语言后缀文件，并以 Pull Request 提交回 GitHub；支持公开仓库只读预览。

An opinionated Claude Code harness: lock specs & contracts as the source of truth, then drive a team of agents to implement against them with outside-in TDD and adversarial multi-agent review.

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

Review uncommitted and branch changes, PRs, or paths in Codex with configurable depth, optional fixes, and GitHub inline comments.

Interactive Rust Tutor + Claude Plugin 2026 – Auto-Learning Projects with Quality Gates

Autonomous local SRE agent — ingests logs, detects anomalies, and routes all remediation actions through a policy webhook before execution. TDD-built, fail-closed, no cloud dependency.

Discipline layer for AI coding agents (Claude Code & Codex): task router + three pipeline modes with run controls, premortem reviews, TDD gates, evidence-based acceptance, and crash-safe resume. Noncommercial license, 138 behavioral evals.

Modular AI agent skills used across engineering, writing, and research workflows. Model‑agnostic, composable, and production‑tested. Includes engineering, productivity, personal, and experimental skill packs.

Structured agentic development, shipped as Agent Skills - plan, triage, build, and review with autonomous sub-agents, human approval gates, and automatic review on every diff. Runs in Claude Code, Cursor, Codex, Gemini, Mistral, pi, and any Agent Skills harness.

Agent 작업의 신뢰성 높이기 · Improving the Reliability of Agent's Work

Agent skills and a Rust CLI that take an issue to a reviewed, verified PR overnight. Works with any harness (Claude Code, Codex, Cursor) and any stack.

Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after compaction, plug-in code standards, optional TDD mode, and zero behavior changes for developers.

🏛️ A strategy game where every nation is ruled by an AI agent: they trade, sign pacts, betray each other and go to war. The AI proposes, the engine decides. Built by hand, milestone by milestone: spec first, tests first.

You describe a change. Orkestra walks Claude Code, Cursor, or GitHub Copilot through a local pipeline: learn the project, write a spec and a plan, implement with tests, and review the result. Hooks block commits, deploys, and secret files unless you ask. MIT License. Not those companies' product, and not a sandbox.