athola/claude-night-market
23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.
What it solves
Claude Night Market provides a plugin marketplace for Claude Code, allowing users to extend the AI's capabilities with specialized tools for git workflows, code review, spec-driven development, and autonomous agents. It solves the problem of needing a standardized way to add professional software engineering practices—like TDD enforcement and architecture review—directly into the Claude Code session.
How it works
The project is organized into four layers of plugins:
- Foundation: Base utilities for authentication, git management, and TDD enforcement (e.g.,
sanctum,imbue). - Utility: Cross-cutting tools for token optimization, external model delegation, and autonomous agent orchestration (e.g.,
conserve,egregore). - Domain: Specialized tools for the actual development work, such as code review (
pensive), project lifecycle management (attune), and codebase visualization (cartograph). - Meta: Tools for creating and evaluating new skills and hooks (e.g.,
abstract).
Users install plugins via the /plugin install command within Claude Code. The system includes safety guards, such as TDD gates that block implementation writes without failing tests and blockers for destructive shell commands.
Who it’s for
Practitioners who already use Claude Code and want to automate complex engineering workflows, enforce quality gates, and integrate autonomous agents into their development process.
Highlights
- Integrated Workflow Commands: Provides high-level commands like
/attune:missionfor project lifecycles and/full-reviewfor multi-discipline code reviews. - TDD Enforcement: The
imbueplugin ensures a failing test is written before the implementation code is created. - Agent Orchestration: Includes
egregorefor managing autonomous agents andconjurefor delegating tasks to other model CLIs. - Safety Guards: Built-in protections against destructive commands like
rm -rforgit push --force.
Related
- Project
- Project
- Project
- Project
- Project