Alternative: Install via npx with npx skills add athola/claude-night-market (installs all plugins at once).

After installation, run claude --init for one-time setup.

Note: If the Skill tool is unavailable, read skill files directly at plugins/{plugin}/skills/{skill-name}/SKILL.md.

opkg (OpenPackage)

# Install specific plugins
opkg i gh@athola/claude-night-market --plugins sanctum
opkg i gh@athola/claude-night-market --plugins pensive,conserve

# Plugins that depend on shared runtime skills (e.g. attune, conjure)
# automatically pull packages/core as a dependency

See the Installation Guide for detailed setup options.

Architecture

23 internal plugins in four layers, plus external plugins from the superpowers-marketplace. Arrows show dependency direction (A --> B means A depends on B). Dashed arrows mark optional complements.

Source: assets/architecture.d2 — regenerate with d2 assets/architecture.d2 assets/architecture-light.svg

Plugin Catalog

| Plugin | Layer | Description | Skills | Cmds | |--------|-------|-------------|:------:|:----:| | abstract | Meta | Skill authoring, hook development, evaluation frameworks, escalation governance | 12 | 18 | | leyline | Foundation | Auth flows (GitHub/GitLab/AWS), quota management, error patterns, markdown formatting, Discussions retrieval, damage-control, stewardship, trust verification, injection detection, deferred-capture contracts | 21 | 3 | | sanctum | Foundation | Git workflows, commit messages, PR prep, docs updates, version management, sessions, deferred-item capture | 14 | 46 | | imbue | Foundation | TDD enforcement, proof-of-work validation, scope guarding, additive-bias auditing, rigorous reasoning | 11 | 4 | | conserve | Utility | Context optimization, bloat detection, context mapping, CPU/GPU monitoring, token conservation | 13 | 4 | | conjure | Utility | Delegation framework for routing tasks to external LLMs (Gemini, Qwen) with cheapest-capable model selection | 4 | 0 | | hookify | Utility | Behavioral rules engine with markdown configuration and hook-to-rule conversion | 2 | 6 | | egregore | Utility | Autonomous agent orchestrator with parallel worktrees, agent specialization, cross-item learning, and crash recovery | 4 | 5 | | herald | Utility | Shared notification library: GitHub issue alerts, webhook support (Slack, Discord, generic) | 0 | 0 | | oracle | Utility | ONNX Runtime inference daemon for ML-enhanced plugin capabilities over localhost HTTP | 1 | 1 | | pensive | Domain | Code review, architecture review, bug hunting, blast radius analysis, Makefile audits, NASA Power of 10 | 13 | 12 | | attune | Domain | Project lifecycle: brainstorm, specify, plan, initialize, execute, war-room, dorodango polishing | 13 | 10 | | spec-kit | Domain | Spec-driven development: specifications, task generation, implementation | 3 | 10 | | parseltongue | Domain | Python: testing, performance, async patterns, packaging | 4 | 3 | | minister | Domain | GitHub issue management, label taxonomy, initiative tracking | 2 | 3 | | memory-palace | Domain | Spatial knowledge organization, digital garden curation, PR review capture | 6 | 5 | | archetypes | Domain | Architecture paradigm selection (hexagonal, CQRS, microservices, etc.) | 14 | 0 | | gauntlet | Domain | Codebase learning through knowledge extraction, challenges, code knowledge graph, and spaced repetition | 6 | 6 | | phantom | Domain | Computer use: screenshot capture, mouse/keyboard control, autonomous desktop agent | 1 | 1 | | scribe | Domain | Documentation with AI slop detection, style learning, session replay, tech tutorials | 7 | 5 | | scry | Domain | Terminal recordings (VHS), browser recordings (Playwright), GIF processing | 4 | 2 | | tome | Domain | Multi-source research: code archaeology, community discourse, academic literature, TRIZ analysis | 7 | 4 | | cartograph | Domain | Codebase visualization: architecture, data flow, dependency, call chains, community detection, class diagrams via Mermaid | 7 | 1 |

Full inventory: Capabilities Reference.

How the Layers Work

Governance. imbue enforces TDD via a PreToolUse hook that verifies test files before allowing implementation writes. Quality gates halt execution when tests fail.

Security. leyline manages OAuth flows with local token caching. conserve auto-approves safe commands while blocking destructive operations. sanctum isolates named sessions, and agents can run in worktree isolation for parallel execution.

Orchestration. egregore manages autonomous agent lifecycles with parallel worktree execution, agent specialization, cross-item learning, and crash recovery via watchdog monitoring.

Maintenance. /update-ci reconciles pre-commit hooks and GitHub Actions with code changes. abstract tracks skill stability and auto-triggers improvement agents when degradation is detected.

Cross-session state. attune, spec-kit, and sanctum persist state across sessions via CLAUDE_CODE_TASK_LIST_ID. GitHub Discussions serve as a second persistence layer for decisions, war-room deliberations, and evergreen knowledge.

Risk classification. leyline:risk-classification provides 4-tier task gating (GREEN/YELLOW/RED/CRITICAL). RED and CRITICAL tasks escalate to war-room-checkpoint for expert deliberation.

Common Workflows

See the [Common Workflows Guide][workflows] for full details.

| Workflow | Command | What it does | |----------|---------|-------------| | Project lifecycle | /attune:mission | Routes through brainstorm, specify, plan, execute phases | | Initialize project | /attune:arch-init | Architecture-aware scaffolding with language detection | | Review a PR | /full-review | Multi-discipline code review in a single pass | | Fix PR feedback | /fix-pr | Address review comments progressively | | Implement issues | /do-issue | Issue resolution with parallel agent execution | | Prepare a PR | /prepare-pr | Quality gates, linting, clean git state | | Write specs | /speckit-specify | Specification-first development | | Catch up on changes | /catchup | Context recovery from recent git history | | Codebase cleanup | /unbloat | Bloat removal with progressive depth levels | | Update CI/CD | /update-ci | Reconcile hooks and workflows with code changes | | Strategic decisions | /attune:war-room | Expert routing with reversibility scoring | | Refine code | /refine-code | Duplication, algorithm, and clean code analysis |

What's New

See the Changelog for the full history.

Requirements

• Claude Code 2.1.16+ (2.1.32+ for agent teams, 2.1.38+ for security features, 2.1.85+ latest tested)
• Python 3.9+ for hooks (macOS ships 3.9.6). Plugin packages may target 3.10+ via virtual environments, but all hook code must be 3.9-compatible. See the [Plugin Development Guide][dev-guide] for compatibility rules.

Plugin Development

Create a new plugin:

make create-plugin NAME=my-plugin
make validate
make lint && make test

Plugin layout:

my-plugin/
├── .claude-plugin/
│   └── plugin.json        # Metadata: skills, commands, agents, hooks
├── commands/               # Slash commands (markdown)
├── skills/                 # Agent skills (SKILL.md + modules/)
├── hooks/                  # Event handlers (Python, 3.9-compatible)
├── agents/                 # Specialized agent definitions
├── tests/                  # pytest suite
├── Makefile                # Build, test, lint targets
└── pyproject.toml          # Package config

See the [Plugin Development Guide][dev-guide] for structure requirements an