By athola
Autonomously orchestrates the full development lifecycle—managing work items, running quality pipelines, enforcing token budgets, and handling crash recovery with zero human input. Includes a watchdog daemon for persistent session relaunching on macOS/Linux.
The ONLY way to stop the egregore. Human-initiated graceful shutdown that saves all state.
Install the egregore watchdog daemon for automatic session relaunching
Show current egregore state and progress
Summon the egregore to autonomously process work items through the full development lifecycle. Runs indefinitely by default until dismissed.
Remove the egregore watchdog daemon and clean up files
The egregore's autonomous will. Reads the manifest, picks the next active work item, invokes specialist skills for each pipeline step, and manages the full development lifecycle. This agent: 1. Reads .egregore/manifest.json 2. Picks the next active work item 3. Invokes the skill mapped to the current pipeline step 4. Advances the pipeline on success 5. Handles failures (retry or mark failed) 6. Monitors context budget via continuation agents 7. Monitors token budget via graceful shutdown 8. Alerts overseer on events via GitHub issues/webhooks 9. Repeats until all work items are completed or failed 10. In indefinite mode, scans for new work and continues
Monitors egregore's resource budget and handles graceful shutdown when token windows are exhausted. Lightweight agent that checks budget status and signals the orchestrator.
Install the egregore watchdog daemon using the OS-native scheduler. Creates a launchd plist (macOS) or systemd timer (Linux) that checks every 5 minutes if egregore needs relaunching.
Orchestrates egregore's QUALITY pipeline stage. Runs convention checks and invokes review skills for each quality step. Supports self-review (pre-PR) and PR-review (other agents' PRs) modes.
Autonomous orchestrator processing manifest work items through the development lifecycle with budget tracking.
Remove the egregore watchdog daemon and clean up all associated files (plist/unit, pidfile, watchdog log).
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A plugin marketplace for Claude Code, Anthropic's agentic coding tool.
Night Market extends Claude Code with 23 plugins covering git workflows, code review, spec-driven development, architecture selection, codebase visualization, autonomous agents, multi-LLM delegation, ML-enhanced scoring, and multi-source research. 161 skills, 146 slash commands, and 50 agents. Each plugin installs independently.
Requires Claude Code 2.1.16+ and Python 3.9+ for hooks. See Requirements for details.
# Add the marketplace
/plugin marketplace add athola/claude-night-market
# Install plugins you need
/plugin install sanctum@claude-night-market # Git workflows
/plugin install pensive@claude-night-market # Code review
/plugin install spec-kit@claude-night-market # Spec-driven dev
# Use them
/prepare-pr # Prepare a pull request
/full-review # Run code review
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
Skilltool is unavailable, read skill files directly atplugins/{plugin}/skills/{skill-name}/SKILL.md.
# 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.
23 plugins organized in four layers. Domain specialists depend on utility plugins, which depend on foundation plugins, which depend on the meta layer.
flowchart TB
classDef domainClass fill:#e8f4f8,stroke:#2980b9,stroke-width:2px,color:#2c3e50
classDef utilityClass fill:#f8f4e8,stroke:#f39c12,stroke-width:2px,color:#2c3e50
classDef foundationClass fill:#f4e8f8,stroke:#8e44ad,stroke-width:2px,color:#2c3e50
classDef metaClass fill:#e8f4e8,stroke:#27ae60,stroke-width:2px,color:#2c3e50
subgraph Domain["Domain Specialists"]
direction LR
D1[archetypes]:::domainClass
D2[pensive]:::domainClass
D3[parseltongue]:::domainClass
D4[memory-palace]:::domainClass
D5[spec-kit]:::domainClass
D6[minister]:::domainClass
D7[attune]:::domainClass
D8[scry]:::domainClass
D9[scribe]:::domainClass
D10[tome]:::domainClass
D11[gauntlet]:::domainClass
D12[cartograph]:::domainClass
end
subgraph Utility["Utility Layer"]
direction LR
U1[conserve]:::utilityClass
U2[conjure]:::utilityClass
U3[hookify]:::utilityClass
U4[egregore]:::utilityClass
U5[herald]:::utilityClass
U6[oracle]:::utilityClass
end
subgraph Foundation["Foundation Layer"]
direction LR
F1[imbue]:::foundationClass
F2[sanctum]:::foundationClass
F3[leyline]:::foundationClass
end
subgraph Meta["Meta Layer"]
direction LR
M1[abstract]:::metaClass
end
Domain ==> Utility ==> Foundation ==> Meta
npx claudepluginhub athola/claude-night-market --plugin egregoreMeta-skills infrastructure for Claude Code plugin ecosystem - skill authoring, hook development, modular design patterns, and evaluation frameworks
Documentation review, cleanup, and generation with AI slop detection, style learning, and human-quality writing enforcement
Spatial knowledge organization using memory palace techniques - build, navigate, and maintain virtual memory structures for enhanced recall and information management. Includes PR Review Room for capturing review knowledge.
Spec Driven Development toolkit - structured specification, planning, and implementation workflows for systematic feature development
Architecture paradigm selection and implementation planning for software systems
Self-orchestrating multi-agent development system powered by Claude Fable 5 — 15 agents (8 core + 1 security gate + 6 department), Smart Routing default, token-efficient subagents, risk-based quality gates. You say WHAT, the AI decides HOW.
Human-AI partnership for Claude Code. Share a terminal, orchestrate workers, evolve together. Brainstorm ideas, turn them into wishes, execute with /work, validate with /review, and ship as one team.
Long-running agent harness with 5-layer memory architecture, GitHub integration, autonomous batch processing, Agent Teams with ATDD, 9 hooks (safety, quality gates, team coordination), and 6 Agent Skills
Automated development loop and ad-hoc workflow generation for orchestrating AI coding agents
Language-agnostic development process harness implementing the Stateless Agent Methodology (SAM) 7-stage pipeline with ARL human touchpoint model and Voltron-style language plugin composition. Provides orchestration, workflows, planning, verification, and testing methodology that any language plugin can compose with.
Complete project development toolkit: 23 agents, 23 slash commands, 29 lifecycle hooks, and 69 reusable skills for Claude Code workflows