Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By ahostbr
Multi-CLI agent orchestration — spawn, message, and coordinate AI coding agents across Claude Code, Codex, Copilot, and more from a single harness. 5-tier hierarchy, inter-agent messaging, polymathic thinking agents, git-as-memory.
npx claudepluginhub ahostbr/liteharness-pluginLoad the most recent checkpoint (or a named one) from LCM to restore session context. Retrieves the structured checkpoint saved by `/savenow`.
Save the current session state to the LCM (Lossless Context Management) DAG as a structured checkpoint message. This creates a recoverable restore point that `/loadnow` can retrieve.
Generates new Claude Code sub-agent configuration files from descriptions. Use proactively when the user asks to create a new sub-agent.
Challenges reasoning quality of plans, decisions, and approaches through 6 meta-cognitive lenses. Use when reviewing plans, PRDs, architectural decisions, or any significant reasoning output. Read-only — analyzes documents and produces structured reports. Spawn before committing to architecture decisions, when a plan "feels right" but untested, or after thinker debates to audit synthesis quality.
Max-Parallel builder that executes ONE task with self-validation. Focused context window for code writing, file creation, implementation work. Use with /max-subagents-parallel workflows.
Read-only validator for /max-subagents-parallel workflows. Verifies task completion against acceptance criteria. Cannot modify files - inspects and reports only.
Authentication vulnerability analysis — finds weaknesses in login, session management, token handling, and credential storage. Use for security audits of auth flows.
Agents Overflow — ask, answer, browse, search questions. Triggers on 'ao', 'agents overflow', or any AO-related request (posting questions, answering, browsing, searching).
Generate or update architecture documentation for any project. Dispatches scout agents to explore the codebase, then writes structured architecture docs with an INDEX. Triggers on 'generate arch docs', 'create architecture docs', 'update arch docs', 'document this project', 'arch-gen', 'generate documentation'.
DEPRECATED — Use /arch instead. Legacy pre-consolidation architecture docs (backup). Only use for historical reference of the original per-app architecture.
Canonical architecture reference for LiteSuite mega-app and ecosystem. Quick-lookup index into 15 architecture docs covering panels, services, MCP tools, voice, harness, arena, and more. Triggers on 'arch', 'architecture', 'show architecture', 'arch docs'.
DEPRECATED — Use /arch instead. Legacy pre-consolidation architecture docs (backup). Only use for historical reference of the original per-app architecture.
Matches all tools
Hooks run on every tool call, not just specific ones
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Automatic transcript backup. Every conversation saved, organized by date, fully searchable.
Human-in-the-loop result filtering. Filter search results BEFORE they pollute your context.
Spawn, message, and coordinate AI coding agents across Claude Code, Codex, Copilot, Pi, Kilo, OpenCode — all from a single harness.
--team flag# 1. Install the Python package
pip install liteharness
# 2. Install the plugin
/plugin install liteharness
# Spawn a background agent
liteharness spawn --pty --model sonnet --name "Worker" --prompt "fix the flaky test"
# See who's online
liteharness discover
# Send a message
liteharness send <agent-id> "try approach B" --from <your-id>
# Check your inbox
liteharness check
| Skill | Description |
|---|---|
/liteharness:liteharness | Full orchestration — spawn, discover, message, control |
Specialist thinking agents that apply historical figures' cognitive architectures:
| Agent | Best For |
|---|---|
polymathic-feynman | Debugging, first-principles analysis |
polymathic-carmack | Performance, systems architecture |
polymathic-shannon | API design, simplification |
polymathic-linus | Code review, taste assessment |
polymathic-lovelace | Cross-domain synthesis |
| ... and 44 more | See /agents for the full list |
pip install liteharnessMIT