AutoHarness vs wshobson/agents
Which should you use? A side-by-side look at what each one does, who it suits, what it costs, how hard it is to set up, and where each falls short.
Open source · MIT
Claude Code plugin that learns reusable skills from your sessions and prunes unused ones.
Open source · MIT
A collection of plugins, agents, skills, and commands that run across several AI coding tools.
The short answer
Choose AutoHarness if you need…
- Developers who use Claude Code heavily and repeat the same kinds of tasks
- Teams that want project-level skills to build up without manual upkeep
- People who want to see and control what gets learned, since skills are plain files with a ledger marker
Choose wshobson/agents if you need…
- Developers who already use one of the listed AI coding tools and want ready-made specialist agents
- Python or JavaScript/TypeScript developers looking for testing, packaging, or project setup guidance
- Teams wanting a shared set of review and security-scanning workflows across different tools
- People who want to install only individual skills without the full plugin set
Side-by-side
| AutoHarness | wshobson/agents | |
|---|---|---|
| Type | Dev tool | Dev tool |
| Price | Free and open source | Free and open source |
| Licence | MIT | MIT |
| GitHub stars | 10.6k | 42.1k |
| Setup difficulty | Beginner | Beginner |
| How you get it | See the README | Install with a package manager |
| Main language | Python | Python |
| Last code update | 6 days ago | 4 days ago |
What each one is
AutoHarness
AutoHarness is a plugin for Claude Code, Anthropic's coding assistant. While you work, it turns useful episodes from your sessions into reusable skill files under .claude/skills/, merges similar skills, updates them as they are used, and removes ones that stop being used. It only manages skills it generated itself and leaves your own or installed skills alone.
wshobson/agents
This project is a shared library of prompts-as-plugins for AI coding assistants. It contains 94 plugins with specialist agents, skills (reference guidance an agent loads when relevant), and commands (named workflows) covering areas like Python, JavaScript, code review, testing, infrastructure, and security. One Markdown source is adapted to Claude Code, OpenAI Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot, and Pi.
Best for
AutoHarness
- Developers who use Claude Code heavily and repeat the same kinds of tasks
- Teams that want project-level skills to build up without manual upkeep
- People who want to see and control what gets learned, since skills are plain files with a ledger marker
wshobson/agents
- Developers who already use one of the listed AI coding tools and want ready-made specialist agents
- Python or JavaScript/TypeScript developers looking for testing, packaging, or project setup guidance
- Teams wanting a shared set of review and security-scanning workflows across different tools
- People who want to install only individual skills without the full plugin set
Strengths
AutoHarness
- Installs as a Claude Code plugin with zero third-party Python dependencies, according to the README
- Only touches skills it wrote itself, so your own skills are not modified
- Tunable cadence and scope through AUTOHARNESS_* environment variables
wshobson/agents
- Covers seven coding tools from one shared source of components
- Large catalog: 94 plugins, 202 agents, 185 skills, and 105 commands according to the README
- Offers a skills-only install route that does not require the full plugin set
Not ideal for
AutoHarness
- Users who do not use Claude Code, since the plugin only runs inside it
- Users on Python older than 3.11 or without python3 on PATH, because hooks silently stay off
- People who want a measured benchmark score for skill quality, since the README says validation comes from use rather than a benchmark
wshobson/agents
- People who do not use any supported AI coding tool, since the components only run inside those harnesses
- Anyone expecting the scores from the plugin-eval tool to prove a task will succeed, because the README says the LLM judge and Monte Carlo layers are experimental and not validated against human labels
- Users wanting a fully stable, versioned release, since the README lists no latest release
Trade-offs
AutoHarness
- Requires Python 3.11+ as python3 on PATH; the README warns that older interpreters silently disable the hooks
- The README lists Linux and macOS as the platforms; Windows is not mentioned
- Effectiveness is described as validated by use, not a benchmark, so quality claims are hard to verify independently
wshobson/agents
- The README notes that available components depend on the installation route and each harness's limits, so features differ by tool
- Some features (LLM judge, Monte Carlo evaluation) are experimental and may bill your Anthropic API account if ANTHROPIC_API_KEY is set
- Pi agents need a separate subagent extension, and the Codex native and generated routes behave differently
Getting started
AutoHarness
Add the marketplace (type inside Claude Code)
/plugin marketplace add tigerless-labs/autoharnessInstall the plugin (type inside Claude Code)
/plugin install autoharness@autoharnesswshobson/agents
Claude Code: register marketplace (run inside Claude Code)
/plugin marketplace add wshobson/agentsClaude Code: install Python plugin (run inside Claude Code)
/plugin install python-development@claude-code-workflowsFrequently asked questions
What is the difference between AutoHarness and wshobson/agents?
AutoHarness: Claude Code plugin that learns reusable skills from your sessions and prunes unused ones. wshobson/agents: A collection of plugins, agents, skills, and commands that run across several AI coding tools. AutoHarness suits developers who use claude code heavily and repeat the same kinds of tasks, while wshobson/agents suits developers who already use one of the listed ai coding tools and want ready-made specialist agents.
Are AutoHarness and wshobson/agents free?
AutoHarness: Free and open source. wshobson/agents: Free and open source.
Is AutoHarness or wshobson/agents more popular?
wshobson/agents has more GitHub stars (42.1k) than AutoHarness (10.6k). Popularity isn't the same as fit — check which one matches your use case above.
What are other alternatives to AutoHarness and wshobson/agents?
Other options people compare them with include Agentic Awesome Skills, planning-with-files, Distilly, claude-obsidian, 9Router.
Keep comparing
Built from our catalogue entries for both products: open-source details come from each project's README (AI-assisted, refreshed weekly) and GitHub data; AI-tool details are editorial. Spotted something wrong? Let us know from either product's page.