Autoharness is a self-learning skill layer for Claude Code that distills skills from real work sessions, combines overlapping skills, updates them during use, and removes ones that are no longer used. It is for people who want Claude Code to maintain a working library of reusable skills as they work. The catalogue entries provide the hooks, agents, MCP integration, plugin, and skill that make up its workflow.
Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add tigerless-labs/autoharness/plugin install autoharnessWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/tigerless-labs/autoharness/stage_skill)<a href="https://agentmods.dev/mcp/tigerless-labs/autoharness/stage_skill"><img src="https://agentmods.dev/badge/mcp/tigerless-labs/autoharness/stage_skill.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
stage_skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"stage_skill": {
"command": "python3",
"args": [
"-m",
"autoharness.stage_skill.server"
],
"env": {
"PYTHONPATH": "${CLAUDE_PLUGIN_ROOT}/src"
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 12 lines scan A ca56c8419405
stage_skill is an MCP server published in the GitHub repository tigerless-labs/autoharness (1,532 stars, last pushed today), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other mcp servers, from other repositories
stripe
Stripe's hosted MCP server: lets the agent work with customers, products, prices and payment links. Remote server at mcp.stripe.com.
chrome-devtools
Lets the agent inspect and automate a live Chrome instance through the DevTools protocol: performance traces, network, console. Runs locally from the chrome-devtools-mcp npm package.
agent-observability
AI agent observability with deterministic record/replay — capture any LangGraph or OpenAI Agents SDK run, replay it offline at zero API cost. Runs locally from the agent-observability-trace-cli Python package.
dt
DomainTome — the living knowledge graph for your software project. A programmatic MCP-backed graph of business logic, flows, events and rules. Runs locally from the domaintome Python package.
docs-langchain
MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.
reference-langchain
MCP server "reference-langchain", hosted remotely at reference.langchain.com, as configured in langchain-ai/langchain.