Autocontext

by greyhaven-ai

Autocontext is an AI Engineering skill for Claude Code, published by greyhaven-ai in autocontext.

1.3K stars110 forkson greyhaven-ai/autocontextAdded 2026/08/20Repository updated 2026/08/20

View source on GitHub Download repo ZIP

agentsaiautoresearchclaudeclaude-codecodexhermeshermes-agentllmsmlopenclawpipi-coding-agent

Install in seconds

Install Autocontext

Copy Autocontext into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/greyhaven-ai/autocontext/tree/main/skills/autocontext ~/.claude/skills/autocontext

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/greyhaven-ai/autocontext.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/autocontext/SKILL.md in greyhaven-ai/autocontext
Installs to: ~/.claude/skills/autocontext
Collection: One of 5 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Autocontext does

Autocontext is a control plane for evaluating agent behavior, preserving run artifacts, exporting training data, and distilling stable behavior into local runtimes. Use it when a Hermes agent needs to run scenarios, inspect Hermes Curator state, or prepare local MLX/CUDA training data through the autoctx CLI.

Autocontext is cataloged under AI Engineering on DirSkills. Autocontext comes from a repository tagged agents, ai, autoresearch, claude and claude-code.

Documentation

README

Excerpt

Autocontext

Overview

Autocontext is a control plane for evaluating agent behavior, preserving useful run artifacts, exporting training data, and distilling stable behavior into local runtimes. In Hermes, use this skill when the work calls for measurement, replay, datasets, local MLX/CUDA training, or read-only analysis of Hermes skill curation.

Hermes Curator owns Hermes skill mutation. Autocontext should inspect, evaluate, replay, export, and recommend. Do not use Autocontext as a replacement for Hermes Curator, and do not edit Hermes skills directly unless the user explicitly asks for that operation.

When to Use

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Autocontext

What else does greyhaven-ai publish alongside Autocontext?
Autocontext is one of 5 skills that DirSkills catalogs from greyhaven-ai/autocontext, the repository it ships in. Its siblings there include AutoContext, Autocontext Consumer and Autocontext Creator. Each one is a separate skill with its own page in this directory, installs the same way Autocontext does, and is maintained by greyhaven-ai in that same repository. The rest of the collection is listed on the greyhaven-ai/autocontext page.
How does Autocontext compare to other AI Engineering skills?
Autocontext ranks #1121 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Autocontext against them. Open each page to compare what they document and how they install.