No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by greyhaven-ai · Codex Skill · ★ 1.3k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is autocontext safe to install? View the security audit →
turn repeated agent work into validated, reusable execution autocontext is a system for running scenarios, tasks, and missions, analyzing what happened, and carrying forward the knowledge that actually improved outcomes. The North Star is to move from one-off frontier-model exploration toward workflows that become more reliable, more auditable, and cheaper to run over time. The intended use is mostly hands-off: point the harness at a real task in plain language, let it work the problem, and then inspect the traces, reports, artifacts, datasets, playbooks, and optional distilled model it produces. What's New GEPA-inspired ASI/Pareto optimizer wired into improvement loop Component sensitivity profiling and credit assignment Pluggable scoring backends with Elo and Glicko support Novelty exploration and multi-basin playbook branching Cost-aware loop control and long-run presets North Star Most agent systems still start every run cold. They do not reliably preserve what worked, separate signal from noise, or turn repeated success into a reusable asset. autocontext is built to close that loop: run a scenario, task, or mission evalu
| Stars | 1,303 |
| Forks | 114 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 66.5430383989818/100 |
| Open Issues | 7 |
| Last Updated | 2026-09-29 |
| Created | 2026-02-11 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~16k |
These tools work well together with autocontext for enhanced workflows:
Looking for a autocontext alternative? If you're comparing autocontext with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
🛰️ Track token usage across AI coding agents from your terminal. 🏅 Global leaderboard with trillions of toke
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C
One Hub All LLMs For You | 为个人打造的 LLM API 聚合网关
Manage multiple Claude Code, OpenCode agents from either TUI or Web for easy access on mobile. Also supports M
🦞+🔬 NanoResearch: The Autonomous AI Research Assistant
Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs
Explore other popular codex skill tools:
autocontext is a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task. It is categorized as a Codex Skill with 1.3k GitHub stars.
autocontext is primarily written in Python. It covers topics such as agents, ai, autoresearch.
You can find installation instructions and usage details in the autocontext GitHub repository at github.com/greyhaven-ai/autocontext. The project has 1.3k stars and 114 forks, indicating an active community.
autocontext is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to autocontext on Agent Skills Hub include tokscale, kindly-web-search-mcp-server, octopus. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: