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 Necmttn · Codex Skill · ★ 114
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ax safe to install? View the security audit →
ax the retro loop for AI coding agents Make your agent learn. Turn every agent session into a better next run. Every sub-agent you spawn finishes its work and disappears. Whatever it figured out - which command failed three times before the right one, which file actually mattered, which approach to skip - dies with it. The next sub-agent rediscovers it from scratch. Your own next session does too. watches every session your harness runs, spots the mistakes it repeats, and turns them into small, repo-specific fixes you review and apply - one at a time. Under the hood, it's the loop that closes before the session ends. A Stop hook fires at session-end (main or sub-agent), asks the agent for a structured retro (tried · worked · failed · next), and indexes the result as a typed experiment in a local graph. Friction patterns become proposals you triage. Accepted proposals become experiments with t+7 / t+30 / t+90 verdicts. The next session reads what worked. What did this sub-agent learn? Which experiments are still open? Which skills earned their keep? What did that branch cost in tokens? answers these by reading what already happened.
| Stars | 114 |
| Forks | 15 |
| Language | TypeScript |
| Category | Codex Skill |
| License | AGPL-3.0 |
| Quality Score | 63.7479128419257/100 |
| Open Issues | 37 |
| Last Updated | 2026-10-02 |
| Created | 2026-05-08 |
| Platforms | claude-code, codex, node |
| Est. Tokens | ~17k |
These tools work well together with ax for enhanced workflows:
Looking for a ax alternative? If you're comparing ax 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.
See your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Cod
Local-first observability your agent reads back. TMA1 records every LLM call, then routes what it sees into th
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Slack CLI for humans and AI agents. Read, send, search and reply across one or many Slack workspaces from the
Co-creation infrastructure for humans and code agents — visual environment, skills, continuous learning, and d
🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace
Explore other popular codex skill tools:
ax is the agent experience layer · observability + memory for AI coding agents (Claude Code + Codex) · local-first, typed, yours. It is categorized as a Codex Skill with 114 GitHub stars.
ax is primarily written in TypeScript. It covers topics such as agent-memory, agent-observability, ai-agents.
You can find installation instructions and usage details in the ax GitHub repository at github.com/Necmttn/ax. The project has 114 stars and 15 forks, indicating an active community.
ax is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to ax on Agent Skills Hub include clawmetry, tma1, deepcontext-mcp. 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: