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 ChrisTitusTech · Codex Skill · ★ 121
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is titus-ai safe to install? View the security audit →
titus-ai Portable Codex configuration, rules, and reusable skills. Install Preview and install: Restart Codex after installation. Existing managed files are backed up under . Credentials, sessions, history, caches, and plugins are not changed. The installer links: configuration and rules into into Install RTK RTK is an optional Rust CLI proxy that compresses verbose command output before it reaches Codex's context window. Install it directly from GitHub: Do not use . The package name on crates.io belongs to a different project. Ensure Cargo's binary directory is on : Then verify both the binary and its output-savings command: The managed already instructs Codex to prefix supported commands with , so no separate step is required after running this repository's installer. Codex falls back to the raw command when RTK is missing or rejects an unsupported command or flag. Use Start Codex normally to use the default configuration: Invoke a skill explicitly when needed: text $linux-sysadmin diagnose this service failure $python-ai add an
| Stars | 121 |
| Forks | 21 |
| Language | Shell |
| Category | Codex Skill |
| Quality Score | 57.9375149680931/100 |
| Last Updated | 2026-09-08 |
| Created | 2026-06-09 |
| Platforms | cli, codex |
| Est. Tokens | ~11k |
Looking for a titus-ai alternative? If you're comparing titus-ai with other codex skill tools, these 2 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Skills for agentic development on Solana
A Codex/Claude skill that maintains per-repo operating theory documents.
Explore other popular codex skill tools:
titus-ai is Codex and AI skills. It is categorized as a Codex Skill with 121 GitHub stars.
titus-ai is primarily written in Shell.
You can find installation instructions and usage details in the titus-ai GitHub repository at github.com/ChrisTitusTech/titus-ai. The project has 121 stars and 21 forks, indicating an active community.
The top alternatives to titus-ai on Agent Skills Hub include solana-dev-skill, theorist. 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: