pstack-codex — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

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 ScriptedAlchemy · Codex Skill · ★ 63

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is pstack-codex safe to install? View the security audit →

About pstack-codex

pstack for Codex A Codex-native adaptation of Lauren Tan's pstack, preserving its workflows, playbooks, principles, and agent personas while adapting host-specific execution to Codex. This is an independent port, not an official Cursor or OpenAI plugin. The plugin lives in ; makes this repository a native Codex marketplace. Read the runtime contract, port coverage and runtime boundaries, and per-file source coverage. Tool availability depends on the Codex host, permissions, and connected integrations. No credentials are bundled. Install Requires a Codex build with support, Git, and Python 3.11+ for validation. If your shell defaults to an older Python, set to the Python 3.11+ executable when running the installer (for example, on a matching Homebrew installation). The script validates the package, registers this checkout as the marketplace, and installs . It does not edit your Codex configuration by hand or overwrite personal agent definitions. Start a new Codex task after installation and invoke . Most pstack skills are intentionally explicit-only;

Quick Facts

Stars63
Forks5
LanguageTypeScript
CategoryCodex Skill
LicenseMIT
Quality Score62.8699388908651/100
Open Issues3
Last Updated2026-10-02
Created2026-09-17
Platformscodex, node
Est. Tokens~15k

Compatible Skills

These tools work well together with pstack-codex for enhanced workflows:

  • Codex-Workflows — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)
  • forgecat-agent-profiles — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (57%)

pstack-codex alternative? Top 1 similar tools

Looking for a pstack-codex alternative? If you're comparing pstack-codex with other codex skill tools, these 1 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • theorist by blader · ⭐ 191

    A Codex/Claude skill that maintains per-repo operating theory documents.

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is pstack-codex?

pstack-codex is Codex-native port of Lauren Tan's pstack: 47 skills, 23 playbooks, agent personas, multi-agent workflows, and Benny automation adapters. Includes a Codex marketplace and installer.. It is categorized as a Codex Skill with 63 GitHub stars.

What programming language is pstack-codex written in?

pstack-codex is primarily written in TypeScript.

How do I install or use pstack-codex?

You can find installation instructions and usage details in the pstack-codex GitHub repository at github.com/ScriptedAlchemy/pstack-codex. The project has 63 stars and 5 forks, indicating an active community.

What license does pstack-codex use?

pstack-codex is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to pstack-codex?

The top alternatives to pstack-codex on Agent Skills Hub include theorist. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Codex Skill tools