thomas — repository deleted, archived audit

Repository no longer available — thomas-security/thomas returns 404 on GitHub. It was deleted, or its owner's account was removed. The data below is our last successful snapshot.

by thomas-security · Codex Skill · ★ 344

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

agent-securityagent-security-evalagent-security-red-teamingai-agent-securityopenclawopenclaw-security

Quick Facts

Stars344
Forks51
LanguageTypeScript
CategoryCodex Skill
LicenseAGPL-3.0
Quality Score67/100
Open Issues1
Last Updated2026-05-01
Created2025-10-22
Platformsnode
Est. Tokens~684k

About thomas

OpenThomas An open-source Bayesian trading worker for prediction markets, named after Thomas Bayes. v0 scope: forecast 2026 World Cup match moneyline markets on Polymarket with statistical priors (Elo → Poisson), de-vigged market prices, and a transparent blend — then keep every belief on an append-only ledger and work as a forecaster on a WorkPnP pool. Trade decisions are computed dry-run only.

Compatible Skills

These tools work well together with thomas for enhanced workflows:

  • thomas — semantic(1.00)+rare_topics+same_lang+similar_pop+shared_platform (70%)
  • TrustedExecBench — semantic(0.89)+rare_topics+same_lang+similar_pop+shared_platform (70%)
  • shellward — semantic(0.40)+complementary+rare_topics+same_lang+similar_pop+shared_platform (69%)
  • agent-threat-rules — semantic(0.30)+complementary+rare_topics+same_lang+similar_pop+shared_platform (60%)

thomas alternative? Top 6 similar tools

Looking for a thomas alternative? If you're comparing thomas 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.

  • thomas by openguardrails · ⭐ 344

    Universal adapter between AI agents and model providers

  • TrustedExecBench by openguardrails · ⭐ 342

    TrustedExecBench: Scenario-grounded security evaluation for autonomous personal AI assistants.

  • thomas by trustunknown · ⭐ 342

    Universal adapter between AI agents and model providers

  • hol-guard by hashgraph-online · ⭐ 1.1k

    Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, maliciou

  • openguardrails-oss by openguardrails · ⭐ 338

    Security checkups and red-team tests for AI agents.

  • thomas-security by openguardrails · ⭐ 338

    Security checkups and red-team tests for AI agents.

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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