by trustunknown · Codex Skill · ★ 342
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is thomas safe to install? View the security audit →
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. Hard limits in v0 (by design, see §6): No LLM calls. Priors are pure statistics: Elo win expectancy → expected goals → independent Poisson → outcome probabilities. No private keys, no real orders. prints intended trades (edge / fractional Kelly) and stops there. No invented numbers. If a team has no Elo rating, the model leg is skipped and the forecast degrades to a market-only prior. The belief ledger philosophy Most trading bots are black boxes that remember only their PnL. OpenThomas treats the belief as the primary artifact: every forecast it ever emits is appended to as a self-contained JSON record — probability, prior, method, and evidence chain (which Elo ratings, which market prices, which blend λ). Outcomes are back-filled into a separate ; the original belief is never edited.
| Stars | 342 |
| Forks | 51 |
| Language | TypeScript |
| Category | Codex Skill |
| Quality Score | 65.2950920297028/100 |
| Open Issues | 1 |
| Last Updated | 2026-05-08 |
| Created | 2025-10-22 |
| Platforms | node |
| Est. Tokens | ~688k |
These tools work well together with thomas for enhanced workflows:
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.
Universal adapter between AI agents and model providers
Universal adapter between AI agents and model providers
TrustedExecBench: Scenario-grounded security evaluation for autonomous personal AI assistants.
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, M
Security checkups and red-team tests for AI agents.
Security checkups and red-team tests for AI agents.
Explore other popular codex skill tools:
thomas is Universal adapter between AI agents and model providers. It is categorized as a Codex Skill with 342 GitHub stars.
thomas is primarily written in TypeScript. It covers topics such as agent-security, agent-security-eval, agent-security-red-teaming.
You can find installation instructions and usage details in the thomas GitHub repository at github.com/trustunknown/thomas. The project has 342 stars and 51 forks, indicating an active community.
The top alternatives to thomas on Agent Skills Hub include thomas, thomas, TrustedExecBench. 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: