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 frenzymath · Codex Skill · ★ 356
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Danus safe to install? View the security audit →
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory Danus orchestrates mathematical reasoning agents with fact-graph memory. A main agent (Claude Code) steers a swarm of autonomous codex workers that prove; a cold-start verifier is the sole authority on correctness: a result becomes real only once it passes. Verified results accumulate in a content-addressed fact graph — the system's only source of truth — and a strategy loop (a strong reasoning model) decomposes the problem and steers the swarm. When you have the answer, Danus render
| Stars | 356 |
| Forks | 54 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 61.037885384596/100 |
| Open Issues | 1 |
| Last Updated | 2026-08-27 |
| Created | 2026-07-07 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~15k |
These tools work well together with Danus for enhanced workflows:
Looking for a Danus alternative? If you're comparing Danus 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.
Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, a
Samurai-inspired multi-agent system for Claude Code. Orchestrate parallel AI tasks via tmux with shogun → karo
TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets reco
Give Claude Code, Cursor, Codex CLI a ChatGPT for your codebase. Multi-agent knowledge engine, grounded Q&A wi
The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular,
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
Explore other popular codex skill tools:
Danus is Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory. It is categorized as a Codex Skill with 356 GitHub stars.
Danus is primarily written in Python. It covers topics such as agents, ai4math, automated-reasoning.
You can find installation instructions and usage details in the Danus GitHub repository at github.com/frenzymath/Danus. The project has 356 stars and 54 forks, indicating an active community.
Danus is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to Danus on Agent Skills Hub include SWE-AF, multi-agent-shogun, takt. 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: