by crabtalk · Claude Skill · ★ 145
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
cargo install cydoniaTaken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 145 |
| Forks | 11 |
| Language | Rust |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 64/100 |
| Open Issues | 5 |
| Last Updated | 2026-10-22 |
| Created | 2026-08-15 |
| Platforms | claude-code, codex, rust |
| Est. Tokens | ~22k |
Cydonia https://github.com/user-attachments/assets/4f13ea59-98ca-491a-9fd9-0bd6ccc2e90d A desktop workspace for the coding agents you run. Open a directory as a project, put any agent that speaks ACP to work in it, and keep what comes out as durable artifacts on disk — articles, boards and tables, not a chat log. [!NOTE] A fresh install includes articles, sessions and boards. Tables are opt-in.
Looking for a cydonia alternative? If you're comparing cydonia with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
One dashboard for all your local AI coding agents. Switch providers, manage sessions, and orchestrate tasks ac
Native terminal multiplexer for coding agents. Persistent sessions, Git worktrees, diffs, and an integrated ed
Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs
Terminal-first, open-source AI agent manager for any CLI agent (agent agnostic), any OS (mac, windows, linux).
Where terminal agents work together. Claude Code, Codex, Copilot CLI and pi on the same task, in one mission,
The minimal interpretable model router that learns & adapts to your agent workflows
Explore other popular claude skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 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: