by oil-oil · Codex Skill · ★ 60
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
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 | 60 |
| Forks | 7 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 67/100 |
| Open Issues | 1 |
| Last Updated | 2026-10-13 |
| Created | 2026-10-04 |
| Platforms | claude-code, cli, codex, node |
| Est. Tokens | ~15k |
· MIT · Website · Downloads · Usage · Contributing · Agent Skill · 简体中文 Oil Git is a read-only desktop viewer for local Git repositories. Open a project to inspect its current branch, working tree changes, commit history, and file diffs. Keep using Git in your editor, terminal, or agent; Oil Git follows changes made to the real repository. What you can inspect Files grouped by mer
These tools work well together with oil-git for enhanced workflows:
Looking for a oil-git alternative? If you're comparing oil-git 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.
The Git client that actually resolves conflicts: 8 deterministic patterns auto-resolve the ones that were neve
Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support
The review app for code your agent writes. Native Rust/GPUI desktop app with real Git workflows.
Local-first desktop app for AI coding agents (Claude Code, Codex). Built with Tauri v2 + Svelte 5.
Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes
Use Claude Code on Kanban WebUI
Explore other popular codex 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: