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 mainline-org · Codex Skill · ★ 193
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is mainline safe to install? View the security audit →
Mainline Website: https://mainline.sh Hosted Hub: https://mainline.sh/hub/ Detailed reference: docs/reference.md 中文版本: README.zh.md We have code review. Now we need intent review. Mainline is a Git-native memory layer for coding agents. It gives agents and reviewers repo memory before the diff: prior decisions, constraints, abandoned approaches, validation notes, and related in-flight work. AI agents make code cheap to produce and harder to review. Mainline makes the intent reviewable before the generated code lands. Review the intent before you review the code. The Problem Code review was built for a world where humans wrote most of the code. The diff was expensive, so it was usually small enough for reviewers to infer the intent.
| Stars | 193 |
| Forks | 12 |
| Language | Go |
| Category | Codex Skill |
| Quality Score | 66.2788899491002/100 |
| Open Issues | 3 |
| Last Updated | 2026-08-13 |
| Created | 2026-04-25 |
| Platforms | claude-code, codex, go |
| Est. Tokens | ~18k |
These tools work well together with mainline for enhanced workflows:
Looking for a mainline alternative? If you're comparing mainline 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.
Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Codex CLI: symbol graph,
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. W
An LLM council that reviews your coding agent's every move
Curated AI coding agent skills and AGENTS.md playbooks for Codex, Claude Code, Cursor, OpenClaw, and other SKI
Explore other popular codex skill tools:
mainline is Git-native memory for coding agents. Repo memory before the diff.. It is categorized as a Codex Skill with 193 GitHub stars.
mainline is primarily written in Go. It covers topics such as agent-context, agent-memory, ai-agents.
You can find installation instructions and usage details in the mainline GitHub repository at github.com/mainline-org/mainline. The project has 193 stars and 12 forks, indicating an active community.
The top alternatives to mainline on Agent Skills Hub include sverklo, memorix, Overture. 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: