by mainline-org · Codex Skill · ★ 199
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
go install github.com/mainline-org/mainline@latest
npx --yes skills update mainline --global --yesTaken from the project's README on GitHub.
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.
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 | 199 |
| Forks | 13 |
| Language | Go |
| Category | Codex Skill |
| Quality Score | 66/100 |
| Open Issues | 3 |
| Last Updated | 2026-10-27 |
| Created | 2026-04-25 |
| Platforms | claude-code, codex, go |
| Est. Tokens | ~18k |
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.
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
Reusable project context and specialist workflows for the AI tools you already use. Agents, skills, rules and
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
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: