by o8-run · MCP Server · ★ 63
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 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 | 63 |
| Forks | 12 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 62/100 |
| Open Issues | 270 |
| Last Updated | 2026-11-20 |
| Created | 2026-03-11 |
| Platforms | claude-code, codex, mcp, node |
| Est. Tokens | ~16k |
o8 Run a fleet of coding agents. Approve what ships. o8 is an open-source control room for one person running several AI coding agents across their repositories, the governance layer above them. Claude Code, Codex, Grok Build, DeepSeek Harness, OpenCode, Gemini, and twelve more do the work in isolated git worktrees; o8 brings the work, the reviews, and the decisions into one place so you can...
These tools work well together with o8 for enhanced workflows:
Looking for a o8 alternative? If you're comparing o8 with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Native terminal multiplexer for coding agents. Persistent sessions, Git worktrees, diffs, and an integrated ed
A Rust-native, multi-agent development cockpit for macOS — spawn isolated worktrees, run CLI coding agents in
Your agents. Your workspace. Your control—from prompt to commit, desktop to mobile. Works with Codex, Claude C
Reusable project context and specialist workflows for the AI tools you already use. Agents, skills, rules and
Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.
Native macOS terminal for running, monitoring, and reviewing parallel Claude Code and Codex sessions.
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 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: