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 oil-oil · Codex Skill · ★ 120
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is codex-team-mode safe to install? View the security audit →
English · 简体中文 is a Codex Skill for coordinating four custom agents across substantial development, research, analysis, planning, document, data, and content tasks. The main thread keeps unresolved decisions and verifies the final result; subagents take on work that benefits from focused context, lower cost, safe parallelism, or independent judgment. It is a routing guide, not a mandatory pipeline. The team Explorer（探索者）· Luna Medium · read-only — gathers evidence across current web sources, documents, data, code, APIs, logs, and configuration. Executor（执行者）· Luna Medium · workspace-write — completes clear, bounded, low-risk work with deterministic checks. Complex Executor（复杂执行者）· Sol High · workspace-write — completes substantial but bounded work after the intended outcome and safety boundaries are clear. Reviewer（复审者）· Sol High · read-only — independently checks stable code, reports, plans, analyses, data, and other artifacts from fresh context. Luna keeps routine exploration and execution economical. Sol is reserved for consequential execution and independent review, where missing an important detail co
| Stars | 120 |
| Forks | 14 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 65.7358488948746/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-16 |
| Created | 2026-07-17 |
| Platforms | codex, python |
| Est. Tokens | ~14k |
Looking for a codex-team-mode alternative? If you're comparing codex-team-mode 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.
Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.
Cross-LLM sub-agent orchestration as an Agent Skills. Route tasks to Codex, Claude Code, Grok, GLM, Kimi, Curs
Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. W
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Multi-agent orchestration extension for Gemini CLI — 22 specialists, parallel subagents, persistent sessions,
10 Claude sessions running. What are they doing? Live dashboard — monitor, cost tracking, search, sub-agent vi
Explore other popular codex skill tools:
codex-team-mode is 协调探索、执行和独立评审，让复杂任务按明确职责并行推进，由主 Agent 统一验收。. It is categorized as a Codex Skill with 120 GitHub stars.
codex-team-mode is primarily written in Python. It covers topics such as agent-skill, ai-agents, codex.
You can find installation instructions and usage details in the codex-team-mode GitHub repository at github.com/oil-oil/codex-team-mode. The project has 120 stars and 14 forks, indicating an active community.
codex-team-mode is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to codex-team-mode on Agent Skills Hub include sub-agents-mcp, sub-agents-skills, compose-skill. 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: