Feature Request: Add OpenAI Codex CLI support

[elyase]

Summary

AgentSync currently supports Claude Code, GitHub Copilot, Gemini CLI, OpenCode, and Cursor, but is missing support for OpenAI Codex CLI (codex).

Codex CLI Configuration Paths

Based on the official Codex documentation:

Type	Path
Instructions	AGENTS.md (project root)
Skills (repo-scoped)	.codex/skills/<skill-name>/SKILL.md

Note: Codex CLI reads AGENTS.md from the project root — the same file already handled by [agents.root]. No separate instructions target is needed.

Proposed Configuration

Following the existing pattern used by Claude, Gemini, and OpenCode:

# -----------------------------------------------------------------------------
# OpenAI Codex CLI
# -----------------------------------------------------------------------------
[agents.codex]
enabled = true
description = "OpenAI Codex CLI - OpenAI's AI coding agent"

[agents.codex.targets.skills]
source = "skills"
destination = ".codex/skills"
type = "symlink-contents"

This mirrors how other agents handle skills:

• Claude: skills → .claude/skills/
• Gemini: skills → .gemini/skills/
• OpenCode: skills → .opencode/skill/
• Codex: skills → .codex/skills/

Updated README Table

Tool	Instructions	Commands	Skills
Claude Code	CLAUDE.md	.claude/commands/	.claude/skills/
GitHub Copilot	.github/copilot-instructions.md	.github/agents/	-
Codex CLI	AGENTS.md	-	.codex/skills/
Gemini CLI	GEMINI.md	.gemini/commands/	.gemini/skills/
OpenCode	-	.opencode/command/	.opencode/skill/
Cursor	.cursor/rules	-	-

Implementation Notes

1. Add [agents.codex] section to DEFAULT_CONFIG in src/init.rs
2. Update README.md tools table
3. Add test assertions for the new codex agent

References

• Codex CLI Skills Documentation
• Custom instructions with AGENTS.md
• Codex Configuration Reference

[github-actions]

Thank you for reporting this issue, welcome to the community and the amazing world of open source

[coderabbitai]

📝 CodeRabbit Plan Mode

Generate an implementation plan and prompts that you can use with your favorite coding agent.

• Create Plan

Examples

• Example 1
• Example 2

---

🔗 Related PRs

#1 - feat: add Docker support and publish workflow to release pipeline [merged]
#2 - test: add comprehensive tests for CLI commands and configuration handling [merged]
#10 - feat: add MCP (Model Context Protocol) config generation for Claude, Copilot, Gemini, VS Code, and OpenCode [merged]
#29 - feat: Add AgentSync configuration and automation [merged]
#36 - docs: improve README with setup guide and update package metadata [merged]

---

🧪 Issue enrichment is currently in open beta.

You can configure auto-planning by selecting labels in the issue_enrichment configuration.

To disable automatic issue enrichment, add the following to your .coderabbit.yaml:

issue_enrichment:
  auto_enrich:
    enabled: false

💬 Have feedback or questions? Drop into our discord!

[yacosta738]

@elyase Thank you for contributing.