Name: codex
Author: wietrade

Imported from wietrade/RD-Agent-C (rdagent/scenarios/rl/autorl_bench/agents/codex/AGENTS.md). Install upstream with npx skills add wietrade/RD-Agent-C --skill codex. Copyright stays with the author.

AutoRL-Bench Agent Guidelines

Summary Maintenance (MANDATORY)

You MUST maintain a file called summary.md in the workspace root. Update it after every training attempt and every submission, not just at the end.

Format

# 运行总结

## Attempt N (YYYY-MM-DD HH:MM)
- **状态**: ✅ 成功 / ❌ 失败
- **Score**: X.XX | Improvement: +Y.YY | Best: Z.ZZ
- **训练类型**: SFT / GRPO / PPO / DPO / ...
- **超参数**: lr=X, epochs=Y, batch_size=Z, ...
- **做了什么**: 简述本次尝试的策略和具体操作
- **为什么**: 为什么选择这个方法/这些超参数
- **问题/进步**: 遇到了什么问题，相比上次有什么改进
- **关键代码**: 关键改动的代码片段（如有）
- **下一步建议**: 基于本次结果，下一步打算怎么做

Rules

Append only — never overwrite previous attempts
Analyze code/train.py source to extract training type and hyperparameters
If training fails, extract root cause from error output
"做了什么" and "为什么" are the most important fields — be thorough
Update summary.md IMMEDIATELY after each submission result comes back
Include the grading server response (score, improvement, best) verbatim

Install codex and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "ocm": "1", "id": "wietrade-rd-agent-c-codex", "kind": "skill", "name": "codex", "description": "You MUST maintain a file called `summary.md` in the workspace root. Update it **after every training attempt and every submission**, not just at the end.", "publisher": "wietrade", "version": "1.0.0", "capabilities": { "domains": [ "general" ], "tags": [ "skill-md", "github-agents" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "You MUST maintain a file called `summary.md` in the workspace root. Update it **after every training attempt and every submission**, not just at the end." ], "primary": false, "metadata": { "source": { "provider": "github-agents", "repository": "https://github.com/wietrade/RD-Agent-C", "path": "rdagent/scenarios/rl/autorl_bench/agents/codex/AGENTS.md", "ref": "282721d551388a691e9a52e47a233cbc6f29b098", "url": "https://github.com/wietrade/RD-Agent-C/blob/282721d551388a691e9a52e47a233cbc6f29b098/rdagent/scenarios/rl/autorl_bench/agents/codex/AGENTS.md", "key": "wietrade/RD-Agent-C/rdagent/scenarios/rl/autorl_bench/agents/codex/AGENTS.md" } }, "instructions": "# AutoRL-Bench Agent Guidelines\n\n## Summary Maintenance (MANDATORY)\n\nYou MUST maintain a file called `summary.md` in the workspace root. Update it **after every training attempt and every submission**, not just at the end.\n\n### Format\n\n```markdown\n# 运行总结\n\n## Attempt N (YYYY-MM-DD HH:MM)\n- **状态**: ✅ 成功 / ❌ 失败\n- **Score**: X.XX | Improvement: +Y.YY | Best: Z.ZZ\n- **训练类型**: SFT / GRPO / PPO / DPO / ...\n- **超参数**: lr=X, epochs=Y, batch_size=Z, ...\n- **做了什么**: 简述本次尝试的策略和具体操作\n- **为什么**: 为什么选择这个方法/这些超参数\n- **问题/进步**: 遇到了什么问题，相比上次有什么改进\n- **关键代码**: 关键改动的代码片段（如有）\n- **下一步建议**: 基于本次结果，下一步打算怎么做\n```\n\n### Rul", "cost": { "context_tokens": 251 } }

codex

About

AutoRL-Bench Agent Guidelines

Summary Maintenance (MANDATORY)

Format

Rules

Install codex and it becomes one more candidate the router can pick - when it fits.

Use it

Manifest

Reviews