autoresearch / lib
CLAUDE.md571 starsChanged 7 months agoMITView on GitHub
- Commits and pushes
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agents/claude.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- tests/CLAUDE.mdCLAUDE.md
- prdSkill
The file
We found no rules to list in this file: it reads as prose or reference rather than instructions.
Files
lib
架构约定
- 存放共享的 Shell 脚本和逻辑库,由
run.sh在启动时 source。 - 每个库文件专注于一个独立的功能域,通过全局变量和回调函数与
run.sh交互。 - 修改共享逻辑时,必须确保不破坏现有 Agent 的调用约定。
- 对
set -e敏感的命令失败路径,优先封装到共享函数中,并在函数内部使用cmd || { ... }或if ! cmd; then ... fi保护。
库文件
| 文件 | 职责 | 关键函数 |
agent_logic.sh | Agent 列表解析、审核者轮转 | parse_agent_list, get_review_agent |
git_push.sh | git push 容错与恢复 | push_branch_with_recovery |
branch_cleanup.sh | PR 合并后 branch 清理 | cleanup_merged_branch |
context.sh | 上下文溢出检测与压缩 | detect_context_overflow, compress_context, handle_context_overflow |
prompt.sh | Prompt 裁剪与 program.md 读取 | trim_prompt_smart, apply_prompt_trimming, get_program_instructions |
subtask.sh | 子任务 CRUD 与 prompt 注入 | has_subtasks, mark_subtask_passed, get_subtask_section |
scoring.sh | 评分提取与阈值判断 | extract_score, check_score_passed, check_sentinel |
progress.sh | 跨迭代经验日志 | append_to_progress, get_progress_section, init_progress |
ui_verify.sh | UI 验证(截图+LLM) | run_ui_verification, capture_screenshot, verify_ui_with_llm |
注意事项
- 脚本应保持 bash 兼容。
- 库文件中的函数依赖
run.sh中的全局变量和回调函数(如log,log_console,error,register_temp_file),这些必须在 source 之前定义。 - 测试文件中如需使用库函数,可以直接 source 对应库文件,或从库文件中提取函数做隔离测试。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

