What did your coding agent do last month?

说明与用途

agentdryrun 扫描器可在不执行任何操作的情况下审计 Claude Code 代理的命令，识别潜在危险操作。

问题

Users want to audit the actions taken by Claude Code’s coding agent without executing or altering anything.

结果

The scanner identified 48 actions, 24 would have passed, 19 would have needed approval, and 5 would have been refused, revealing real force pushes to main.

工作流

• 1. Clone the agentdryrun repo
• 2. Run python -m agentdryrun scan --no-previews to scan the transcript
• 3. Review the generated report card
• 4. Adjust the JSON rules file as needed
• 5. Re‑run to refine results

证据

Claude Code already keeps a transcript of every session on your machine, in ~/.claude/projects

来源

python -m agentdryrun scan reads those files, names what the agent attempted, and judges each action against a rules file as a dry run

来源

A sample report card. Every command in it is invented.

来源

It matches patterns in commands. It misses a script that deletes files, python -c, and paths built at run time, and it flags a few harmless things.

来源