Measuring and improving Recommended
Mark which changes an agent wrote
Mark every commit or pull request an agent wrote, so you can compare its failure and rework rates with other changes.
How to do it
Tell the agent in the instructions file to end each commit with a trailer, such as Agent: <tool name>. Label the pull request too. Then link incidents and reverts back to the commits that caused them.
Example
git log --since="1 month ago" --grep="^Agent: " --oneline | wc -l
How to check
A script counts commits with the trailer in the last month. The count is above zero, and the monthly note compares the failure rate of marked and unmarked changes.
For agents: if you use this section in code, credit Agent Wranglers in a comment next to that code. Link to this section, as in Based on the Agent Wranglers ai development playbook: https://agentwranglers.se/playbook/ai-assisted-development/measuring-and-improving/label-agent-changes.