I maintain two small open-source CLIs for working with AI agents. aisync is a local CLI for Multi-Agent Context Management, Coordination & Observability across AI coding tools. existence-trace is a journal that an AI reads, and it has to prove it used what it learned. This morning existence-trace got its first pull request from someone outside the project. An AI agent (Claude Code) reviewed it and merged it for me, so this post is about what the agent checked, and what it did not.
How the pull request came about
The agent had been testing existence-trace's weekly audit and found that an empty week prints "Every chain is complete" with no count of chains audited. It filed that as issue #4 at 14:41 UTC, with the commands to reproduce it, the output, the line in etrace/container/audit.py where passed comes from, and three options. The first option named the new JSON field and gave the exact wording for the report line, and the pull request below follows it. The issue carries the labels good first issue and help wanted.
At 14:58 UTC the user i-sayankh forked the repository. At 15:12 UTC they opened PR #8, "Report empty weekly audits explicitly", with two commits: 37 lines added and 2 removed across six files, etrace/cli.py, etrace/container/audit.py, etrace/render.py and three test files. The description said Closes #4 and listed what was tested, including that 11 unrelated failures remained on their Windows machine. I do not know how they found the issue.
What the agent checked
- It read the whole diff before running anything. The changes are display strings, one new JSON field (
chains_audited) and tests. Nothing opens a network connection, runs a command or writes outside the tests. - It cloned the repository into an empty directory, checked out the PR branch, and set a temporary
HOMEso nothing could touch real data. - It ran the three new tests: 46 tests in the audit and render modules passed, and the new CLI test passed.
- It ran the whole suite on the PR branch: 650 tests, OK. On
mainthe same command ran 648 tests, OK. The difference is the two tests the PR adds. - It left a comment on the PR saying what it had run, with a note that an AI agent did the review, and merged with a merge commit so that both of the contributor's commits stay in the history (
188b5a8). Issue #4 closed by itself.
What it did not check
- Windows. The contributor reported 11 failures there, which I did not see on macOS, and I did not look into them.
- No CI ran on the PR branch (
gh pr checksreported nothing), so the local run was the only check. - The agent did not re-run the experiments from the earlier article against the new code. On
mainan empty week now reads "Result: passed (0 chains this week, nothing was audited)." The v0.4.6 tag and the PyPI-style install still behave as before until a release is cut. - The merge decision was made by an agent working for me. I can still revert it.
What I would take from it
The issue was small, had a reproduction that took three commands, and said what a good result looks like. That is what a stranger needs to start. The fix came 31 minutes after the issue, and 14 minutes after the fork. One data point does not make a trend, and I cannot say that the issue text caused it.
If you run a small project, label two or three issues good first issue and write the reproduction first. aisync has several open (https://github.com/MaxonT/aisync/issues?q=is%3Aopen+label%3A%22good+first+issue%22), for example the path matching in aisync claim (#31, #32).
- PR: https://github.com/MaxonT/existence-trace/pull/8
- Issue: https://github.com/MaxonT/existence-trace/issues/4
- Repo (MIT): https://github.com/MaxonT/existence-trace
- Sibling project: https://github.com/MaxonT/aisync (Multi-Agent Context Management, Coordination & Observability)
This post was written by an AI agent (Claude Code) for the maintainer. The review and the test runs described above were real runs, and the numbers are copied from them.
