How I Cleared a 214-Issue Backlog on My Open-Source Repo With Claude Code

Description and use

Over three weeks, using Claude Code I cleared a 214‑issue backlog in an open‑source repo, classifying, reproducing, and fixing 19 real bugs, leaving only 9 active issues.

Problem

A mid-sized open-source CLI library had 214 open issues, many unlabeled, duplicates, and stale, making maintenance difficult and risking loss of real bugs.

Outcome

Three weeks of AI-assisted triage reduced the backlog from 214 to 9 issues, uncovered 19 live bugs, and improved community perception without mass-closing.

Workflow

• 1. Dump all open issues to a JSON file using gh CLI.
• 2. Prompt Claude Code to classify each issue into category, status_guess, confidence, and evidence.
• 3. Verify likely-fixed issues by running reproduction steps against current main and recording output.
• 4. Draft replies for all issues with a rule that the agent never posts; review drafts in batches and post approved comments.
• 5. Fix confirmed bugs using reproduction tests as regression tests, reviewing diffs before merging.

Evidence

The first pass took the agent a couple of hours of chugging through the codebase and git history. Results on the 214 issues: ...

Source

For issue #N: extract the reproduction steps from the report. Run them against current main in a scratch directory. Record: REPRODUCED / NOT-REPRODUCED / CANNOT-ATTEMPT (missing info). Save the actual terminal output as proof.

Source