I build small, testable open-source tools for coding-agent workflows and OSS maintenance.
My current focus is practical AI engineering infrastructure: deterministic CLIs, repo quality gates, local security checks, and upstream fixes in Python developer tooling.
| Project | What it does |
|---|---|
| issue-to-agent | Turns GitHub issues into ready-to-run task packs for Codex, Claude Code, Cursor, and Copilot. |
| mergepack | Turns PR diffs into agent-ready merge packets for maintainers and reviewers. |
| loopback-litmus | Checks browser-to-localhost exposure in local AI agent and MCP control planes. |
| repo-brief | Generates compact repo briefs for humans and coding agents. |
| action-pin-check | Audits GitHub Actions workflows for mutable or missing action pins. |
| readme-command-check | Checks README shell commands before users copy broken quickstarts. |
- Narrow tools with clear failure modes.
- Local-first by default: no API keys, no network dependency unless the task needs it.
- Reproducible checks over vague claims.
- Small PRs, focused tests, and useful maintainer context.
- Agent-ready handoff formats for issues, PRs, and repository context.
- Shell and browser control-plane validation for local AI tooling.
- Practical OSS maintenance work in Python CLI, testing, and documentation ecosystems.
