Triage issues and open fix PRs with a GitHub bot
A cookbook shows a GitHub bot that triages issues, reviews PRs, answers questions with citations, flags AI-slop contributions, and opens patch PRs for human review.
Done with a custom-built or unnamed agent
- What they did
- The bot runs on OpenCode in GitHub Actions with Muse Spark. Each agent is a markdown file with its own tool allow-list. Events route to agents: a PR runs review, a new issue runs triage, and an agent-fix label runs bugfix. A maintainer's /oc comment goes to an orchestrator agent. Bugfix reproduces the bug, patches it, adds a test, runs pytest and opens a PR. It cannot merge.
- How it went
- Sample outputs show triage asking for a repro, review flagging emoji churn as slop, and a prompt injection being flagged. No benchmark is reported yet. Long review turns sometimes return empty, so re-run.
- Worth knowing
- Prompts are tuned for Python, pytest and uv, so adapt AGENTS.md and the agent files. The allow-lists are not a sandbox; human gates and branch protection are the real boundary.
Try it yourself with Claude Code
Help me set up a GitHub bot for [owner/repo] that triages new issues with labels, reviews pull requests, answers questions with citations to the repo's docs or code, and flags low-effort AI-generated contributions. For clear small bugs it should open a patch PR for human review only. Build it, test it on a few existing issues in dry-run mode, and show me the output before it posts any comments or opens any PRs.
Source: dev.meta.ai · Undated
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
- Claude
Build a C compiler with a team of parallel agents
Anthropic's engineering write-up on tasking Opus 4.6 agent teams with building a C compiler.
- Custom agent
Add agentic forgetting to an agent's memory
Someone implemented a rudimentary version of Tim Kellogg's agentic forgetting approach and reports it works impressively even in its simplest form.
Configure a local AI lab and build a knowledge graph by chat
Users had Hermes Agent set up a local AI stack (liteLLM, Postgres, Prometheus, Grafana) and install Gbrain as an MCP server to build a personal knowledge graph.
Migrate toolchain, architecture and site design with Claude Code
A developer had Claude Code switch a monorepo to oxlint/oxfmt, restructure the architecture and redesign a site, validating in a loop; the redesign took days instead of weeks.
Build and deploy a Game of Life simulation site
In a vendor launch demo, Devin built an interactive Game of Life website, added requested features step by step, and deployed it to Netlify.
Resolve a Slack-reported issue with a coding agent
A Codex agent resolved an issue passed to it in about 40 minutes, and an ops agent verified the fix back in Slack.