Back to directory

The Agentics

A sample pack of reusable GitHub Agentic Workflows covering repository maintenance, CI fault analysis, code review and research or status reporting.

The Agentics

The Agentics is a sample family of reusable GitHub Agentic Workflows, grouped by what they do. Maintainer workflows triage issues and pull requests, run a broader repository assistant that investigates issues, replies with comments and proposes engineering improvements, and moderate spam or AI-generated content.

Fault analysis workflows monitor CI and investigate failures automatically, optimize CI for speed and cost, post per-run agent spend summaries on pull requests, and diagnose agent run failures by scanning logs for errors, retry loops, rate limits and token anomalies. Code review workflows offer on-demand opinionated or fine-grained review, and batch review of open pull requests against contribution guidelines.

A further group covers loop engineering, repeatedly researching, developing and maintaining a repository, and research, status and planning workflows such as weekly research digests, issue activity reports and daily repository status summaries.

More in Code quality

See all 94
  • Critic

    critic.run

    A code-change viewer, backed by Y Combinator, built for reviewing work written by coding agents, presenting a plain-language narrative of each change alongside the diff and a running conversation with the agent.

  • GitIntel

    hoangsonww.github.io

    An MCP server that computes git repository analytics such as hotspots, churn, temporal coupling, knowledge maps and risk scoring entirely from local commit history, for AI coding agents like Claude Code and Codex.

  • Axint

    axint.ai

    A verification layer for AI coding agents working on Apple projects: it runs real Xcode builds and tests against the Swift an agent wrote, reconciles static analysis findings against that evidence, and returns a signed proof with the exact repairs still needed.