Eivind Kjosbakken writes about improving how developers interact with coding agents by moving away from plain terminal text toward formatted visual output. The core technique involves instructing the agent to generate HTML files rather than inline terminal messages, which allows for headings, bold text, screenshots, and other visual formatting that makes information easier for the human brain to process. He also recommends using the Archify GitHub package to generate visual diagrams when understanding how a system works. The author argues that effective human-agent communication will be critical as developers shift from writing code directly to orchestrating fleets of coding agents.
- Uses a split-panel browser setup (called "superset") to view the agent and the generated HTML file side by side.
- Maintains custom Markdown "skills" that instruct the agent on specific HTML report formats, such as test reports that include the original task context and step-by-step verification instructions.
- Claims to use this technique approximately 100 times per day across all coding sessions.
- Uses a split-panel browser setup (called "superset") to view the agent and the generated HTML file side by side.
- Maintains custom Markdown "skills" that instruct the agent on specific HTML report formats, such as test reports that include the original task context and step-by-step verification instructions.
- Claims to use this technique approximately 100 times per day across all coding sessions.
Julia Muiruri writes about managing large outputs from LLM-powered coding agents by employing stacked pull requests rather than a single, massive diff. By decomposing complex features into logically ordered layers through the `gh-stack` CLI extension, developers can convert unmanageable changesets into small, focused units that are easier to review and maintain. This structured approach allows different experts to focus on specific concerns—such as data models or UI components—within a cohesive dependency chain.
- Gartner predicts coding agents will drive 50% productivity gains across the SDLC by 2028.
- The `gh stack` CLI extension enables cascading rebases and synchronization via commands like `gh stack sync`.
- A "stack map" in the GitHub UI provides one-click navigation between related pull requests in a sequence.
- Gartner predicts coding agents will drive 50% productivity gains across the SDLC by 2028.
- The `gh stack` CLI extension enables cascading rebases and synchronization via commands like `gh stack sync`.
- A "stack map" in the GitHub UI provides one-click navigation between related pull requests in a sequence.
An interactive tool designed to visualize the relationships and flow of code reviews within a development team or project. It helps developers and managers understand how changes move through the review process, identifying bottlenecks and key contributors in the codebase evolution.
- Visual mapping of pull requests and code reviews
- Analysis of reviewer engagement and response times
- Identification of workflow patterns and potential delays
- Visual mapping of pull requests and code reviews
- Analysis of reviewer engagement and response times
- Identification of workflow patterns and potential delays
GitHub Agentic Workflows are built with isolation, constrained outputs, and comprehensive logging. Learn how our threat model and security architecture help teams run agents safely in GitHub Actions.
This post explains how we built Agentic Workflows with security in mind from day one, starting with the threat model and the security architecture that it needs. It details the defense in depth approach using substrate, configuration, and planning layers, emphasizing zero-secret agents through isolation and careful exposure of host resources. It also highlights the staging and vetting of all writes using safe outputs, and comprehensive logging for observability and future information-flow controls.
This post explains how we built Agentic Workflows with security in mind from day one, starting with the threat model and the security architecture that it needs. It details the defense in depth approach using substrate, configuration, and planning layers, emphasizing zero-secret agents through isolation and careful exposure of host resources. It also highlights the staging and vetting of all writes using safe outputs, and comprehensive logging for observability and future information-flow controls.
Code Wiki is a platform that maintains a continuously updated, structured wiki for code repositories, aiming to improve developer productivity by unlocking knowledge buried in source code. It features automated documentation, intelligent context-aware chat, and integrated actionable links.
Plandex is an AI coding agent designed to work directly in the terminal, capable of planning and completing large tasks that span many files and steps. It helps developers build new apps quickly, add features to existing codebases, write tests and scripts, understand code, and fix bugs.
