2 posts tagged with "coding-agent"

Better Harness can inspect local evidence from multiple coding-agent hosts: sessions, configured assets, tool activity, and the engineering context around them. But once developers work with several Agents across projects and machines, the central problem is no longer simply aggregating scattered data.

The harder question is how to connect that data into a delivery chain that runs from task intent through execution and verification. How can the same system help an individual complete a task, a team reuse a working method, and an organization operate agent-enabled delivery at scale?

Our working direction is this: an Agent should not only finish one coding task. It should become a delivery capability that can be verified, reproduced, governed, and operated.

Lately we have been trying to improve one capability in Better Harness: automatic SKILL distillation — recognizing the recurring work paths inside an agent's real sessions, and then deciding which of them are worth capturing as a reusable SKILL. Once we actually started, we found the problem was far harder than "just analyze a session."

For a real software task, an agent's behavior never happens in isolation. It starts from a requirement or a user story, moves through understanding the intent, exploring context, editing code, and verifying the change, and only then produces a contribution someone can review. Looking at the session alone, you can see what the agent did, but it is hard to tell why those actions happened, or which of them actually made it into the final delivery.

So we began treating a single agent delivery as one continuous chain. Today, you only need to run this inside a project directory:

npx @qoder-ai/better-harness inspector

and you get a local, read-only Harness Inspector page that puts the project's agent sessions, file activity, and Git commits into one interactive view.