AgentHygiene: workspace hygiene for coding agents

Set rules for agent leftovers and keep your project root clean

Problem

Developers delegating simple tasks to DeepSeek V4 Flash and Qwen3.8 Flash find that agents dump scripts and research notes directly into the project root, creating a mess after a few rounds. Claude and GPT tend to behave better, leaving users unsure whether it's the harness or the model.

Solution

Scan the workspace before and after agent runs to detect temporary scripts, notes, and logs, then archive them into a .agent/ directory or prompt for cleanup. A configurable rules file defines what counts as an intermediate artifact and where it should go, with a hygiene report after each session.

Users

Individual developers and small teams who juggle multiple coding agents such as Codex, Claude, and DeepSeek harnesses.

MVP

Workspace scanner that detects suspected intermediates by extension and path pattern; per-rule archive or delete actions; CLI command to tidy up after a session; concise hygiene report; macOS/Linux/Windows support.

Revenue

Free open-source core; Pro subscription for team rule sharing, CI integration, and historical trends.

Why now

Multi-agent workflows are going mainstream, yet harnesses disagree on temp file handling, and no standard practice has emerged.