AgentSlice – Make AI coding agents ask before they edit
AgentSlice is a free, open-source workflow kit designed for AI coding agents. It helps these agents ask for approval before making edits, reducing common issues like context drift and unauthorized changes. The workflow is structured around a series of Markdown files that guide the agent through planning, approval, and execution phases.
- ▪AgentSlice improves AI coding agents' performance by implementing a project-local workflow.
- ▪The kit includes various Markdown files that define phases, gates, and required actions for the agents.
- ▪It supports multiple AI tools such as Cursor, Claude Code, Codex, and Windsurf.
Opening excerpt (first ~120 words) tap to expand
AgentSlice A free, open-source workflow kit for AI coding agents. Makes Cursor, Claude Code, Codex and Windsurf ask before they edit. Website • Discussions Quick start npx agentslice init # Paste INSTALL_PROMPT.md into Cursor / Claude Code / Codex / Windsurf # Watch the agent ask, plan, and wait That's it. No build step, no runtime, no editor extension. 30-second demo What it does AI coding agents work better when they know the next step. Without a workflow they suffer from three failure modes developers describe constantly: Context drift — the agent forgets what was decided two messages ago and reopens settled questions. Wandering edits — the agent expands the task, touches files you didn't ask about, and burns tokens on detours.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.