Customization

Shape how the AI works in your repo with plain files in the .editvolt/ folder — versionable, reviewable, and shareable with your team.

.editvolt/
├── rules/          # house rules injected into every conversation
├── skills/         # repeatable multi-step workflows
├── subagents/      # specialized delegate agents
├── hooks/          # pre/post tool-use shell hooks (consented)
├── commands/       # your own slash commands
├── automations/    # JSON-defined recurring automations
└── permissions.json  # terminal command allowlist

Rules

Markdown files that state standing constraints — "no hardcoded secrets", "validate at boundaries" — injected into the system prompt for every conversation in the workspace.

Skills & subagents

Skills capture repeatable workflows the AI can invoke (e.g. split-to-PRs). Subagents are specialized delegates — a security reviewer, a docs editor — that the main agent can hand tasks to.

Hooks

Shell scripts that run before or after the agent uses a tool — lint after every edit, block certain paths, notify your team. Hooks require explicit consent before they run.

Slash commands

Add your own commands alongside the built-ins (/explain, /fix, /review, /test, /architect, /why, /scaffold) by dropping prompt files into .editvolt/commands/.

MCP servers

Connect Model Context Protocol servers to give the AI extra tools (databases, ticketing systems, internal APIs). Every MCP tool requires per-tool consent, and you can restrict which servers are allowed with editvolt.agents.mcp.allowlist.

Import what you already have

The Customization Studio (Settings → Skills & Rules) imports your existing Cursor, Claude, and Copilot configurations and AGENTS.md files — including honoring .cursorignore.