aide_init
Initialize an AIDE development environment by creating structured configuration files through a guided, step-by-step process that respects user confirmation at each stage.
Instructions
Bootstrap the AIDE development environment into a project. Returns structured JSON for agent consumption — not prose.
The tool uses a two-call pattern for progressive disclosure:
First call (no category param): Returns a lightweight summary — every step with name, status (would-create/would-skip/exists), category, and filePath, but NO content fields. Also returns brainHints (vault candidates) and detected framework. Use this to understand what needs to be done.
Second call (with category param): The tool writes all would-create files directly to disk itself and returns a manifest — steps with filePath, status (created or exists), and name, but NO content. The agent never sees file content and never uses the Write tool for new files.
Exception — MCP steps: For MCP steps, the manifest includes prescription data (key name and entry object) so the agent can read the existing config, merge, and write. The tool never touches MCP config directly.
Exception — brain category: When calling with category=brain, also pass brainPath with the user-confirmed vault path. The tool creates the vault scaffold directories directly.
Exception — IDE VS Code steps: IDE steps that need external tooling (VS Code CLI) return instructions for the agent to execute, since those aren't simple file writes.
IMPORTANT — one-at-a-time wizard pattern using AskUserQuestion:
Do NOT present a summary table of all categories. Do NOT offer "all" as an option. Do NOT ask conversational questions — use the AskUserQuestion tool with structured options at every pause point. Walk the user through ONE category at a time:
Call without
categoryfirst to get the metadataPresent ONLY the detected framework — use AskUserQuestion with Yes/{alternatives} options. STOP.
Present ONLY the first category with would-create steps — use AskUserQuestion with Yes/Skip options. STOP.
If confirmed, call again with
category=X(andbrainPathwhen category is brain). The tool writes files and returns a manifest. Report what was created, then present the NEXT category with AskUserQuestion. STOP.Repeat step 4 for each remaining category in order: methodology, commands, agents, skills, mcp, brain, ide, readme
For brain: use AskUserQuestion with brainHints as labeled options (user can pick Other for custom path). STOP.
For MCP: use AskUserQuestion with Merge/Skip options. Merge the
prescriptionentry into the existing config yourself (read → merge → write). STOP.For IDE: use AskUserQuestion with multiSelect for Zed/VS Code/Neither. STOP.
Each step is ONE AskUserQuestion → wait for selection → then proceed. Never show multiple categories at once. Never ask open-ended conversational questions.
Do NOT auto-apply steps without user confirmation.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| framework | No | Force a specific framework instead of auto-detecting. Use this when re-calling after the user confirms or overrides detection. | |
| path | No | Custom project root path (defaults to server working directory) | |
| category | No | Write all would-create files for this category to disk and return a manifest. Omit on the first call to get a metadata-only summary of all steps. | |
| brainPath | No | Resolved brain vault path. Required when category=brain. The agent provides this after interviewing the user. |