From dfe3d963130c7ca10dec9392e9acd2c70b56f663 Mon Sep 17 00:00:00 2001 From: dave Date: Sat, 28 Mar 2026 15:12:54 +0000 Subject: [PATCH] docs: move wizard instructions to .storkit/README.md for LLM-agnostic access The wizard check was only in CLAUDE.md which is Claude-specific. Move the primary instruction to .storkit/README.md (step 1 of First Steps) so any LLM reading the dev process docs will discover the wizard. CLAUDE.md keeps a shorter pointer to the README. Also fix stale .story_kit/ paths to .storkit/ in the README. Co-Authored-By: Claude Opus 4.6 (1M context) --- .storkit/README.md | 9 +++++---- server/src/io/fs/scaffold.rs | 8 +++----- 2 files changed, 8 insertions(+), 9 deletions(-) diff --git a/.storkit/README.md b/.storkit/README.md index 88fdc7df..d3e6481b 100644 --- a/.storkit/README.md +++ b/.storkit/README.md @@ -9,16 +9,17 @@ When you start a new session with this project: -1. **Check for MCP Tools:** Read `.mcp.json` to discover the MCP server endpoint. Then list available tools by calling: +1. **Check Setup Wizard:** Call `wizard_status` to check if project setup is complete. If the wizard is not complete, guide the user through the remaining steps conversationally using `wizard_generate`, `wizard_confirm`, `wizard_skip`, and `wizard_retry`. Do not expose tool names or step numbers to the user — just ask about their project and generate files behind the scenes. +2. **Check for MCP Tools:** Read `.mcp.json` to discover the MCP server endpoint. Then list available tools by calling: ```bash curl -s "$(jq -r '.mcpServers["storkit"].url' .mcp.json)" \ -H 'Content-Type: application/json' \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' ``` This returns the full tool catalog (create stories, spawn agents, record tests, manage worktrees, etc.). Familiarize yourself with the available tools before proceeding. These tools allow you to directly manipulate the workflow and spawn subsidiary agents without manual file manipulation. -2. **Read Context:** Check `.story_kit/specs/00_CONTEXT.md` for high-level project goals. -3. **Read Stack:** Check `.story_kit/specs/tech/STACK.md` for technical constraints and patterns. -4. **Check Work Items:** Look at `.story_kit/work/1_backlog/` and `.story_kit/work/2_current/` to see what work is pending. +3. **Read Context:** Check `.storkit/specs/00_CONTEXT.md` for high-level project goals. +4. **Read Stack:** Check `.storkit/specs/tech/STACK.md` for technical constraints and patterns. +5. **Check Work Items:** Look at `.storkit/work/1_backlog/` and `.storkit/work/2_current/` to see what work is pending. --- diff --git a/server/src/io/fs/scaffold.rs b/server/src/io/fs/scaffold.rs index 115f87e0..94507e89 100644 --- a/server/src/io/fs/scaffold.rs +++ b/server/src/io/fs/scaffold.rs @@ -59,11 +59,9 @@ parallel calls work fine.\n\ \n\ Read .storkit/README.md to see our dev process.\n\ \n\ -IMPORTANT: This project uses storkit for development workflow management. \ -On your first conversation, call the `wizard_status` MCP tool to check if \ -project setup is complete. If it is not complete, guide the user through \ -the remaining wizard steps using `wizard_generate`, `wizard_confirm`, \ -`wizard_skip`, and `wizard_retry`.\n"; +IMPORTANT: On your first conversation, call `wizard_status` to check if \ +project setup is complete. If not, read .storkit/README.md for the full \ +setup wizard instructions and guide the user through it conversationally.\n"; const STORY_KIT_CLAUDE_SETTINGS: &str = r#"{ "permissions": {