claude-code-autoconfig 1.0.15 → 1.0.16

package/.claude/commands/autoconfig.md

@@ -1,266 +1,176 @@
-<!-- @description The command you just ran. Analyzes your project and populates CLAUDE.md with real context. Re-run anytime your stack changes. -->
-
-# Autoconfig
-
-Analyze this project and configure Claude Code with real context.
-
-## Step 0: Migrate Existing Configuration
-
-Check for existing Claude Code configuration and migrate to the new structure.
-
-### 0a. AGENTS.md → .claude/agents/
-
-If an `AGENTS.md` file exists (at root or in `.claude/`):
-1. Parse each agent definition (usually separated by headings)
-2. Create individual files in `.claude/agents/` named after the agent (kebab-case)
-3. Each file should contain that agent's prompt/instructions
-4. Delete or rename the original AGENTS.md to AGENTS.md.migrated
-5. Notify: "Migrated X agents from AGENTS.md to .claude/agents/"
-
-### 0b. RULES.md → .claude/rules/
-
-If a `RULES.md` file exists or CLAUDE.md contains a "Rules" section:
-1. Extract rule definitions
-2. Create appropriate rule files in `.claude/rules/` based on path patterns
-3. Notify: "Migrated rules to .claude/rules/"
-
-### 0c. Custom Commands → .claude/commands/
-
-If CLAUDE.md contains custom slash command definitions:
-1. Extract each command definition
-2. Create `.claude/commands/[command-name].md` for each
-3. Notify: "Migrated X custom commands to .claude/commands/"
-
-### 0d. Team Feedback → .claude/feedback/
-
-If CLAUDE.md contains **team feedback** (corrections, preferences, warnings):
-
-**Feedback patterns:**
-- Corrections: "Don't use X", "Always use Y instead", "Never do Z"
-- Preferences: "We prefer...", "Team convention is...", "Boris's setup uses..."
-- Warnings: "Be careful with...", "Watch out for...", "This is deprecated"
-- Custom guidance: Learned behavior or team-specific knowledge
-- Notes about past mistakes
-
-**NOT feedback (standard config - will be regenerated):**
-- Project name and description
-- Tech stack listing
-- Build/test/run commands
-- File structure descriptions
-
-**If feedback found:**
-1. Extract feedback sections
-2. Append to `.claude/feedback/FEEDBACK.md` with header:
-   ```markdown
-   ## [Date]: Migrated from CLAUDE.md
-
-   [extracted feedback]
-   ```
-3. Notify: "Migrated team feedback to .claude/feedback/FEEDBACK.md"
-
-### 0e. MCP Configs
-
-If CLAUDE.md mentions MCP servers or tool integrations:
-1. Extract server configurations
-2. Add to `.claude/.mcp.json` in the mcpServers object
-3. Notify: "Migrated MCP config to .claude/.mcp.json"
-
-## Step 1: Create Scaffold Files
-
-Create these files if they don't already exist:
-
-### .claude/settings.json
-```json
-{
-  "permissions": {
-    "allow": [
-      "Read(./**)",
-      "Edit(./**)",
-      "Write(./**)",
-      "WebSearch",
-      "WebFetch",
-      "Bash(npm run dev)",
-      "Bash(npm run build)",
-      "Bash(npm run lint)",
-      "Bash(npm run lint:fix)",
-      "Bash(npm run typecheck)",
-      "Bash(npm run test)",
-      "Bash(npm run test:*)",
-      "Bash(npm run validate)",
-      "Bash(git status)",
-      "Bash(git diff:*)",
-      "Bash(git add:*)",
-      "Bash(git commit:*)",
-      "Bash(git push:*)",
-      "Bash(git pull)",
-      "Bash(git checkout:*)",
-      "Bash(git branch:*)"
-    ],
-    "deny": [
-      "Read(./.env)",
-      "Read(./.env.*)",
-      "Read(./secrets/**)",
-      "Read(./**/credentials.*)",
-      "Read(./**/*.pem)",
-      "Read(./**/*.key)",
-      "Bash(rm -rf:*)",
-      "Bash(curl:*)",
-      "Bash(wget:*)"
-    ]
-  }
-}
-```
-
-### .claude/.mcp.json
-```json
-{
-  "mcpServers": {}
-}
-```
-
-### .claude/feedback/FEEDBACK.md
-```markdown
-<!-- @description Team-maintained corrections and guidance for Claude. Add notes here when Claude does something wrong — it learns for next time. This directory persists across /autoconfig runs. -->
-
-# Team Feedback
-
-Add corrections and guidance here when Claude does something wrong.
-Claude reads this directory and learns for next time.
-
-## YYYY-MM-DD: Brief title
-
-Describe what Claude did wrong and what to do instead.
-Keep entries brief and actionable.
-```
-
-### .claude/rules/ (empty directory)
-Create the directory if it doesn't exist.
-
-### CLAUDE.md (template)
-If no CLAUDE.md exists, create it with this template:
-```markdown
-# Project Name
-
-> Run `/autoconfig` to populate this based on your project.
-```
-
-## Step 2: Detect Environment
-
-**Operating System:**
-Check the platform and note it for command syntax:
-- Windows → use `del`, `rmdir`, backslashes, `.cmd`/`.ps1` scripts
-- macOS/Linux → use `rm`, `mkdir -p`, forward slashes, `.sh` scripts
-
-Include this in CLAUDE.md so all commands use the correct syntax.
-
-## Step 3: Scan the Project
-
-Look for these indicators to understand the project:
-
-**Package/Config Files:**
-- `package.json` → Node.js, npm scripts, dependencies
-- `requirements.txt` / `pyproject.toml` / `setup.py` → Python
-- `Cargo.toml` → Rust
-- `go.mod` → Go
-- `Gemfile` → Ruby
-- `pom.xml` / `build.gradle` → Java
-- `*.csproj` / `*.sln` → .NET
-- `composer.json` → PHP
-
-**Framework Indicators:**
-- `next.config.*` / `app/` directory → Next.js
-- `vite.config.*` → Vite
-- `angular.json` → Angular
-- `svelte.config.*` → Svelte
-- `remix.config.*` → Remix
-- `nuxt.config.*` → Nuxt
-- `django` in imports → Django
-- `flask` in imports → Flask
-- `fastapi` in imports → FastAPI
-- `express` in dependencies → Express
-- `rails` / `Gemfile` with rails → Rails
-- `laravel` → Laravel
-
-**Testing Frameworks:**
-- `jest.config.*` / `@jest` in deps → Jest
-- `vitest.config.*` → Vitest
-- `pytest.ini` / `conftest.py` → Pytest
-- `*_test.go` files → Go testing
-- `*_spec.rb` files → RSpec
-- `cypress/` or `playwright/` → E2E testing
-
-**Infrastructure:**
-- `Dockerfile` / `docker-compose.*` → Docker
-- `*.tf` files → Terraform
-- `k8s/` or `kubernetes/` → Kubernetes
-- `.github/workflows/` → GitHub Actions
-- `serverless.yml` → Serverless Framework
-
-## Step 4: Populate CLAUDE.md
-
-Focus on what Claude Code actually needs to work effectively. Claude can explore the codebase itself — don't document what it can discover.
-
-**Wrap content in markers** so `/sync-claude-md` knows what's auto-generated:
-
-```markdown
-<!-- AUTO-GENERATED BY /autoconfig — Do not edit. Use .claude/feedback/ for corrections. -->
-
-# Project Name
-...content...
-
-<!-- END AUTO-GENERATED -->
-```
-
-**Always include:**
-- **Project name + one-liner**: What is this thing?
-- **Tech stack**: Runtime, framework, database, key services (so Claude uses correct patterns)
-- **Commands**: How to run, test, build, deploy — Claude needs these to execute tasks
-- **Non-obvious conventions**: Multi-schema databases, monorepo structure, unusual patterns Claude wouldn't infer
-
-**Include if relevant:**
-- **Deployment flow**: If non-standard or involves multiple steps
-- **Key architectural decisions**: Only if Claude would make wrong assumptions without them
-
-**Skip these — Claude can discover them:**
-- Detailed project structure trees (Claude can run `ls` or `tree`)
-- Exhaustive route/endpoint lists (Claude can grep)
-- File-by-file descriptions (Claude can read files)
-- Database model lists (Claude can read schema files)
-
-**Keep it tight.** A 30-line CLAUDE.md that hits the essentials beats a 200-line doc Claude has to parse every session.
-
-**Always end with:**
-```markdown
-## Team Feedback
-See `.claude/feedback/` for corrections and guidance from the team.
-```
-
-This pointer persists across autoconfig runs and directs Claude to team-maintained content.
-
-## Guidelines
-
-- Replace ALL placeholder content with real values from THIS project
-- Delete sections that don't apply — no empty stubs
-- Optimize for Claude's efficiency, not human documentation
-- When uncertain, leave it out — Claude can ask or explore
-
-## Step 5: Update the Guide
-
-After populating CLAUDE.md, update the guide's file preview to show the actual content:
-
-1. Open `.claude/guide/autoconfig.guide.html`
-2. Find the `fileContents` JavaScript object (search for `'claude-md':`)
-3. Replace the `content` value with the actual CLAUDE.md content you just generated
-4. Use template literal syntax and escape any backticks in the content
-
-This ensures double-clicking CLAUDE.md in the guide shows the real generated content.
-
-## After Completion
-
-Once autoconfig is complete, open the interactive guide in the user's browser:
-
-- macOS: `open .claude/guide/autoconfig.guide.html`
-- Linux: `xdg-open .claude/guide/autoconfig.guide.html`
-- Windows: `start .claude/guide/autoconfig.guide.html`
-
-This shows the user what got installed and how to use it.
+<!-- @description The command you just ran. Analyzes your project and populates CLAUDE.md with real context. Re-run anytime your stack changes. -->
+
+# Autoconfig
+
+Analyze this project and configure Claude Code with real context.
+
+## Step 1: Detect Environment
+
+**Operating System:**
+Check the platform and note it for command syntax:
+- Windows → use `del`, `rmdir`, backslashes, `.cmd`/`.ps1` scripts
+- macOS/Linux → use `rm`, `mkdir -p`, forward slashes, `.sh` scripts
+
+Include this in CLAUDE.md so all commands use the correct syntax.
+
+## Step 2: Scan the Project
+
+Look for these indicators to understand the project:
+
+**Package/Config Files:**
+- `package.json` → Node.js, npm scripts, dependencies
+- `requirements.txt` / `pyproject.toml` / `setup.py` → Python
+- `Cargo.toml` → Rust
+- `go.mod` → Go
+- `Gemfile` → Ruby
+- `pom.xml` / `build.gradle` → Java
+- `*.csproj` / `*.sln` → .NET
+- `composer.json` → PHP
+
+**Framework Indicators:**
+- `next.config.*` / `app/` directory → Next.js
+- `vite.config.*` → Vite
+- `angular.json` → Angular
+- `svelte.config.*` → Svelte
+- `remix.config.*` → Remix
+- `nuxt.config.*` → Nuxt
+- `django` in imports → Django
+- `flask` in imports → Flask
+- `fastapi` in imports → FastAPI
+- `express` in dependencies → Express
+- `rails` / `Gemfile` with rails → Rails
+- `laravel` → Laravel
+
+**Testing Frameworks:**
+- `jest.config.*` / `@jest` in deps → Jest
+- `vitest.config.*` → Vitest
+- `pytest.ini` / `conftest.py` → Pytest
+- `*_test.go` files → Go testing
+- `*_spec.rb` files → RSpec
+- `cypress/` or `playwright/` → E2E testing
+
+**Infrastructure:**
+- `Dockerfile` / `docker-compose.*` → Docker
+- `*.tf` files → Terraform
+- `k8s/` or `kubernetes/` → Kubernetes
+- `.github/workflows/` → GitHub Actions
+- `serverless.yml` → Serverless Framework
+
+## Step 3: Populate CLAUDE.md
+
+Focus on what Claude Code actually needs to work effectively. Claude can explore the codebase itself — don't document what it can discover.
+
+**Wrap content in markers** so `/sync-claude-md` knows what's auto-generated:
+
+```markdown
+<!-- AUTO-GENERATED BY /autoconfig — Do not edit. Use .claude/feedback/ for corrections. -->
+
+# Project Name
+...content...
+
+<!-- END AUTO-GENERATED -->
+```
+
+**Always include:**
+- **Project name + one-liner**: What is this thing?
+- **Tech stack**: Runtime, framework, database, key services (so Claude uses correct patterns)
+- **Commands**: How to run, test, build, deploy — Claude needs these to execute tasks
+- **Non-obvious conventions**: Multi-schema databases, monorepo structure, unusual patterns Claude wouldn't infer
+
+**Include if relevant:**
+- **Deployment flow**: If non-standard or involves multiple steps
+- **Key architectural decisions**: Only if Claude would make wrong assumptions without them
+
+**Skip these — Claude can discover them:**
+- Detailed project structure trees (Claude can run `ls` or `tree`)
+- Exhaustive route/endpoint lists (Claude can grep)
+- File-by-file descriptions (Claude can read files)
+- Database model lists (Claude can read schema files)
+
+**Keep it tight.** A 30-line CLAUDE.md that hits the essentials beats a 200-line doc Claude has to parse every session.
+
+**Always end with:**
+```markdown
+## Team Feedback
+See `.claude/feedback/` for corrections and guidance from the team.
+```
+
+This pointer persists across autoconfig runs and directs Claude to team-maintained content.
+
+## Step 4: Create Rules Directory
+
+Create an empty `.claude/rules/` directory. Do not create any subdirectories or rule files.
+
+Rules are path-scoped context files that load automatically when Claude works on matching files. Effective rules require deep understanding of your codebase patterns, team conventions, and quality goals — they should be crafted intentionally, not auto-generated.
+
+## Step 5: Configure Settings
+
+Update `.claude/settings.json` using the official schema.
+
+### Deny Patterns (files Claude shouldn't read/write)
+
+Use `Read()` for blocking reads, `Edit()` for blocking writes:
+
+**Always deny (security):**
+```
+Read(./.env)
+Read(./.env.*)
+Read(./secrets/**)
+Edit(./.env)
+Edit(./.env.*)
+```
+
+**Often deny (generated/vendor):**
+```
+Edit(./node_modules/**)
+Edit(./dist/**)
+Edit(./.git/**)
+```
+
+### Allow Patterns (auto-approve without prompting)
+
+Use `Bash()` patterns with prefix matching:
+
+```
+Bash(npm run test:*)
+Bash(npm run lint:*)
+Bash(npm run build)
+```
+
+### Environment Variables
+
+Set session-level env vars:
+
+```json
+{
+  "env": {
+    "NODE_ENV": "development"
+  }
+}
+```
+
+**Keep it minimal** — only include patterns that actually exist in this project.
+
+## Guidelines
+
+- Replace ALL placeholder content with real values from THIS project
+- Delete sections that don't apply — no empty stubs
+- Optimize for Claude's efficiency, not human documentation
+- When uncertain, leave it out — Claude can ask or explore
+
+## Step 6: Update the Guide
+
+After populating CLAUDE.md, update the guide's file preview to show the actual content:
+
+1. Open `.claude/guide/autoconfig.guide.html`
+2. Find the `fileContents` JavaScript object (search for `'claude-md':`)
+3. Replace the `content` value with the actual CLAUDE.md content you just generated
+4. Use template literal syntax and escape any backticks in the content
+
+This ensures double-clicking CLAUDE.md in the guide shows the real generated content.
+
+## After Completion
+
+Once autoconfig is complete, prompt the user:
+
+**Run `/show-guide` for an interactive walkthrough of your new Claude Code project setup.**