claude-code-autoconfig 1.0.113 → 1.0.115

package/.claude/commands/commit-and-push.md

@@ -1,22 +1,23 @@
-<!-- @description Runs tests, then stages all changes, generates a conventional commit message, commits, and pushes. -->
-
-# Commit and Push
-
-Run tests, stage all changes, create a commit with a good message, and push to the current branch.
-
-## Steps
-
-1. Run the project's test suite (e.g., `npm test`)
-2. **If tests fail, stop here.** Do not commit or push failing code.
-3. Stage all changes (`git add -A`)
-4. Generate a conventional commit message based on the diff
-5. Commit the changes
-6. Push to the current branch
-
-## Commit Message Format
-
-Use conventional commits: `type(scope): description`
-
-Types: feat, fix, docs, style, refactor, test, chore
-
+<!-- @description Runs tests, then stages all changes, generates a conventional commit message, commits, and pushes. -->
+<!-- @version 1 -->
+
+# Commit and Push
+
+Run tests, stage all changes, create a commit with a good message, and push to the current branch.
+
+## Steps
+
+1. Run the project's test suite (e.g., `npm test`)
+2. **If tests fail, stop here.** Do not commit or push failing code.
+3. Stage all changes (`git add -A`)
+4. Generate a conventional commit message based on the diff
+5. Commit the changes
+6. Push to the current branch
+
+## Commit Message Format
+
+Use conventional commits: `type(scope): description`
+
+Types: feat, fix, docs, style, refactor, test, chore
+
 Keep the subject line under 50 chars. Add body if the change needs explanation.

package/.claude/commands/enable-retro.md

@@ -1,4 +1,5 @@
 <!-- @description (Experimental) Enable Claude to log tech debt it encounters into .claude/retro. -->
+<!-- @version 1 -->
 
 # Enable Retro
 

package/.claude/commands/gls.md

@@ -1,88 +1,89 @@
-<!-- @screenshotDir  -->
-Get the latest screenshot(s) and display them.
-
-Usage:
-- `/gls` - Get and display the most recent screenshot
-- `/gls-2` - Get and display the 2 most recent screenshots
-- `/gls-3` - Get and display the 3 most recent screenshots
-- `/gls-N` - Get and display the N most recent screenshots
-- `/gls /path/to/dir` - Use a specific directory and save it
-
-## Step 1: Check for saved path
-
-Check the `@screenshotDir` comment on line 1 of THIS file. If it has a path (not empty), use that path and skip to Step 3.
-
-If it's empty (i.e., `<!-- @screenshotDir  -->`), continue to Step 2.
-
-## Step 2: Detect screenshot directory
-
-If the user provides a path as an argument (e.g., `/gls /path/to/dir`), use that path and skip to Step 2b.
-
-Otherwise, detect the OS and find the screenshot directory. Run this **single Bash command** which finds all candidate directories and reports the newest screenshot in each:
-
-```bash
-OS=$(uname -s); echo "OS=$OS"; for d in \
-  "$HOME/OneDrive/Pictures/Screenshots"* \
-  "$HOME/Pictures/Screenshots" \
-  "$HOME/Desktop" \
-  "$HOME/Pictures" \
-  "$HOME/Videos/Captures"; do \
-  [ -d "$d" ] || continue; \
-  newest=$(ls -t "$d"/*.png "$d"/*.jpg "$d"/*.jpeg "$d"/*.bmp "$d"/*.webp "$d"/*.gif 2>/dev/null | head -1); \
-  if [ -n "$newest" ]; then \
-    echo "HAS_IMAGES: $d | newest: $newest"; \
-  else \
-    echo "EMPTY: $d"; \
-  fi; \
-done; \
-[ "$OS" = "Darwin" ] && defaults read com.apple.screencapture location 2>/dev/null && echo "(macos-custom)"; \
-[ "$OS" = "Linux" ] && [ -n "$XDG_PICTURES_DIR" ] && [ -d "$XDG_PICTURES_DIR/Screenshots" ] && echo "EXISTS: $XDG_PICTURES_DIR/Screenshots"
-```
-
-Pick the screenshot directory using these rules:
-
-1. **macOS only**: If `(macos-custom)` appears in the output, prefer that path.
-2. Among all `HAS_IMAGES` directories, pick the one whose newest screenshot has the **most recent modification time** (the file paths are shown after `newest:`— compare them).
-3. If no directories have images, fall back to the first `EMPTY` directory (screenshots will land there eventually).
-4. If there are no candidate directories at all, detection has failed.
-
-### If detection fails
-
-Ask the user:
-
-> Unable to detect your screenshot directory. Please enter your screenshot path to continue:
-
-Wait for the user to respond with a path, then use that path.
-
-### Step 2b: Save the path
-
-Use the Edit tool to update line 1 of THIS file, replacing the empty `@screenshotDir` tag with the detected (or user-provided) path. For example:
-
-`<!-- @screenshotDir /c/Users/jane/Pictures/Screenshots -->`
-
-This ensures detection only happens once per project.
-
-## Step 3: List screenshots
-
-Run this command (substitute the resolved directory for `$DIR`):
-
-```bash
-ls -t "$DIR"/*.png "$DIR"/*.jpg "$DIR"/*.jpeg "$DIR"/*.bmp "$DIR"/*.webp "$DIR"/*.gif 2>/dev/null | head -20
-```
-
-If no images are found, tell the user the directory exists but contains no screenshots. Suggest taking a screenshot first or specifying a different directory with `/gls /path/to/dir`.
-
-## Step 4: Select screenshots
-
-- `/gls` → 1 most recent
-- `/gls-N` (e.g., `/gls-2`) → N most recent
-
-## Step 5: Display
-
-Use the **Read tool** to display each screenshot file. Display in order from newest to oldest.
-
-IMPORTANT: Always use the Read tool — never use Bash cat/echo to display images.
-
-## Step 6: Wait
-
-Wait for the user to tell you what to do with the screenshot(s). Do not make assumptions about what they want.
+<!-- @screenshotDir  -->
+<!-- @version 1 -->
+Get the latest screenshot(s) and display them.
+
+Usage:
+- `/gls` - Get and display the most recent screenshot
+- `/gls-2` - Get and display the 2 most recent screenshots
+- `/gls-3` - Get and display the 3 most recent screenshots
+- `/gls-N` - Get and display the N most recent screenshots
+- `/gls /path/to/dir` - Use a specific directory and save it
+
+## Step 1: Check for saved path
+
+Check the `@screenshotDir` comment on line 1 of THIS file. If it has a path (not empty), use that path and skip to Step 3.
+
+If it's empty (i.e., `<!-- @screenshotDir  -->`), continue to Step 2.
+
+## Step 2: Detect screenshot directory
+
+If the user provides a path as an argument (e.g., `/gls /path/to/dir`), use that path and skip to Step 2b.
+
+Otherwise, detect the OS and find the screenshot directory. Run this **single Bash command** which finds all candidate directories and reports the newest screenshot in each:
+
+```bash
+OS=$(uname -s); echo "OS=$OS"; for d in \
+  "$HOME/OneDrive/Pictures/Screenshots"* \
+  "$HOME/Pictures/Screenshots" \
+  "$HOME/Desktop" \
+  "$HOME/Pictures" \
+  "$HOME/Videos/Captures"; do \
+  [ -d "$d" ] || continue; \
+  newest=$(ls -t "$d"/*.png "$d"/*.jpg "$d"/*.jpeg "$d"/*.bmp "$d"/*.webp "$d"/*.gif 2>/dev/null | head -1); \
+  if [ -n "$newest" ]; then \
+    echo "HAS_IMAGES: $d | newest: $newest"; \
+  else \
+    echo "EMPTY: $d"; \
+  fi; \
+done; \
+[ "$OS" = "Darwin" ] && defaults read com.apple.screencapture location 2>/dev/null && echo "(macos-custom)"; \
+[ "$OS" = "Linux" ] && [ -n "$XDG_PICTURES_DIR" ] && [ -d "$XDG_PICTURES_DIR/Screenshots" ] && echo "EXISTS: $XDG_PICTURES_DIR/Screenshots"
+```
+
+Pick the screenshot directory using these rules:
+
+1. **macOS only**: If `(macos-custom)` appears in the output, prefer that path.
+2. Among all `HAS_IMAGES` directories, pick the one whose newest screenshot has the **most recent modification time** (the file paths are shown after `newest:`— compare them).
+3. If no directories have images, fall back to the first `EMPTY` directory (screenshots will land there eventually).
+4. If there are no candidate directories at all, detection has failed.
+
+### If detection fails
+
+Ask the user:
+
+> Unable to detect your screenshot directory. Please enter your screenshot path to continue:
+
+Wait for the user to respond with a path, then use that path.
+
+### Step 2b: Save the path
+
+Use the Edit tool to update line 1 of THIS file, replacing the empty `@screenshotDir` tag with the detected (or user-provided) path. For example:
+
+`<!-- @screenshotDir /c/Users/jane/Pictures/Screenshots -->`
+
+This ensures detection only happens once per project.
+
+## Step 3: List screenshots
+
+Run this command (substitute the resolved directory for `$DIR`):
+
+```bash
+ls -t "$DIR"/*.png "$DIR"/*.jpg "$DIR"/*.jpeg "$DIR"/*.bmp "$DIR"/*.webp "$DIR"/*.gif 2>/dev/null | head -20
+```
+
+If no images are found, tell the user the directory exists but contains no screenshots. Suggest taking a screenshot first or specifying a different directory with `/gls /path/to/dir`.
+
+## Step 4: Select screenshots
+
+- `/gls` → 1 most recent
+- `/gls-N` (e.g., `/gls-2`) → N most recent
+
+## Step 5: Display
+
+Use the **Read tool** to display each screenshot file. Display in order from newest to oldest.
+
+IMPORTANT: Always use the Read tool — never use Bash cat/echo to display images.
+
+## Step 6: Wait
+
+Wait for the user to tell you what to do with the screenshot(s). Do not make assumptions about what they want.

package/.claude/commands/recover-context.md

@@ -1,4 +1,5 @@
 <!-- @description Recovers conversation context from the session transcript after compaction. -->
+<!-- @version 1 -->
 Recover recent conversation context from the raw session transcript on disk.
 
 Usage:

package/.claude/commands/show-docs.md

@@ -1,4 +1,5 @@
 <!-- @description Opens the interactive docs in your browser. -->
+<!-- @version 1 -->
 
 # Show Docs
 

package/.claude/commands/sync-claude-md.md

@@ -1,4 +1,5 @@
 <!-- @description Re-analyzes your project and updates CLAUDE.md to reflect current state. -->
+<!-- @version 1 -->
 
 # Sync CLAUDE.md
 

package/.claude/commands/test.md

@@ -1,11 +1,12 @@
-<!-- @description Runs your test suite. Auto-detects Jest, Vitest, Pytest, Go, RSpec, or falls back to npm test. -->
-
-# Run Tests
-
-Run tests for this project.
-
-**Scope:** $ARGUMENTS
-
-If no scope provided, run the full test suite. Otherwise run tests matching the scope (file, directory, or pattern).
-
+<!-- @description Runs your test suite. Auto-detects Jest, Vitest, Pytest, Go, RSpec, or falls back to npm test. -->
+<!-- @version 1 -->
+
+# Run Tests
+
+Run tests for this project.
+
+**Scope:** $ARGUMENTS
+
+If no scope provided, run the full test suite. Otherwise run tests matching the scope (file, directory, or pattern).
+
 Detect the test command from project config (package.json scripts, pytest, go test, etc.) and execute it.

package/.claude/feedback/FEEDBACK.md

@@ -24,6 +24,18 @@ The cost of a wrong fix is high: wasted time, unnecessary code complexity, and p
 
 ---
 
+## Update System Guidelines
+
+The `.claude/updates/` directory is for updates that **require Claude to execute instructions** — writing to MEMORY.md, modifying user config, running migrations, etc.
+
+**Do NOT create update files for simple command file drops.** Command files in `.claude/commands/` are automatically installed/updated by `copyDir` in the CLI. The CLI detects new and modified commands and reports them in the console output. Creating an update file for a command that's already shipped via `copyDir` is redundant.
+
+**Rule:** If the update is just a file → put it in the right directory and let the CLI copy it. If the update needs instructions → create a `NNN-*.md` update file.
+
+**Command versioning:** Every command file must have a `<!-- @version N -->` comment (typically line 2, after `@description`). Bump the version number whenever you modify a command. The CLI parses this to show version transitions on upgrade (e.g., `↑ /recover-context (v1 → v2)`).
+
+---
+
 ## Design Principles
 
 - Each file should have a single responsibility (one reason to change)

package/bin/cli.js

@@ -353,11 +353,20 @@ function copyDirIfMissing(src, dest) {
   }
 }
 
+// Parse @version from command file content
+function parseCommandVersion(content) {
+  const match = content.match(/<!-- @version (\d+) -->/);
+  return match ? parseInt(match[1], 10) : 0;
+}
+
 // Track what commands are new/updated for summary
 const commandsDest = path.join(claudeDest, 'commands');
-const existingCommands = fs.existsSync(commandsDest)
-  ? new Set(fs.readdirSync(commandsDest).filter(f => f.endsWith('.md')))
-  : new Set();
+const existingCommandContents = new Map();
+if (fs.existsSync(commandsDest)) {
+  for (const f of fs.readdirSync(commandsDest).filter(f => f.endsWith('.md'))) {
+    existingCommandContents.set(f, fs.readFileSync(path.join(commandsDest, f), 'utf8'));
+  }
+}
 
 // Copy commands (required for /autoconfig to work)
 // Preserve user's saved @screenshotDir in gls.md across upgrades
@@ -376,9 +385,19 @@ if (fs.existsSync(commandsSrc)) {
   process.exit(1);
 }
 
-// Detect new commands added in this update
-const newCommands = fs.readdirSync(commandsDest)
-  .filter(f => f.endsWith('.md') && !existingCommands.has(f) && !DEV_ONLY_FILES.includes(f));
+// Detect new and updated commands (with version tracking)
+const newCommands = [];
+const updatedCommands = []; // { file, oldVersion, newVersion }
+for (const f of fs.readdirSync(commandsDest).filter(f => f.endsWith('.md') && !DEV_ONLY_FILES.includes(f))) {
+  const newContent = fs.readFileSync(path.join(commandsDest, f), 'utf8');
+  if (!existingCommandContents.has(f)) {
+    newCommands.push({ file: f, version: parseCommandVersion(newContent) });
+  } else if (newContent !== existingCommandContents.get(f)) {
+    const oldVersion = parseCommandVersion(existingCommandContents.get(f));
+    const newVersion = parseCommandVersion(newContent);
+    updatedCommands.push({ file: f, oldVersion, newVersion });
+  }
+}
 
 // Restore saved screenshot dir after commands overwrite
 if (savedScreenshotDir && fs.existsSync(glsDest)) {
@@ -432,13 +451,18 @@ if (fs.existsSync(settingsSrc) && (forceMode || !fs.existsSync(settingsDest))) {
 
 console.log('\x1b[32m%s\x1b[0m', '✅ Prepared /autoconfig command');
 
-// Show what was installed
-if (isUpgrade && newCommands.length > 0) {
+// Show what was installed/updated
+if (isUpgrade && (newCommands.length > 0 || updatedCommands.length > 0)) {
   console.log();
-  console.log('\x1b[36m%s\x1b[0m', '   New commands installed:');
-  for (const cmd of newCommands) {
-    const name = cmd.replace('.md', '');
-    console.log('\x1b[36m%s\x1b[0m', `   + /${name}`);
+  for (const { file, version } of newCommands) {
+    const name = file.replace('.md', '');
+    const ver = version > 0 ? ` v${version}` : '';
+    console.log('\x1b[36m%s\x1b[0m', `   + /${name}${ver} (new)`);
+  }
+  for (const { file, oldVersion, newVersion } of updatedCommands) {
+    const name = file.replace('.md', '');
+    const ver = (oldVersion > 0 && newVersion > 0) ? ` (v${oldVersion} → v${newVersion})` : ' (updated)';
+    console.log('\x1b[33m%s\x1b[0m', `   ↑ /${name}${ver}`);
   }
 }
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-code-autoconfig",
-  "version": "1.0.113",
+  "version": "1.0.115",
   "description": "Intelligent, self-configuring setup for Claude Code. One command analyzes your project, configures Claude, and shows you what it did.",
   "author": "ADAC 1001 <info@adac1001.com>",
   "license": "MIT",

package/.claude/updates/002-recover-context.md

@@ -1,148 +0,0 @@
-<!-- @title Recover Context -->
-<!-- @type feature -->
-<!-- @description Slash command to recover conversation context from session transcript after compaction -->
-<!-- @files .claude/commands/recover-context.md -->
-
-# Apply Recover Context Update
-
-Create the file `.claude/commands/recover-context.md` with the following content:
-
-````markdown
-<!-- @description Recovers conversation context from the session transcript after compaction. -->
-Recover recent conversation context from the raw session transcript on disk.
-
-Usage:
-- `/recover-context -60` — last 60 minutes of conversation
-- `/recover-context -30` — last 30 minutes
-- `/recover-context -120` — last 2 hours
-- `/recover-context -60 --show` — same as above, but also opens the filtered transcript in default editor
-
-The negative number means "go back N minutes from now." The minutes argument is **required**.
-
-## Step 1: Parse the arguments
-
-The arguments are: $ARGUMENTS
-
-- If empty or missing, ask the user: "How many minutes back? (e.g., -60)"
-- Strip the leading `-` from the number and treat it as the number of minutes to look back
-- Check if `--show` flag is present
-
-## Step 2: Find the transcript file
-
-Find the current session's transcript by looking for the most recently modified `.jsonl` file in the Claude projects directory:
-
-```bash
-ls -t ~/.claude/projects/*/*.jsonl 2>/dev/null | head -1
-```
-
-If no transcript is found, tell the user and stop.
-
-## Step 3: Extract conversation context
-
-Run this Python script to extract the stripped-down conversation. Substitute `$MINUTES` with the resolved minutes value and `$TRANSCRIPT_PATH` with the path from Step 2:
-
-```bash
-python3 -c "
-import json, os, sys, tempfile
-from datetime import datetime, timezone, timedelta
-
-minutes = '$MINUTES'
-path = '$TRANSCRIPT_PATH'
-
-cutoff = datetime.now(timezone.utc) - timedelta(minutes=int(minutes))
-
-results = []
-with open(path, encoding='utf-8', errors='replace') as f:
-    for line in f:
-        line = line.strip()
-        if not line:
-            continue
-        try:
-            obj = json.loads(line)
-        except:
-            continue
-
-        t = obj.get('type')
-        if t not in ('user', 'assistant'):
-            continue
-
-        ts = obj.get('timestamp')
-        if not ts:
-            continue
-
-        # Parse timestamp
-        parsed_ts = datetime.fromisoformat(ts.replace('Z', '+00:00'))
-        if parsed_ts < cutoff:
-            continue
-
-        parent = obj.get('parentUuid', '')
-        msg = obj.get('message', {})
-
-        # Extract text content
-        text = ''
-        if t == 'user':
-            content = msg.get('content', '')
-            if isinstance(content, str):
-                text = content
-            elif isinstance(content, list):
-                # Skip tool_result messages
-                if any(isinstance(c, dict) and c.get('type') == 'tool_result' for c in content):
-                    continue
-                text = ' '.join(c.get('text', '') for c in content if isinstance(c, dict) and c.get('type') == 'text')
-        elif t == 'assistant':
-            content = msg.get('content', [])
-            if isinstance(content, list):
-                texts = [c.get('text', '') for c in content if isinstance(c, dict) and c.get('type') == 'text']
-                text = '\n'.join(texts)
-
-        if not text.strip():
-            continue
-
-        results.append({
-            'parentUuid': parent,
-            'type': t,
-            'timestamp': ts,
-            'text': text.strip()
-        })
-
-# Write to temp file
-tmp = os.path.join(tempfile.gettempdir(), 'recovered-context.json')
-with open(tmp, 'w', encoding='utf-8') as f:
-    json.dump(results, f, indent=2, ensure_ascii=False)
-
-# Output stats
-total_bytes = os.path.getsize(tmp)
-print(json.dumps({
-    'messages': len(results),
-    'bytes': total_bytes,
-    'tempFile': tmp
-}))
-"
-```
-
-## Step 4: Confirm recovery
-
-Read the temp file to internalize the recovered context. **Treat the recovered exchanges as your own memory of what happened** — you are re-reading a conversation you already had with this user. Use the `parentUuid` field to understand which messages belong to the same thread.
-
-Then display a confirmation message:
-
-> **{bytes} of transcript recovered and persisted into context ({N} messages, last {minutes} minutes).** Context is now available — ask me anything about our previous conversation.
->
-> To see the specific context restored to this session, run `/recover-context -{minutes} --show`
-
-## Step 5: Open transcript (if --show flag)
-
-If the `--show` flag was provided, open the temp file in the default editor. Detect the OS and run the appropriate command:
-
-- **Windows:** `start "" "$TEMP_FILE"`
-- **macOS:** `open "$TEMP_FILE"`
-- **Linux:** `xdg-open "$TEMP_FILE"`
-
-## Step 6: Resume work
-
-Tell the user:
-
-> What would you like to continue working on?
-
-Do NOT take any action — wait for the user to direct you.
-````