feat: add /changelog, /dep-check, commit-size-guard + cleanup

.ai-workspace/scripts/align-workspace.py

@@ -272,6 +272,10 @@ def render_agents_md_content(config: AIWorkspaceConfig, base_dir: Path) -> str:
 
 def render_agents_md(config: AIWorkspaceConfig, base_dir: Path) -> None:
     """Render and write AGENTS.md."""
+    template_path = base_dir / ".ai-workspace/templates/AGENTS.md.j2"
+    if not template_path.exists():
+        print("Skipped AGENTS.md (no template found)")
+        return
     rendered = render_agents_md_content(config, base_dir)
     agents_md_path = base_dir / "AGENTS.md"
     agents_md_path.write_text(rendered, encoding="utf-8")
@@ -280,6 +284,10 @@ def render_agents_md(config: AIWorkspaceConfig, base_dir: Path) -> None:
 
 def check_agents_md(config: AIWorkspaceConfig, base_dir: Path) -> list[str]:
     """Check if AGENTS.md is up to date. Returns list of issues."""
+    template_path = base_dir / ".ai-workspace/templates/AGENTS.md.j2"
+    if not template_path.exists():
+        return []
+
     rendered = render_agents_md_content(config, base_dir)
     agents_md_path = base_dir / "AGENTS.md"
 

.ai-workspace/scripts/commit-size-guard.sh

@@ -0,0 +1,31 @@
+#!/usr/bin/env bash
+# PreToolUse hook: warn when a git commit has a large staged diff.
+# Advisory only — always exits 0.
+
+THRESHOLD=500
+
+CMD=$(echo "$CLAUDE_TOOL_INPUT" | grep -oP '"command"\s*:\s*"\K[^"]+' 2>/dev/null)
+[ -z "$CMD" ] && exit 0
+
+# Only care about git commit commands
+echo "$CMD" | grep -qiE "git commit" || exit 0
+
+# Skip amend commits (reworking existing commits, not adding new bulk)
+echo "$CMD" | grep -qiE "\-\-amend" && exit 0
+
+# Count staged diff lines (additions + deletions)
+STAT=$(git diff --cached --stat 2>/dev/null | tail -1)
+[ -z "$STAT" ] && exit 0
+
+INSERTIONS=$(echo "$STAT" | grep -oP '\d+(?= insertion)' || echo 0)
+DELETIONS=$(echo "$STAT" | grep -oP '\d+(?= deletion)' || echo 0)
+TOTAL=$((${INSERTIONS:-0} + ${DELETIONS:-0}))
+
+if [ "$TOTAL" -gt "$THRESHOLD" ]; then
+  echo "Large commit: $TOTAL changed lines (threshold: $THRESHOLD)."
+  echo "Consider splitting into smaller, focused commits:"
+  echo "  - Use 'git add -p' to stage related changes separately"
+  echo "  - Group by logical unit: one commit per feature, fix, or refactor"
+fi
+
+exit 0

.claude/commands/changelog.md

@@ -0,0 +1 @@
+../../commands/changelog/command.md

.claude/commands/dep-check.md

@@ -0,0 +1 @@
+../../commands/dep-check/command.md

.claude/commands/update-docs.md

@@ -0,0 +1 @@
+../../commands/update-docs/command.md

.claude/settings.json

@@ -25,6 +25,17 @@
         ],
         "matcher": "Bash"
       },
+      {
+        "hooks": [
+          {
+            "command": "bash \"$CLAUDE_PROJECT_DIR/.ai-workspace/scripts/commit-size-guard.sh\"",
+            "statusMessage": "Checking commit size...",
+            "timeout": 5,
+            "type": "command"
+          }
+        ],
+        "matcher": "Bash"
+      },
       {
         "hooks": [
           {

.gitignore

@@ -118,6 +118,17 @@ evaluation-results/
 # Paper / blog drafts (local only, not published via repo)
 paper/
 
+# Local project directories (user-specific, not part of the workspace)
+UnifAI/
+ai-initiatives-observer/
+skills/redhat-writing/
+
+# Archived workspace components
+archive/
+
+# Loose PDF / image artifacts
+*.pdf
+
 # Temporary files and directories used by AI agents.
 # Ignore all content in .tmp/, but keep the directory itself.
 .tmp/*

GUIDE.md

@@ -8,8 +8,8 @@ Everything this workspace gives you — skills, commands, hooks, and how they wo
 
 1. **Clone the workspace**, install dependencies, and run setup:
    ```bash
-   git clone https://github.com/redhat-community-ai-tools/claude-code-setup-evaluator.git
-   cd claude-code-setup-evaluator
+   git clone https://github.com/redhat-community-ai-tools/claude-code-basecamp.git
+   cd claude-code-basecamp
    uv sync
    uv run .ai-workspace/scripts/setup.py
    ```
@@ -94,6 +94,8 @@ Type the command name in the chat to run it.
 | `/ai-engineer-review` | Architecture check | Brutally honest architecture and code review |
 | `/architecture-docs` | Documentation | Generates architecture docs with diagrams (`--quick` for just a Mermaid diagram) |
 | `/focus` | Switch repos mid-session | Re-presents the repo menu, replaces current focus |
+| `/changelog` | Before a release | Generates a changelog grouped by intent from git history |
+| `/dep-check` | Periodic audit | Checks for unused deps, outdated versions, vulnerabilities, license issues |
 | `/toolkit` | First time / discovery | Shows everything available and recommends what to use |
 
 ---
@@ -106,6 +108,7 @@ Hooks fire on specific events — you don't trigger them manually.
 |------|-------|-------------|
 | Session start | When Claude starts | Reports git status of all repos in `repositories/` |
 | Secret scan | Before `git commit` or `git push` | Blocks if API keys detected in tracked files (GitHub, AWS, Anthropic, Atlassian, HuggingFace patterns) |
+| Commit size guard | Before `git commit` | Warns if staged diff exceeds 500 lines and suggests splitting |
 | Skill suggestion | When you edit files | Reminds Claude which skills are relevant to the files you're working on |
 
 The secret scan hook catches these patterns:

README.md

@@ -1,4 +1,4 @@
-# Claude Code Setup Evaluator
+# Claude Code Basecamp
 
 A workspace for Claude Code users who work across multiple repositories. Clone your repos, get shared skills and commands out of the box, add your own.
 
@@ -7,7 +7,7 @@ A workspace for Claude Code users who work across multiple repositories. Clone y
 This is a **meta-workspace**. You clone your project repositories into the `repositories/` folder and run Claude Code from the workspace root. Claude automatically gets access to all skills and commands. Your repos stay independent — they push to their own remotes, the workspace never touches them.
 
 ```
-claude-code-setup-evaluator/
+claude-code-basecamp/
   repositories/           # Clone your repos here (gitignored — yours, not shared)
     my-api/
     frontend/
@@ -20,8 +20,8 @@ claude-code-setup-evaluator/
 ## Quick Start
 
 ```bash
-git clone https://github.com/redhat-community-ai-tools/claude-code-setup-evaluator.git
-cd claude-code-setup-evaluator
+git clone https://github.com/redhat-community-ai-tools/claude-code-basecamp.git
+cd claude-code-basecamp
 uv sync
 uv run .ai-workspace/scripts/setup.py
 
@@ -68,6 +68,8 @@ Skills are knowledge that Claude carries in the background. You don't trigger th
 | `/env-check` | Something broke | Validate environment setup |
 | `/recap` | End of session | Summarize for standup |
 | `/focus` | Switch repos | Pick repos from a list |
+| `/changelog` | Before a release | Generate changelog grouped by intent |
+| `/dep-check` | Periodic audit | Check unused deps, outdated versions, vulnerabilities |
 | `/toolkit` | Discovery | See everything available |
 
 ### Hooks (automatic safety nets)
@@ -76,6 +78,7 @@ Skills are knowledge that Claude carries in the background. You don't trigger th
 |------|-------------|
 | Session start | Reports git status of all your repos |
 | Secret scan | Blocks `git commit`/`push` if API keys detected in tracked files |
+| Commit size guard | Warns if staged diff exceeds 500 lines, suggests splitting |
 | Skill suggestion | Reminds Claude which skills are relevant to files you're editing |
 
 ## Adding Your Own Skills and Commands