--- name: config-audit:feature-gap description: Context-aware feature recommendations — what could enhance your setup and why argument-hint: "[path]" allowed-tools: Read, Write, Edit, Glob, Grep, Bash, Agent, AskUserQuestion model: opus --- # Config-Audit: Feature Opportunities Context-aware analysis of Claude Code features that could benefit your specific project — with the option to implement selected recommendations on the spot. ## What the user gets - Project context detection (language, size, existing configuration) - Numbered recommendations grouped by impact (high / worth considering / explore) - Each recommendation backed by evidence (Anthropic docs, proven issues) - **Interactive selection: "Which would you like to implement?"** - Direct implementation with backup for selected items ## Implementation ### Step 1: Determine target and greet Parse `$ARGUMENTS` for a path (default: current working directory). Tell the user: ``` ## Feature Opportunities Analyzing which Claude Code features could benefit your workflow... ``` ### Step 2: Create session and run posture Generate session ID (`YYYYMMDD_HHmmss`) if no active session exists. ```bash mkdir -p ~/.claude/config-audit/sessions/{session-id}/findings 2>/dev/null node ${CLAUDE_PLUGIN_ROOT}/scanners/posture.mjs --json --output-file ~/.claude/config-audit/sessions/{session-id}/posture.json 2>/dev/null; echo $? ``` If exit code is non-zero: "Assessment couldn't run. Check that the path exists and contains configuration files." ### Step 3: Read posture data and detect project context Read `~/.claude/config-audit/sessions/{session-id}/posture.json` using the Read tool. Extract GAP findings from `scannerEnvelope.scanners` (find scanner with `scanner === 'GAP'`). Detect project context: ```bash test -f /package.json && echo "has_package_json" || echo "no_package_json" ls /*.py /requirements.txt /pyproject.toml 2>/dev/null | head -3 ``` ### Step 4: Build numbered recommendations Read `${CLAUDE_PLUGIN_ROOT}/knowledge/gap-closure-templates.md` for implementation templates. Group GAP findings into three sections. Number them sequentially across sections: ```markdown ### High Impact These address correctness or safety — consider them seriously. **1.** Add permissions.deny for sensitive paths → Settings enforcement is stronger than CLAUDE.md instructions. → Effort: Low (5 min) **2.** Configure at least one hook for safety automation → Hooks guarantee the action happens. CLAUDE.md instructions are advisory. → Effort: Medium (15 min) ### Worth Considering These improve workflow efficiency for projects like yours. **3.** Split CLAUDE.md into focused modules with @imports → Files over 200 lines degrade Claude's adherence to instructions. → Effort: Low (10 min) **4.** Add path-scoped rules for different file types → Unscoped rules load every session regardless of relevance. → Effort: Low (10 min) ### Explore When Ready Nice-to-have. Skip if your current setup works well. **5.** Custom keybindings (Shift+Enter for newline) → Effort: Low (2 min) **6.** Status line configuration → Effort: Low (2 min) ``` Each recommendation MUST have: - A number - A one-line description - A "Why" with evidence - An effort estimate from the templates ### Step 5: Ask what to implement ``` AskUserQuestion: question: "Which would you like to implement? I'll create a backup first." options: - "All high impact (1-2)" - "Pick specific: e.g. 1,3,5" - "None — just wanted to see the recommendations" ``` If "None": show the full report location and exit. If the user picks numbers: parse the selection and proceed to Step 6. ### Step 6: Implement selected recommendations For each selected recommendation: 1. **Create backup** of any files that will be modified: ```bash node ${CLAUDE_PLUGIN_ROOT}/scanners/fix-cli.mjs --json 2>/dev/null ``` Or create manual backup: ```bash mkdir -p ~/.claude/config-audit/backups/$(date +%Y%m%d_%H%M%S)/files/ 2>/dev/null ``` Copy each file that will be touched. 2. **Apply the template** from gap-closure-templates.md. Use the Write or Edit tool to create or modify the relevant configuration file. 3. **Show progress** as each item is done: ``` Implementing 3 recommendations... ✓ 1. permissions.deny — added to .claude/settings.json ✓ 3. Modular CLAUDE.md — created .claude/rules/testing.md, added @import ✓ 5. Keybindings — created ~/.claude/keybindings.json ``` 4. **Verify** by re-running posture: ```bash node ${CLAUDE_PLUGIN_ROOT}/scanners/posture.mjs --json --output-file /tmp/config-audit-verify-$$.json 2>/dev/null ``` ### Step 7: Show results ```markdown ### Done **{N} recommendations implemented** | Backup created {If health grade changed:} Health: {old_grade} → {new_grade} (+{delta} points) {Show remaining opportunities if any:} {remaining} more opportunities available — run `/config-audit feature-gap` again anytime. **Rollback:** If anything looks wrong, run `/config-audit rollback` to restore. ``` ## Implementation Guidelines When implementing recommendations, be smart about context: - **permissions.deny**: Look at the project for common sensitive paths (`.env`, `secrets/`, `.git/config`, `*.pem`). Don't just copy a template blindly — check what actually exists. - **hooks**: Start with a simple, useful hook. Don't scaffold 5 hooks at once. - **path-scoped rules**: Look at the project's file structure to determine meaningful scopes (e.g., `tests/**/*.ts` vs `src/**/*.ts`). - **CLAUDE.md modularization**: Only suggest splitting if the file is over 100 lines. Read it first to find natural section boundaries. - **MCP setup**: Only relevant if the user actually has external tools to connect. Ask before creating. - **Custom plugin**: Too complex for inline implementation — suggest `/config-audit plan` instead. For items that genuinely need user input (e.g., "which MCP servers do you use?"), ask briefly during implementation rather than skipping them. ## Safety - **Backup mandatory** — always create before modifying - **Show what's changing** — the user sees each change as it happens - **Rollback available** — `/config-audit rollback` at any time - **Non-destructive** — only create new files or add to existing; never delete content