# Config-Audit Plugin for Claude Code

> Know if your configuration is correct. Find what could improve it. Fix it automatically.

*Built for my own Claude Code workflow and shared openly for anyone who finds it useful. This is a solo project — bug reports and feature requests are welcome, but pull requests are not accepted.*

*AI-generated: all code produced by Claude Code through dialog-driven development. [Full disclosure →](../../README.md#ai-generated-code-disclosure)*

![Version](https://img.shields.io/badge/version-4.0.0-blue)
![Platform](https://img.shields.io/badge/platform-Claude_Code_Plugin-purple)
![Scanners](https://img.shields.io/badge/scanners-9-cyan)
![Commands](https://img.shields.io/badge/commands-17-green)
![Agents](https://img.shields.io/badge/agents-6-orange)
![Hooks](https://img.shields.io/badge/hooks-4-red)
![Tests](https://img.shields.io/badge/tests-543+-brightgreen)
![License](https://img.shields.io/badge/license-MIT-lightgrey)

A Claude Code plugin that checks configuration health, suggests context-aware improvements, and auto-fixes issues — `CLAUDE.md`, `settings.json`, hooks, rules, MCP servers, `@imports`, and plugins. 8 quality scanners for correctness, context-aware feature recommendations, auto-fix with backup/rollback, plus an Opus-4.7-aware Token Hotspots scanner. Zero external dependencies.

---

## Table of Contents

- [What Is This?](#what-is-this)
- [The Configuration Problem](#the-configuration-problem)
- [Quick Start](#quick-start)
- [Feature Opportunities](#feature-opportunities--context-aware-recommendations)
- [Workflow Examples](#workflow-examples)
- [Commands](#commands)
- [Deterministic Scanners](#deterministic-scanners)
- [Agent Architecture](#agent-architecture)
- [Hooks & Safety](#hooks--safety)
- [Skills](#skills)
- [Suppressions](#suppressions)
- [Examples & Self-Audit](#examples--self-audit)
- [Scanner Library](#scanner-library-scannerslib)
- [Knowledge Base](#knowledge-base-knowledge)
- [Testing](#testing)
- [Gotchas](#gotchas)
- [Data Storage & Safety Guarantees](#data-storage--safety-guarantees)
- [What This Plugin Does Not Cover](#what-this-plugin-does-not-cover)
- [Version History](#version-history)
- [License](#license)

---

## What Is This?

Claude Code reads instructions from at least 7 different file types across multiple scopes: `CLAUDE.md`, `settings.json`, `.claude/rules/`, `hooks.json`, `.mcp.json`, `.claudeignore`, and `settings.local.json`. Each can exist at project level, user level, or both. Plugins add more. The system is powerful — but nobody tells you what you're using wrong, what you're missing, or what's silently conflicting.

This plugin provides three layers of configuration intelligence:

- **Health** — 8 deterministic scanners verify correctness across every configuration file, catching broken imports, deprecated settings, conflicting rules, format errors, permission contradictions, and Opus-4.7-era token waste
- **Opportunities** — context-aware recommendations for Claude Code features that could benefit your specific project, backed by Anthropic's official guidance
- **Action** — auto-fix with mandatory backups, syntax validation, rollback support, and a human-in-the-loop workflow for anything non-trivial

> [!TIP]
> Start with `/config-audit posture` for a 30-second scorecard, then `/config-audit` for the full picture.

---

## The Configuration Problem

You've been using Claude Code for weeks — maybe months. It works fine. But there's a gap between "works fine" and "configured well," and it's invisible until someone shows you.

**These are not hypotheticals.** They come from running the posture scanner on real setups:

- Your global `CLAUDE.md` says "never use mocks" but a project rule says "prefer mocks" — Claude gets confused and you don't know why
- You've written dozens of projects but have never set up hooks, rules, or keybindings because you didn't know they existed
- Three plugins define hooks for the same event with conflicting behavior
- Your `settings.json` has a deprecated key that silently does nothing
- An `@import` in your CLAUDE.md points to a file you deleted last week
- You're using maybe 30% of what Claude Code can do — and you don't know what the other 70% is

The plugin ships with two example projects. Run them yourself:

### `examples/minimal-setup/` — just a CLAUDE.md, nothing else

```
> node scanners/posture.mjs examples/minimal-setup/

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 Config-Audit Health Score
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

 Health: A (99/100)    7 areas scanned

 Area Scores
 ───────────
 CLAUDE.md ............ A (90)
 Settings ............. A (100)   Hooks ............... A (100)
 Rules ................ A (100)   MCP ................. A (100)
 Imports .............. A (100)   Conflicts ........... A (100)

 22 opportunities available — run /config-audit feature-gap for recommendations

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
```

**Grade A** — nothing is broken. The health grade only reflects real issues, and this setup has none. The 22 opportunities are not failures — they're features you *could* use. Run `/config-audit feature-gap` to see which ones are relevant to your project.

### `examples/optimal-setup/` — full configuration across all 4 tiers

```
> node scanners/posture.mjs examples/optimal-setup/

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 Config-Audit Health Score
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

 Health: A (93/100)    7 areas scanned

 Area Scores
 ───────────
 CLAUDE.md ............ A (100)   Settings ............ A (90)
 Hooks ................ A (100)   Rules ............... B (80)
 MCP .................. A (90)    Imports ............. A (100)
 Conflicts ............ A (90)

 3 opportunities available — run /config-audit feature-gap for recommendations

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
```

Also **Grade A** — with only 3 opportunities remaining. This project has CLAUDE.md split via `@imports`, permissions scoped to specific tools, path-scoped rules (different rules for `src/` vs. `tests/`), hooks covering multiple events, and MCP servers. Both setups are healthy — the difference is how much of Claude Code's surface area you're choosing to use.

---

## Quick Start

### Prerequisites

- [Claude Code](https://docs.anthropic.com/en/docs/claude-code) installed
- Node.js 18+ (for standalone CLI tools)

### Installation

Add the marketplace and browse plugins with `/plugin`:

```bash
claude plugin marketplace add https://git.fromaitochitta.com/open/ktg-plugin-marketplace.git
```

Or enable directly in `~/.claude/settings.json`:

```json
{
  "enabledPlugins": {
    "config-audit@ktg-plugin-marketplace": true
  }
}
```

### First Scan

```bash
# Full audit with auto-scope detection (inside Claude Code)
/config-audit

# 30-second posture check (standalone, no LLM needed)
node scanners/posture.mjs /path/to/project

# Auto-fix issues with backup
node scanners/fix-cli.mjs /path/to/project --apply
```

The CLI tools work standalone — no Claude Code session needed, just Node.js 18+.

---

## Feature Opportunities — Context-Aware Recommendations

Most configuration tools stop at "is it valid?" Config-audit goes further: **what could improve your setup, and is it relevant to your project?**

The feature opportunity scanner checks 25 dimensions and groups recommendations by impact:

| Impact Level | Focus | Examples |
|--------------|-------|---------|
| **High** | Correctness & security | `permissions.deny` for sensitive files, basic hooks for safety automation |
| **Worth Considering** | Workflow efficiency | Path-scoped rules, modular `@imports`, custom agents |
| **Explore** | Nice-to-have | Keybindings, status line, output styles, agent teams |

Each recommendation is **context-aware** — it considers what your project actually contains. A solo TypeScript project gets different suggestions than a team Python monorepo. Recommendations include *why* (backed by Anthropic's official guidance) and *how* (concrete steps).

Run `/config-audit feature-gap` to see what's relevant to your project.

---

## Workflow Examples

### 1. First Time — Just Curious

You heard about this plugin and want to know where you stand:

```
/config-audit                          # Auto-detects scope, runs full audit
                                       # → See your grade, top issues, and gaps
/config-audit posture                  # Even faster: 30-second scorecard only
```

### 2. Monthly Configuration Checkup

A quick health check — are things still clean?

```
/config-audit posture                  # Quick health check (A-F grade, 7 areas)
/config-audit                          # Full audit if grade dropped
/config-audit fix                      # Auto-fix deterministic issues
/config-audit posture                  # Verify improvement
```

### 3. Deep Optimization

You want to go from C to A. The full pipeline:

```
/config-audit                          # Audit — understand what you have
/config-audit feature-gap              # Opportunities — context-aware recommendations
/config-audit plan                     # Plan — prioritized actions with risk assessment
/config-audit implement                # Execute — changes with backup + verification
```

### 4. Plugin Author

You maintain Claude Code plugins and want to ensure quality:

```
/config-audit plugin-health            # Audit plugin structure, frontmatter, cross-plugin conflicts
                                       # → Checks naming, frontmatter completeness, tool grants, duplicates
```

### 5. Track Configuration Drift

Your team configuration changes over time. Track it:

```
/config-audit drift                    # First run creates baseline, subsequent runs show delta
                                       # → New findings, resolved findings, unchanged, moved
/config-audit drift --save my-baseline # Save a named baseline for comparison
```

---

## Commands

### Core (just run `/config-audit` to get started)

| Command | Description |
|---------|-------------|
| `/config-audit` | Full audit with auto-scope detection (no setup needed) |
| `/config-audit posture` | Quick health scorecard: A-F grades across 8 quality areas (incl. Token Efficiency) |
| `/config-audit tokens` | Opus-4.7-aware token hotspots — ranked by estimated waste, with 4-pattern findings |
| `/config-audit feature-gap` | Context-aware feature recommendations grouped by impact |
| `/config-audit fix` | Auto-fix deterministic issues with backup + verification |
| `/config-audit rollback` | Restore configuration from a previous backup |
| `/config-audit plan` | Generate prioritized action plan from audit findings |
| `/config-audit implement` | Execute plan with automatic backup + verification |
| `/config-audit help` | Show all commands with usage examples |

### Additional

| Command | Description |
|---------|-------------|
| `/config-audit drift` | Compare current config against a saved baseline |
| `/config-audit plugin-health` | Audit plugin structure, frontmatter, cross-plugin coherence |
| `/config-audit discover` | Run discovery phase only |
| `/config-audit analyze` | Run analysis phase only |
| `/config-audit interview` | Set preferences for action plan _(optional)_ |
| `/config-audit status` | Show current session state and available actions |
| `/config-audit cleanup` | Remove old session directories |

### Scope

By default, `/config-audit` auto-detects scope from your git context. Override with: `/config-audit current`, `/config-audit repo`, `/config-audit home`, `/config-audit full`. Use `--delta` for incremental scanning (only new/changed findings).

---

## Deterministic Scanners

9 Node.js scanners that perform structural analysis an LLM cannot reliably do: schema validation, circular reference detection, import resolution, conflict detection across scopes, and Opus-4.7-aware token-cost analysis. Zero external dependencies.

**Why deterministic?** LLMs are powerful at understanding intent and context. But they cannot reliably validate JSON schemas, detect circular `@import` chains, or catch that your global `settings.json` contradicts your project-level one. These scanners fill that gap — fast, repeatable, and zero false positives on structural issues.

| Scanner | Prefix | What It Catches |
|---------|--------|-----------------|
| `claude-md-linter.mjs` | CML | Oversized files, missing sections, broken @imports, duplicates, stale TODOs |
| `settings-validator.mjs` | SET | Schema violations, unknown/deprecated keys, type mismatches, permission issues |
| `hook-validator.mjs` | HKV | Invalid format, missing scripts, wrong event names, timeout risks |
| `rules-validator.mjs` | RUL | Bad glob patterns, orphaned rules, deprecated fields, unscoped rules |
| `mcp-config-validator.mjs` | MCP | Invalid server types, missing trust levels, exposed env vars |
| `import-resolver.mjs` | IMP | Broken @imports, circular references, deep chains, tilde path issues |
| `conflict-detector.mjs` | CNF | Settings contradictions across scopes, permission conflicts, hook duplicates |
| `feature-gap-scanner.mjs` | GAP | 25 feature checks — shown as opportunities, not grades |
| `token-hotspots.mjs` | TOK | Cache-breaking volatile content, redundant tool permissions, deep import chains, sonnet-era setups |

### CLI Tools

All tools work standalone — no Claude Code session needed:

| Tool | Usage |
|------|-------|
| **Posture** | `node scanners/posture.mjs <path> [--json] [--global] [--full-machine] [--output-file path]` |
| **Fix** | `node scanners/fix-cli.mjs <path> [--apply] [--json] [--global]` |
| **Drift** | `node scanners/drift-cli.mjs <path> [--save] [--baseline name] [--json]` |
| **Tokens** | `node scanners/token-hotspots-cli.mjs <path> [--json] [--global] [--output-file path]` |
| **Self-audit** | `node scanners/self-audit.mjs [--json] [--fix]` |
| **Full scan** | `node scanners/scan-orchestrator.mjs <path> [--global] [--full-machine] [--no-suppress]` |

---

## Agent Architecture

Six specialized agents collaborate through the audit workflow, each matched to an appropriate model for cost and quality:

| Agent | Model | Role | Tools |
|-------|-------|------|-------|
| **scanner-agent** | Sonnet | Fast filesystem scanning, file discovery | Read, Glob, Grep, Write |
| **analyzer-agent** | Sonnet | Deep analysis, hierarchy mapping, conflict detection | Read, Glob, Grep, Write |
| **planner-agent** | Opus | Action plan generation with risk assessment | Read, Glob, Write |
| **implementer-agent** | Sonnet | Change execution with mandatory backups | Read, Write, Edit, Bash, Glob |
| **verifier-agent** | Sonnet | Post-implementation verification | Read, Glob, Grep |
| **feature-gap-agent** | Opus | Context-aware feature recommendations | Read, Glob, Grep, Write |

### Orchestration Flow

```
                                    +-----------+
                                    | Interview |  (optional)
                                    +-----+-----+
                                          |
+-----------+     +---------+     +-------v---+     +-----------+
| Discover  | --> | Analyze | --> |   Plan    | --> | Implement |
| (sonnet)  |     | (sonnet)|     | (opus)    |     | (sonnet)  |
+-----------+     +---------+     +-----------+     +-----+-----+
                                                          |
                                                    +-----v-----+
                                                    |  Verify   |
                                                    |  (sonnet) |
                                                    +-----------+
```

---

## Hooks & Safety

Four hooks provide automatic safety and session continuity — they activate the moment the plugin is installed:

| Event | Script | What It Does |
|-------|--------|--------------|
| **PreToolUse** | `auto-backup-config.mjs` | Backs up any config file before Edit/Write touches it |
| **PostToolUse** | `post-edit-verify.mjs` | Re-scans after edits — blocks if new critical/high findings introduced |
| **SessionStart** | `session-start.mjs` | Checks for incomplete audit sessions so you can resume |
| **Stop** | `stop-session-reminder.mjs` | Shows current phase so your next session picks up where you left off |

All hooks are Node.js (`.mjs`) for cross-platform compatibility (macOS, Linux, Windows).

> [!IMPORTANT]
> The PreToolUse and PostToolUse hooks only activate when config-audit is modifying configuration files. They don't interfere with your normal development workflow.

---

## Skills

| Skill | Trigger | Description |
|-------|---------|-------------|
| `config-hierarchy` | "CLAUDE.md hierarchy", "config file locations", "settings.json structure" | Comprehensive reference for Claude Code's configuration hierarchy — CLAUDE.md, settings.json, managed config, @imports, path-scoped rules |

Skills activate automatically when your question matches their trigger patterns.

---

## Suppressions

### Finding ID Format

Every finding has a unique ID: `CA-{SCANNER}-{NNN}` — where `{SCANNER}` is the scanner prefix (see table above) and `{NNN}` is a sequential number. Examples: `CA-CML-001`, `CA-SET-003`, `CA-HKV-002`, `CA-RUL-005`.

### Suppression

Some findings are expected — maybe you intentionally have a large CLAUDE.md, or a feature gap doesn't apply to your workflow. Create a `.config-audit-ignore` file to suppress them:

```
# Suppress by exact finding ID
CA-SET-003

# Suppress by scanner prefix (glob pattern)
CA-GAP-*

# Suppress all plugin health findings
CA-PLH-*
```

Suppressed findings are tracked in the scan envelope's `suppressed_findings` array for audit trail — nothing is silently hidden. Use `--no-suppress` to see everything.

---

## Examples & Self-Audit

### Example Projects

The `examples/` directory contains two projects shown in the [before/after demo](#the-configuration-problem) above:

| Example | Description | Grade | Opportunities |
|---------|-------------|-------|---------------|
| `minimal-setup/` | Single CLAUDE.md, nothing else | A | 22 |
| `optimal-setup/` | Full configuration across all 4 tiers | A | 3 |

```bash
# Run them yourself
node scanners/posture.mjs examples/minimal-setup/
node scanners/posture.mjs examples/optimal-setup/
```

### Self-Audit: Scanning the Scanner

The plugin runs all 9 scanners on itself via `self-audit.mjs`. Current result: **Grade A, score 98, 0 real findings.** Test fixtures and example files are automatically excluded from scoring — a security plugin that ships deliberately broken examples shouldn't fail its own audit.

```bash
node scanners/self-audit.mjs
```

---

## Scanner Library (`scanners/lib/`)

Shared modules used by all scanners — useful if you're reading the source or extending the plugin:

| Module | Purpose |
|--------|---------|
| `severity.mjs` | Severity constants, risk scoring, verdict logic |
| `output.mjs` | Finding objects (`CA-XXX-NNN` format), scanner results, envelope |
| `file-discovery.mjs` | Config file discovery: single-path, multi-path, full-machine |
| `yaml-parser.mjs` | Frontmatter parsing, JSON parsing, @import/section extraction |
| `string-utils.mjs` | Line counting, truncation, similarity, key extraction |
| `scoring.mjs` | Area scoring, health scorecard |
| `backup.mjs` | Backup creation, manifest parsing, checksum verification |
| `diff-engine.mjs` | Drift diffing: `diffEnvelopes()`, `formatDiffReport()` |
| `baseline.mjs` | Baseline save/load/list/delete for drift detection |
| `report-generator.mjs` | Unified markdown reports: posture, drift, plugin health |
| `suppression.mjs` | `.config-audit-ignore` parsing, finding suppression, audit trail |

### Action Engines

| Module | Purpose |
|--------|---------|
| `fix-engine.mjs` | `planFixes()`, `applyFixes()`, `verifyFixes()` — 9 fix types |
| `rollback-engine.mjs` | `listBackups()`, `restoreBackup()`, `deleteBackup()` |
| `fix-cli.mjs` | CLI entry point for auto-fix |
| `drift-cli.mjs` | CLI entry point for drift detection |

---

## Knowledge Base (`knowledge/`)

Reference documents that inform the feature-gap agent and context-aware recommendations:

| File | Content |
|------|---------|
| `claude-code-capabilities.md` | Feature register: 18 config surfaces, Anthropic guidance, relevance table |
| `configuration-best-practices.md` | Per-layer best practices |
| `anti-patterns.md` | Common mistakes mapped to scanner IDs |
| `hook-events-reference.md` | All 26 hook events with details |
| `feature-evolution.md` | Feature timeline for staleness detection |
| `gap-closure-templates.md` | Config-specific templates for closing gaps |

---

## Testing

```bash
node --test 'tests/**/*.test.mjs'
```

486 tests across 27 test files (10 lib + 16 scanner + 1 hook). Test fixtures in `tests/fixtures/`. Requires Node.js 18+ (`node:test`).

---

## Gotchas

- **Session accumulation** — session directories at `~/.claude/config-audit/sessions/` grow over time. Use `/config-audit cleanup` to manage
- **Node.js version** — scanners require Node.js 18+ (uses `node:test`, `node:fs/promises`)
- **Plugin CLAUDE.md in node_modules** — these should be excluded via scope to avoid false positives

---

## Data Storage & Safety Guarantees

### Where Data Lives

All data stays local at `~/.claude/config-audit/sessions/`:

```
~/.claude/config-audit/sessions/{session-id}/
  scope.yaml              # Scan boundaries
  discovery.json          # File manifest
  findings/               # Individual issues (YAML)
  analysis-report.md      # Full report
  action-plan.md          # Prioritized actions
  backups/                # Pre-modification copies
  implementation-log.md   # Change log
  state.yaml              # Phase tracking
```

### Safety Guarantees

This plugin is cautious by design — configuration files are important, and a bad edit can break your entire Claude Code setup:

| Guarantee | How |
|-----------|-----|
| **Backups mandatory** | Every file is copied before modification — no exceptions |
| **Read-only audit** | `/config-audit` and `/config-audit posture` analyze without changing anything |
| **Rollback support** | `/config-audit rollback` restores from any backup |
| **Syntax validation** | Every change is validated before finalization |
| **Verification pass** | A separate agent confirms changes actually work |
| **Human-in-the-loop** | You approve the plan before anything is implemented |
| **Post-edit guard** | Hook blocks the session if a new critical/high finding is introduced |

---

## What This Plugin Does Not Cover

- **Runtime behavior** — this plugin audits configuration files, not what Claude actually does at runtime. For runtime defense, see [claude-code-llm-security](https://git.fromaitochitta.com/open/claude-code-llm-security)
- **Secret scanning** — config-audit checks for structural issues, not leaked credentials. Use llm-security for secret detection
- **Custom scanner rules** — scanners check against known Claude Code configuration schemas. Custom rule definitions are not supported
- **Remote/team configuration** — managed settings, SSO-provisioned config, and organization-level policies are detected as gaps but not managed

---

## Version History

| Version | Date | Highlights |
|---------|------|-----------|
| **4.0.0** | 2026-04-19 | Opus 4.7 era: new TOK scanner (cache-breaking volatile content, redundant tool permissions, deep import chains, sonnet-era setups), `/config-audit tokens` command, Token Efficiency 8th quality area, scanner-agent + verifier-agent migrated haiku → sonnet. 543 tests |
| **3.1.0** | 2026-04-14 | New `/config-audit whats-active` — read-only inventory of active plugins, skills, MCP, hooks, CLAUDE.md for a repo, with token estimates. 522 tests |
| **3.0.1** | 2026-04-04 | Cross-platform fix: Windows path separators. 486 tests |
| **3.0.0** | 2026-04-04 | Health redesign: quality-only grades, context-aware opportunities (replaces utilization/maturity/segment), Anthropic guidance. 482 tests |
| **2.2.0** | 2026-04-04 | Fixture filtering (test findings excluded from grades), session path fix, UX polish. 461 tests |
| **2.1.0** | 2026-04-03 | UX redesign: auto-scope, zero questions, simplified commands (15 from 17). 441+ tests |
| **2.0.0** | 2026-04-03 | Complete rewrite: 8 scanners, 25 gap dimensions, auto-fix, drift, suppressions, self-audit. 408+ tests |
| **1.6.0** | 2026-04-03 | Report generator, suppression engine, self-audit CLI, PostToolUse hook |
| **1.5.0** | 2026-04-03 | Diff engine, baseline manager, drift CLI, plugin health scanner |
| **1.4.0** | 2026-04-03 | Fix engine, rollback engine, fix CLI, PreToolUse hook |
| **1.3.0** | 2026-04-03 | Scoring module, posture CLI, feature-gap agent |
| **1.2.0** | 2026-04-03 | 4 advanced scanners (MCP, import, conflict, feature-gap) |
| **1.1.0** | 2026-04-03 | 4 core scanners, scan orchestrator, test infrastructure |
| **1.0.0** | 2026-02-11 | Cross-platform support |
| **0.7.0** | 2026-02-07 | Initial version (version reset from inflated 1.2.0) |

See [CHANGELOG.md](CHANGELOG.md) for full details.

---

## License

[MIT License](LICENSE) — Copyright (c) 2025-2026 Kjell Tore Guttormsen