# Config-Audit Plugin for Claude Code

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

> **Solo-maintained, fork-and-own.** This plugin is a starting point, not a vendor product. Issues are welcome as signals; pull requests are not accepted. See [GOVERNANCE.md](GOVERNANCE.md) for the full model and what upstream provides.

*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-5.7.0-blue)
![Platform](https://img.shields.io/badge/platform-Claude_Code_Plugin-purple)
![Scanners](https://img.shields.io/badge/scanners-15-cyan)
![Commands](https://img.shields.io/badge/commands-21-green)
![Agents](https://img.shields.io/badge/agents-7-orange)
![Hooks](https://img.shields.io/badge/hooks-4-red)
![Tests](https://img.shields.io/badge/tests-1168+-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. 15 deterministic scanners across 10 quality areas, context-aware feature recommendations, auto-fix with backup/rollback, a prompt-cache-aware Token Hotspots scanner with optional API-calibrated `--accurate-tokens` mode, plus cache-prefix stability, dead-tool, cross-plugin collision, and output-style detection. Zero external dependencies.

---

## Table of Contents

- [What's New in v5.4.0](#whats-new-in-v540)
- [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's New in v5.4.0

**Plugin-hygiene & settings-validation hardening.** Three additive findings extend the plugin and
settings surfaces — no new scanner, so the count stays **13**:

- **PLH plugin-folder shadowing** (`CA-PLH-015`) — flags a `plugin.json` component-path key in the
  *replaces* set (`commands`/`agents`/`outputStyles`) that points at a custom path while the
  default folder of that name still exists, so the folder is silently ignored (dead config).
  Mirrors Claude Code's own warning in `/doctor`, `claude plugin list`, and the `/plugin` detail
  view. `skills` is excluded (it *adds to* the default scan, never shadows), as are
  `hooks`/`mcpServers`/`lspServers` (own merge rules); a custom path resolving *into* the default
  folder is not flagged.
- **PLH `skills:`-array validation** (`CA-PLH-016`) — validates each `plugin.json` `skills` entry
  (string or array) resolves to an existing directory inside the plugin root; flags `non-string`,
  `escapes-root`, `not-found`, and `not-a-directory` entries. Mirrors `claude plugin validate`.
- **SET `autoMode` structure + dead-config** — checks that `autoMode` is an object whose only keys
  are `environment`/`allow`/`soft_deny`/`hard_deny`, each a string array (the literal `"$defaults"`
  is valid); unknown sub-keys and wrong types are flagged (medium). Separately, `autoMode` placed
  in **shared** project settings (`.claude/settings.json`) is flagged as dead config (low) —
  Claude Code's classifier does not read it there.

All three extend existing PLH and SET scanners. `--json` and `--raw` output remain byte-stable.

---

## 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** — 15 deterministic scanners verify correctness across every configuration file, catching broken imports, deprecated settings, conflicting rules, format errors, permission contradictions, prompt-cache token waste, cache-prefix instability, dead tool grants, cross-plugin skill collisions, output styles that silently strip Claude Code's coding instructions, and procedures in CLAUDE.md that would fit better as a skill
- **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 10 quality areas (incl. Token Efficiency, Plugin Hygiene) |
| `/config-audit tokens` | prompt-cache-aware token hotspots — ranked by estimated waste, each tagged with its load pattern (always / on-demand / external); 6 patterns + optional `--accurate-tokens` API calibration |
| `/config-audit manifest` | Ranked table of every token source (CLAUDE.md, rules, agents, skills, output styles, MCP, hooks) sorted by estimated tokens — each tagged with its **load pattern** (always-loaded / on-demand / external) plus an **always-loaded subtotal** ("≈X tokens enter context every turn before you type"). Component-level: no coarse plugin roll-up (it would double-count) |
| `/config-audit feature-gap` | Context-aware feature recommendations grouped by impact |
| `/config-audit optimize` | Optimization lens (mechanism-fit): config that works but fits a better mechanism — procedure→skill, lifecycle→hook, unscoped path→rule, "never"→permission. Hybrid motor (deterministic pre-filter + opus precision gate), every finding cites a best-practices-register rule |
| `/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 whats-active` | Read-only inventory of plugins, skills, MCP, hooks, CLAUDE.md active for a repo (with token estimates) |
| `/config-audit knowledge-refresh` | Keep the best-practices register fresh — flag stale entries (sources older than ~90d) + poll for new/changed Claude Code practices; **human-approved writes only** (Verifiseringsplikt). Deterministic stale core + web candidate poll |
| `/config-audit campaign` | Machine-wide audit campaign — durable ledger above sessions tracking each repo's lifecycle (pending → audited → planned → implemented) + a machine-wide roll-up by severity + a single **cross-repo prioritized backlog** to pick from (severity-weighted) + plan **export** (drop a planned repo's plan into its own `docs/`), resumable across sessions; **human-approved writes only** (read-only report + deterministic write/export CLIs). Execution reuses the existing `/config-audit implement` + `rollback` |
| `/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

15 Node.js scanners that perform structural analysis an LLM cannot reliably do: schema validation, circular reference detection, import resolution, conflict detection across scopes, prompt-cache-aware token-cost analysis, cache-prefix stability, dead-tool detection, cross-plugin skill collisions, output-style validation, and a best-practice optimization lens (mechanism-fit). Plus a standalone plugin-health scanner. 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 (line count **plus** a context-window-scaled char budget mirroring Claude Code's ~40.0k-char startup warning), 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, exposed env vars, unknown fields |
| `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 — plus a conditional `disableBundledSkills` recommendation when the active skill listing is over budget |
| `token-hotspots.mjs` | TOK | Cache-breaking volatile content, redundant tool permissions, deep import chains, oversized cascades, bloated skill descriptions, MCP tool-schema budget |
| `cache-prefix-scanner.mjs` | CPS | Volatile content in lines 31–150 of the CLAUDE.md cascade — beyond the cache-prefix window but still re-loaded every turn |
| `disabled-in-schema-scanner.mjs` | DIS | Dead/ineffective permission entries: (1) tools in BOTH `permissions.deny` and `permissions.allow` — deny wins (incl. the `Tool(*)` deny-all glob, equivalent to a bare deny); (2) unanchored allow wildcards (`*`, `B*`, `mcp__*`) that Claude Code silently skips — valid only as `mcp__<server>__*`; (3) `Tool(param:value)` rules whose key is the tool's own canonicalizing field (`command`/`file_path`/`path`/`notebook_path`/`url`) — CC ignores these and emits a startup warning |
| `collision-scanner.mjs` | COL | Cross-plugin skill name collisions; user-vs-plugin overlaps |
| `skill-listing-scanner.mjs` | SKL | Skill-listing token budget: a single skill description over the ~1,536-char listing cap Claude Code truncates (`CA-SKL-001`), and the summed active-skill descriptions exceeding the ~2%-of-context listing budget (`CA-SKL-002`) |
| `output-style-scanner.mjs` | OST | Output-style validation: a custom (user/project) style missing `keep-coding-instructions: true` that silently strips built-in software-engineering instructions (`CA-OST-001`), a plugin style with `force-for-plugin: true` overriding the user's selected `outputStyle` (`CA-OST-002`), and a settings `outputStyle` resolving to no built-in or custom style — dead config (`CA-OST-003`) |
| `optimization-lens-scanner.mjs` | OPT | Optimization lens (mechanism-fit): a multi-step procedure in CLAUDE.md that would fit better as a skill (`CA-OPT-001`) — reads the machine-readable best-practices register, framed as an opportunity, not a failure. The deterministic half of the lens; prose-judgment cases (lifecycle→hook, unscoped path→rule, "never"→permission) are judged by the opus `optimization-lens-agent` via `/config-audit optimize` |

> **Cross-scanner remediation — diagnosis meets the fix.** SKL diagnoses an over-budget
> skill listing (`CA-SKL-002`); GAP prescribes the remedy. When the active skill listing
> exceeds its ~2%-of-context budget and `disableBundledSkills` is not already set (in the
> env var or the settings cascade), the feature-gap scanner recommends that lever — hiding
> Claude Code's bundled skills (`/code-review`, `/batch`, `/debug`, `/loop`, `/claude-api`, …)
> from the model to reclaim listing budget without touching your own skills (CC 2.1.169+).
> It fires only under measured pressure, so it stays an opportunity rather than noise. Both
> scanners share one budget definition (`scanners/lib/skill-listing-budget.mjs`).

> **CLAUDE.md size — two complementary signals.** CML checks line count (200/500, for
> readability) **and** a character budget that mirrors Claude Code's own startup warning
> — *"Large CLAUDE.md will impact performance (X chars > 40.0k)."* CC 2.1.169 scales that
> threshold with the model's context window, so the char finding anchors on a conservative
> 200k window and discloses the relaxed ~200,000-char figure at 1M context. A file can be
> long by lines yet under the char budget (short lines), or short by lines yet over it — so
> both signals earn their place. The 200k/1M window constants live in the shared
> `scanners/lib/context-window.mjs` (single source of truth with the skill-listing budget).

> **Permission rules CC silently ignores — severity follows intent.** `Tool(param:value)`
> matching is real (CC 2.1.178), but the tool's own canonicalizing fields are off-limits:
> `command` (Bash/PowerShell), `file_path` (Read/Edit/Write), `path` (Grep/Glob),
> `notebook_path` (NotebookEdit), `url` (WebFetch). CC ignores a rule keyed on its tool's
> field and emits a startup warning, because `Bash(command:rm *)` is bypassable by a compound
> command. DIS splits severity by where the rule lives: in **deny/ask** it is **false
> security** (medium — the block you intended never applies), in **allow** it is **dead
> config** (low — `param:value` matching is deny/ask-only, so the entry grants nothing). The
> predicate lives in `scanners/lib/permission-rules.mjs`; valid forms like `Bash(npm:*)`,
> `WebFetch(domain:host)`, and `Agent(model:opus)` are never flagged.

> **Plugin namespace collisions — the one shadow that actually loses components.**
> Claude Code namespaces every plugin component by the plugin's declared `name`
> (`/name:command`, `name:skill`, agent `name`), so a plugin component can never shadow a
> user- or project-level one — they live in separate namespaces. The real hazard is two
> plugins that declare the **same** `name` in `plugin.json`: their namespaces collapse into
> one, and because the resolution between two installed same-name plugins is undocumented,
> one plugin's commands, skills, and agents are silently shadowed and become unreachable.
> The standalone plugin-health scanner (PLH) flags this at **medium** severity, keying on the
> declared `name` field rather than the folder name (the folder name is irrelevant to the
> namespace). A *command* name shared by two **differently-named** plugins is a milder case —
> namespacing keeps both reachable as `/a:cmd` and `/b:cmd`, so it is only ambiguity in error
> messages, search results, and the command listing. PLH reports that at **low** severity
> (group-first, one finding per command name), mirroring the COL scanner, which owns the
> analogous skill-name overlaps across *different* namespaces.

> **Plugin-folder shadowing — when a manifest path silently buries a default folder.**
> A plugin's `plugin.json` can point a component type at a custom path — `commands`,
> `agents`, and `outputStyles` all *replace* their default folder when set. So if a plugin
> declares `"commands": "./custom/"` while a `commands/` folder still exists, Claude Code
> stops scanning `commands/` entirely and everything in it silently disappears (dead config).
> PLH flags this at **medium** severity (`CA-PLH-015`), mirroring Claude Code's own warning in
> `/doctor` and `claude plugin list` (v2.1.140+). It does **not** flag `skills` — that key
> *adds to* the default `skills/` scan rather than replacing it, so both load — nor does it
> flag a custom path that points back into the default folder (e.g.
> `"commands": ["./commands/x.md"]`), because the folder is then addressed explicitly.

> **`skills:`-array validation — every listed path must be a real skill folder.**
> A plugin's `plugin.json` may list custom skill directories in a `skills` array (each entry a
> path to a folder containing `SKILL.md`). PLH validates each entry (`CA-PLH-016`, **medium**)
> and flags four ways an entry can be broken: it isn't a string, it points at a path that
> **doesn't exist**, it points at a **file** instead of a directory, or it **escapes the plugin
> root** (`../…` — installed plugins can't reference files outside their own directory, so the
> skill never loads). A valid existing directory is never flagged. This mirrors
> `claude plugin validate`. Note `skills` *adds to* the default `skills/` scan, so a custom path
> here is never a shadow — it just has to resolve to a real folder.

> **`autoMode` validation — structure and the shared-settings blind spot.** The SET scanner
> checks the auto-mode classifier config two ways. **Structure:** `autoMode` must be an object
> whose only keys are `environment`, `allow`, `soft_deny`, and `hard_deny`, each a list of
> plain-text rule strings (the literal `"$defaults"` is allowed). An unknown sub-key (e.g. a
> typo'd `hard_denies`), a non-object value, or a sub-key that isn't a string array is flagged
> **medium** — a typo'd key silently drops those rules. **Scope:** Claude Code does **not** read
> `autoMode` from *shared* project settings (`.claude/settings.json`) — "a checked-in repo cannot
> inject its own allow rules" — so an `autoMode` block committed there is dead config (**low**);
> it only takes effect in user (`~/.claude/settings.json`), local (`.claude/settings.local.json`),
> or managed settings.

### 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] [--accurate-tokens] [--with-telemetry-recipe]` |
| **Manifest** | `node scanners/manifest.mjs <path> [--json]` — ranked component-level source table with per-source load pattern + always-loaded subtotal |
| **What's active** | `node scanners/whats-active.mjs <path> [--json] [--verbose] [--suggest-disables]` |
| **Self-audit** | `node scanners/self-audit.mjs [--json] [--fix] [--check-readme]` |
| **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 |
| **optimization-lens-agent** | Opus | Mechanism-fit precision gate — judges prose-judgment lens candidates (lifecycle→hook, path→rule, never→permission), cites the best-practices register | 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 15 scanners + the standalone plugin-health scanner on itself via `self-audit.mjs`. Test fixtures and example files are automatically excluded from scoring — a configuration plugin that ships deliberately broken examples shouldn't fail its own audit. Use `--check-readme` to verify badge counts are in sync with the filesystem.

```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, `WEIGHTS` export (v5 F3) |
| `output.mjs` | Finding objects (`CA-XXX-NNN` format), scanner results, envelope, `details` field |
| `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 (v5 severity-weighted), health scorecard, `scoringVersion: 'v5'` |
| `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 |
| `active-config-reader.mjs` | Read-only inventory of plugins/skills/MCP/hooks/CLAUDE.md cascade with token estimates |
| `tokenizer-api.mjs` | Anthropic `count_tokens` wrapper for `--accurate-tokens` (v5 N5); 5s timeout, 429 backoff, key masking |

### 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 |
| `manifest.mjs` | CLI: ranked component-level source table w/ load-pattern accounting (v5 N2; v5.6 B) |
| `whats-active.mjs` | CLI: read-only active-config inventory (v3.1.0+) |
| `token-hotspots-cli.mjs` | CLI: token hotspots ranking with optional `--accurate-tokens` |

---

## 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 (cache-stability guidance) |
| `anti-patterns.md` | Common mistakes mapped to scanner IDs |
| `hook-events-reference.md` | All 28 hook events with details |
| `feature-evolution.md` | Feature timeline for staleness detection |
| `gap-closure-templates.md` | Config-specific templates for closing gaps |
| `prompt-cache-patterns.md` | Token-cost dynamics (prompt-cache patterns) — patterns powering the TOK scanner |
| `cache-telemetry-recipe.md` | `jq` recipe for verifying prompt-cache hit rate from session transcripts |

**Machine-readable register (`best-practices.json`).** Alongside the human-readable documents
above, `knowledge/best-practices.json` is a provenance-stamped, schema-validated register of
best-practice claims and mechanism-fit rules — each entry carries `source.url`, a `verified`
date, and a `confidence`. It is the source of truth for the optimization lens (OPT scanner +
`/config-audit optimize`); the Markdown files remain the human-readable mirror. Loaded and validated by
`scanners/lib/best-practices-register.mjs` (zero-dependency, native JSON). See
`docs/v5.7-optimization-lens-plan.md`.

---

## Testing

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

1168 tests across 67 test files (22 lib + 35 scanner + 1 hook + 1 agent + 3 commands + 1 knowledge + 4 top-level). 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 |
|---------|------|-----------|
| **5.7.0** | 2026-06-21 | "Optimization lens" — first detector of the «optimally shaped?» axis (vs «correct?»), plus a living knowledge layer. **Register:** `knowledge/best-practices.json`, a provenance-stamped, schema-validated best-practices register (first runtime-consumed `knowledge/` file). **OPT scanner (count 14→15):** `CA-OPT-001` (LOW) a ≥6-step CLAUDE.md procedure that would fit better as a skill, citing register entry `BP-MECH-003`. **`/config-audit optimize` + `optimization-lens-agent` (opus, agents 6→7):** prose-judgment lens for lifecycle→hook (`BP-MECH-001`), unscoped path→rule (`BP-MECH-002`), "never"→permission (`BP-MECH-004`); pre-filter recall + opus precision gate. **`/config-audit knowledge-refresh` (commands 19→20):** deterministic stale-check (injected reference date, 90-day cadence) + web re-verify/poll, human-approved writes only. Last two are agent/web-driven (not byte-stable). 1091 tests |
| **5.6.0** | 2026-06-20 | "Steering-model II" — the load-pattern / compaction-survival model lands end-to-end. **Foundation:** `active-config-reader` now enumerates rules, agents, and output styles (alongside CLAUDE.md/plugins/skills/hooks/MCP), each tagged `loadPattern` (always / on-demand / external) + `survivesCompaction` from the published loading model; the frontmatter parser also reads YAML block sequences (`paths:` lists). **B (load-pattern accounting):** `manifest` reports component-level sources (the double-counting plugin roll-up is gone), tags every source with the load-pattern triple, and leads with an **always-loaded subtotal** ("tokens that enter context every turn"); `token-hotspots` annotates each ranked hotspot with its load pattern. **C (output styles):** new orchestrated **OST** scanner (count 13→**14**) — `CA-OST-001` a custom style stripping built-in coding instructions (missing `keep-coding-instructions: true`, V10), `CA-OST-002` a plugin style with `force-for-plugin: true` overriding the user's `outputStyle` (V11), `CA-OST-003` a settings `outputStyle` resolving to no known style (dead config). Doc-verified; frozen v5.0.0 snapshots preserved via strip-helpers, SC-5 regenerated. 1023 tests |
| **5.5.0** | 2026-06-20 | "Steering-model I" — two additive compaction-durability / dead-config findings (count stays **13**, `--json`/`--raw` byte-stable). Per the official "what survives compaction" model: RUL flags a large (>50-line) **path-scoped** rule not re-injected after compaction (LOW); CML flags a **nested** (subdir) CLAUDE.md not re-injected after compaction (LOW). PLH flags a plugin agent setting `hooks`/`mcpServers`/`permissionMode` — Claude Code ignores these for plugin subagents, so it's dead config (`permissionMode` = MEDIUM false-security, `hooks`/`mcpServers` = LOW). Known limitation: the frontmatter parser reads inline `paths:` but not YAML block sequences (deferred to v5.6 Foundation). 961 tests |
| **5.4.1** | 2026-06-20 | Scanner-correctness patch (count stays **13**, `--json`/`--raw` byte-stable). HKV: added `Setup`/`UserPromptExpansion`/`PostToolBatch` to the valid-event set (a valid hook using one was wrongly flagged "will never fire"), and **removed** `post-session` (the 2.1.169 `post-session` is a self-hosted-runner workspace-lifecycle hook, **not** a settings.json event — absent from `hooks.md`; verified 2026-06-20). RUL: globs-rule wording corrected — only `paths:` is documented, so the finding drops the unverified "deprecated/legacy" claim and steers to the documented field. PLH: optional `model`/`tools`/`name`/`allowed-tools` frontmatter no longer required; CLAUDE.md component-section required only for components the plugin actually ships. 954 tests |
| **5.4.0** | 2026-06-19 | Plugin-hygiene & settings-validation hardening. Three additive findings extend existing PLH and SET scanners (count stays **13**): PLH plugin-folder shadowing (`CA-PLH-015` — a `plugin.json` component-path key in the *replaces* set `commands`/`agents`/`outputStyles` pointing at a custom path while the default folder still exists) mirroring CC's `/doctor` & `claude plugin list` warning; PLH `skills:`-array validation (`CA-PLH-016` — each entry must resolve to a directory in the plugin root; flags `non-string`/`escapes-root`/`not-found`/`not-a-directory`) mirroring `claude plugin validate`; SET `autoMode` structure (only `environment`/`allow`/`soft_deny`/`hard_deny` string arrays) + dead-config (`autoMode` in shared `.claude/settings.json` is not read by CC). `--json`/`--raw` byte-stable. 949 tests |
| **5.3.0** | 2026-06-19 | Permission-rule & plugin-hygiene hardening. Five additive scanner findings extend existing scanners (count stays **13**): DIS forbidden-param rules (`Tool(param:value)` on a canonicalizing field — deny/ask = false security, allow = dead config) and ineffective allow-wildcards + `Tool(*)` deny-all; CML context-window-scaled 40.0k-char CLAUDE.md budget mirroring CC's startup warning; PLH plugin namespace collision (two plugins declaring the same `name`); feature-gap `disableBundledSkills` lever under skill-listing pressure. PLH cross-plugin command-name overlap reframed HIGH → LOW (namespacing keeps both reachable). `--json`/`--raw` byte-stable. 936 tests |
| **5.2.0** | 2026-06-18 | CC 2.1.114→181 compatibility + skill-listing budget. New orchestrated scanner **SKL** (`CA-SKL-001` 1,536-char listing cap, `CA-SKL-002` listing-budget sum) → 13 orchestrated scanners. Five validators refreshed for CC 2.1.114–181 settings/hook surface (`xhigh` effort, `MessageDisplay` + post-session events, 28 hook events). False positives eliminated in MCP (auto-injected/POSIX env vars, invented `trust` field) and permissions (param-aware DIS/CNF). Hermetic HOME isolation across all CLI-spawning tests. 875 tests |
| **5.1.0** | 2026-05-01 | Plain-language UX humanizer. Default output of all 18 commands now leads with prose; findings grouped by user-impact category (Configuration mistake, Conflict, Wasted tokens, Missed opportunity, Dead config) and led by urgency phrase (Fix this now → FYI). New `--raw` flag preserves v5.0.0 verbatim output for tooling that scrapes stderr; `--json` is unchanged and byte-stable. New scanner-lib modules: `humanizer.mjs`, `humanizer-data.mjs` with TRANSLATIONS for 13 scanner prefixes. Self-audit terminal output also humanized. 792 tests (+157 humanizer-tester) |
| **5.0.0** | 2026-05-01 | Reality-based token-optimization. 3 new scanners (CPS cache-prefix, DIS dead tools, COL plugin collisions) → 12 deterministic scanners. New `/config-audit manifest` and `--accurate-tokens` API calibration. Severity-weighted scoring (`scoringVersion: 'v5'`). MCP token estimates 15 → 500+. Plugin Hygiene as 10th quality area. Knowledge: cache-stability replaces 200-line rule, cache-telemetry recipe. **Breaking:** F2 token magnitude jump, F3 severity weighting, F5 Pattern D removed, N1 `CA-TOK-*` glob now matches CA-TOK-005. 635 tests |
| **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