From claude-ecosystem
Audits Claude Code settings.json files for syntax, schema compliance, permissions, sandbox settings, env vars, and exposed secrets. Validates configs before deployment.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-ecosystem:audit-settingsopusThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Audit Claude Code settings.json files for quality, compliance, and security.
Audit Claude Code settings.json files for quality, compliance, and security.
Before auditing, initialize the environment:
Get the current UTC date, capture the project root path, ensure the temp directory exists, and clean up stale audit files. The settings-management skill provides authoritative validation guidance (auto-loaded when this command runs).
| Argument | Description |
|---|---|
| (none) | Audit all discoverable settings files |
project | Only audit .claude/settings.json |
user | Only audit ~/.claude/settings.json |
all | Audit all scopes explicitly |
--force | Audit regardless of modification status |
--skip-validation | Skip finding validation (faster, but may include false positives) |
Check project settings (.claude/settings.json), user settings (~/.claude/settings.json on Unix, %USERPROFILE%\.claude\settings.json on Windows), and plugin settings in marketplace repos.
Parse scope selector and --force flag. Filter files to match requested scope.
Display mode, files discovered, and list with scope and last modified date.
For each file, spawn the settings-auditor subagent with scope, path, and last audit date. Run in parallel when multiple exist.
Subagents write findings to .claude/temp/. The main conversation thread collects results and updates audit logs using its Write/Edit tools.
Unless --skip-validation flag is present:
audit-finding-validator agent with:
project_root: The captured project root pathaudit_type: "settings"audit_files: List of .claude/temp/audit-*-settings-*.json file paths.claude/temp/audit-filtered-findings.jsonIf --skip-validation flag is present:
Report total audited by scope, results, and details table. List security alerts with remediation.
Include validation statistics (if validation was performed):
| Scope | Credentials Found | Result |
|---|---|---|
| Project | Yes | CRITICAL - version controlled |
| User | Yes | WARNING - not version controlled |
Project settings should NEVER contain API keys or tokens (version controlled).
| Platform | User Settings |
|---|---|
| Unix | ~/.claude/settings.json |
| Windows | %USERPROFILE%\.claude\settings.json |
All audit results are written to .claude/audit/settings.md.
Use /audit-log settings to view current audit status.
User: /audit-settings
Claude: Discovering settings files...
## Audit Plan
**Mode**: SMART
**Files discovered**: 2
1. [project] .claude/settings.json
2. [user] ~/.claude/settings.json
[Spawns settings-auditor subagents]
## Audit Complete
| Scope | File | Result | Score |
| --- | --- | --- | --- |
| project | .claude/settings.json | PASS | 100/100 |
| user | ~/.claude/settings.json | PASS | 98/100 |
User: /audit-settings project
Claude: Auditing project settings...
npx claudepluginhub melodic-software/claude-code-plugins --plugin claude-ecosystemAudits .claude/ config for cross-references, permissions, inventory drift, model tiers, docs freshness. Auto-fixes issues at high/medium/all severity levels or upgrades with verification and A/B testing.
Audits Claude Code configurations for best practices in skills, instructions, MCP servers, hooks, plugins, security, over-engineering, and context efficiency via file scans and focused checks. Invoke with /claudit [focus-area].
Audits .claude/rules/*.md files for quality, compliance, glob validity, naming, and structure using subagents. Use when creating, validating rules, or troubleshooting loading issues.