RohiRIK

Audit — Security skill for Claude Code

Security community

Run a read-only system audit and report findings by severity.

How to install Audit

Installs to ~/.claude/skills/rohirik-claude-code-config-audit/SKILL.md

Terminal
mkdir -p ~/.claude/skills/rohirik-claude-code-config-audit && curl -fsSL https://raw.githubusercontent.com/RohiRIK/claude-code-config/HEAD/commands/audit.md -o ~/.claude/skills/rohirik-claude-code-config-audit/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Audit does

description: "Run a read-only system audit and report findings by severity." disable-model-invocation: true

/audit — Read-Only System Auditor

Runs two isolated Gemini CLI instances (Flash + Pro) and produces a ranked findings report.

**IMPORTANT**: Strictly read-only. Only writes to `~/.claude/auditor/reports/`.

Modes

Command What it audits Time
/audit Core — rules, hooks, agents, settings.json, CLAUDE.md ~2 min
`/audit

Alternatives in Security

  • Security Scan Report — Generated: 2026-04-10 20:48 UTC Skills scanned: 134 Total findings: 836 Critical: 32 High: 50 Safe skills: 100 18.1k ★
  • Portaljs Check Data Quality — Audit a local or remote tabular file (CSV/TSV) for common data quality issues 2.3k ★
  • /chain — Build an A→B→C exploit chain for higher severity and payout 927 ★

Full documentation available on GitHub

View Source Repository

Related Skills

Repo Audit — Security skill for Claude Code

Repo Audit

Read-only four-phase repository audit covering discovery and mapping, evidence-based severity-rated findings,

Security community
Audit Report — Security skill for Claude Code

Audit Report

Aggregate audit checkpoints into the final report — executive summary, Scope Coverage, findings by severity, m

Security community
Vf Review — Security skill for Claude Code

Vf Review

Parallel Salesforce code review of the diff against a base ref - dispatch the quality gate and security review

Security community
Ext Report — Security skill for Claude Code

Ext Report

Launch the ext-reporter agent to turn the external-pentest engagement artifacts (scope, inventory, attack plan

Security community
UX A11y — Security skill for Claude Code

UX A11y

WCAG 2.1 AA accessibility audit plus common-courtesy checks beyond the spec. Produces findings grouped by WCAG

Security community
Chain Findings — Security skill for Claude Code

Chain Findings

Escalate low-severity findings into reportable vulnerabilities by building exploit chains (A→B→C)

Security community

Related Agents

Audit Reporter — Security agent for Claude Code

Audit Reporter

Deterministic report assembly — aggregates verdicts and findings, builds the Scope Coverage table, severity ro

Security community
Perf Report Writer — Security agent for Claude Code

Perf Report Writer

Invoke last in a performance audit, after both perf-pattern-scanner and perf-complexity-analyzer have complete

Security community
Project Structure Reviewer — Security agent for Claude Code

Project Structure Reviewer

Read-only audit of the current repo against spec/project/project-structure/, producing a severity-sorted findi

Security community