Skip to main content
subagent CX Codex

read-only-auditor — Claude Code subagent: security audit without edits

read-only-auditor — a security audit subagent that cannot touch your files. Hooks in its frontmatter block Write, Edit, and Bash for the whole session.

no license 434 installs updated 2026-10-24

Install into Claude Code · claude-code-templates All methods and platforms ↓
npx claude-code-templates@latest --agent security/read-only-auditor
Open on GitHub

What read-only-auditor does

Most audit prompts rely on trust: you ask the model not to change anything and hope it complies. read-only-auditor takes a different path. PreToolUse hooks reject Write, Edit, and Bash calls before they run, so the read-only guarantee is enforced by the system.

Coverage includes hardcoded credentials, SQL injection through raw queries, XSS, path traversal, permissive CORS, and debug endpoints left in production config. For each finding it records the file path, line number, vulnerability class, and severity from Critical down to Low. Fixes are described in prose, never applied to the code.

It uses only Read, Grep, and Glob, with the sonnet model. The report ends with a table sorted by severity and a note that no files were modified.

Installation drops .claude/agents/read-only-auditor.md into your project. For PCI-DSS reviews of payment code or pre-merge audits, the guarantee being mechanical rather than conversational matters.

What it helps with

  • Run a security audit that cannot alter the codebase
  • Check payment processing code for PCI-DSS issues safely
  • Find hardcoded secrets and JWT misconfigurations
  • Produce a severity-ranked report for each finding
  • Audit a branch before merge without touching it

Example prompts for the agent

  • Audit src/payments/ for PCI-DSS compliance, do not change anything
  • Review src/auth/ for hardcoded secrets and JWT problems
  • Run a read-only audit of app/ before merging to main

How to install read-only-auditor

1claude-code-templates

npx claude-code-templates@latest --agent security/read-only-auditor

2Manually: put the files in place

.claude/agents/read-only-auditor.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about read-only-auditor

How do I install read-only-auditor in Claude Code?

Run npx claude-code-templates@latest --agent security/read-only-auditor. This creates .claude/agents/read-only-auditor.md and the subagent becomes available in your project.

What does read-only-auditor do?

It performs a security audit with write access blocked at the hook level. Write, Edit, and Bash calls are rejected automatically, so files stay untouched even if the model tries to modify them.

How is it different from just prompting the model to stay read-only?

The restriction lives in PreToolUse hooks, not in a polite instruction. An attempt to call Write, Edit, or Bash is interrupted before execution, which a plain prompt cannot guarantee.

Similar subagents

All subagents for Security →

From the same set745

The whole set →
deslop deslop cleans AI-generated clutter from a branch before merging code. It inspects diffs against main to strip needless comments, type workarounds, and unneeded guards. CX Codex +1 437installs flutter-expert flutter-expert sets up Claude Code for cross-platform app engineering with Flutter 3.x and Dart 3. Helps handle state management, platform channels, and Impeller tuning. CX Codex +1 437installs memory-search memory-search searches conversation history and semantic memory across sessions. Helps agents recall earlier decisions before tackling new code. CX Codex +1 434installs penetration-test A slash command that runs penetration testing on a web app, API or auth flow and returns a report with fixes. CX Codex +1 434installs session-learning-capture session-learning-capture is a Claude Code command that saves session insights to project memory. Choose project knowledge, implementation fixes, structure notes, or workflow improvements. CX Codex +1 425installs architecture-scenario-explorer architecture-scenario-explorer walks an agent through architecture choices under load, growth and failure scenarios, then lays out the trade-offs between quality attributes. CX Codex +1 423installs cleanup-cache cleanup-cache cleans npm, Homebrew, Yarn, browser, and ML caches to free up drive space. Helps recover storage using three different cleaning modes. CX Codex +1 416installs agent-manager-skill agent-manager-skill runs multiple CLI agents concurrently inside isolated tmux sessions. It handles background task dispatch, log inspection, and cron scheduling. CX Codex +1 415installs

Project sponsors

Companies that keep this analytics open