Prompt Auditor — Security agent for Claude Code
Audit dark-factory prompt files against Prompt Definition of Done.
How to install Prompt Auditor
Installs to ~/.claude/agents/bborbe-dark-factory-prompt-auditor.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/bborbe/dark-factory/HEAD/agents/prompt-auditor.md -o ~/.claude/agents/bborbe-dark-factory-prompt-auditor.md Restart Claude Code, or start a new session, for it to be picked up.
What Prompt Auditor does
name: prompt-auditor description: Audit dark-factory prompt files against Prompt Definition of Done tools:
- Read
- Bash
- Glob model: opus effort: high
Expert dark-factory prompt auditor. You evaluate prompt files against the Prompt Definition of Done and quality criteria. The audit exists to catch failures before they ship — stale code references, missing boundary tests, cross-repo writes that lose work when the container exits. Verify both structure and code reference ac
Alternatives in Security
- Wcag Audit Patterns — Comprehensive guide to auditing web content against WCAG 2.2 guidelines with actionable remediation 31.9k ★
- Retool Parity Audit — Audits the Retool parity checklist against what is actually built, using the export inventories and the Retool 7.2k ★
- Claude Code System Prompts — by Piebald AI - All parts of Claude Code's system prompt, including builtin tool descriptions, sub agent promp 6.3k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Scenario Auditor
Audit dark-factory scenario files against Scenario Writing Guide
Rails Auditor
Final gatekeeper for code quality, security, and performance. Validates Definition of Done (DoD) and reviews G
Quality Guardian
Quality audit — tests, observability, performance, documentation, Definition of Done.
Agent Auditor
Audit agents against Agent & Command Development Guide for structure, role definition, workflow, and effective
Verification Auditor
Verification auditor that checks every agent's claims against the actual codebase. Runs twice — once after imp
Harness UI Reviewer
UI reviewer — two modes: pre-build, judge whether DESIGN.md is a sound contract; post-build, adversarially aud
Related Skills
Audit Scenario
Audit dark-factory scenario file against Scenario Writing Guide
Brotherme Review
Check the current work against the definition of done and report what passes and what does not
Factory Goal
Start an Agent Factory campaign from one prompt — decompose the objective into Linear units, spawn an agent te