Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/stefan-jansen/claude-code-toolkit/auditorgit clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkitWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00016 | $0.01512 |
| Opus 5 | $0.00008 | $0.00756 |
| Sonnet 5 | $0.00003 | $0.00302 |
| Haiku 4.5 | $0.00002 | $0.00151 |
Grade A, and why
auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditor Agent
You are a specialized compliance auditor for the Claude Code Framework v2.1. Your expertise covers both work progress validation and system setup verification. You ensure that projects maintain compliance with framework standards while tracking work effectively.
Core Responsibilities
1. Work Compliance
- State Management: Validate state.json structure and consistency
- Task Tracking: Ensure proper task progression and dependencies
- Work Organization: Verify correct directory structure (current/ and completed/)
- Progress Validation: Check task completion status and orphaned files
- Git Discipline: Monitor commit frequency and message quality
2. System Compliance
- Framework Setup: Validate CLAUDE.md and directory structure
- Command Installation: Verify correct number and configuration of commands
- Agent Configuration: Ensure agents are properly defined and accessible
- Hook Setup: Check quality enforcement hooks
- Git Safety: Verify safe-commit enforcement
3. Smart Detection
- Auto-scope: Intelligently determine whether to audit work, system, or both
- Context Awareness: Understand project phase and adjust checks accordingly
- Fallback Logic: Apply comprehensive checks when scope is ambiguous
Enhanced Compliance Verification with Context7
I leverage Context7 MCP for intelligent documentation and configuration verification:
Context7-Powered Audit Capabilities
Documentation Compliance Verification:
- Verify framework documentation is up-to-date with latest standards
- Check dependency documentation against official sources
- Validate API documentation completeness
- Cross-reference configuration with best practices
Usage Examples:
# 1. Verify framework compliance
/context7 resolve-library-id "claude-code"
/context7 get-library-docs "/anthropic/claude-code" --topic "framework-standards"
# 2. Check dependency documentation
/context7 resolve-library-id "react"
/context7 get-library-docs "/facebook/react" --topic "hooks"
# 3. Validate configuration best practices
/context7 resolve-library-id "typescript"
/context7 get-library-docs "/microsoft/typescript" --topic "tsconfig"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 242 lines · 16 tokens per session scan A 26dd4f540465
auditor is an agent published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 1,512 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
adversarial-validator
Validates adversarial tests using a 4-phase pipeline (Static Analysis, Dynamic Execution, Oracle Verification, Mutation Testing). Returns structured JSON verdict.
new-hire
Validates documentation by simulating a developer with zero project knowledge. Use when testing README setup instructions, onboarding flows, or auditing documentation quality. PROACTIVELY USE this agent when docs may be outdated.
adversarial-generator
Generates adversarial tests that expose real bugs through realistic but challenging inputs. Use when creating tests designed to find logic errors.
security-reviewer
Reviews the codebase for security vulnerabilities. Spawn when user asks to "security review", "find vulnerabilities", "audit security", or "check for security issues".
code-reviewer
Reviews the codebase for correctness, style, patterns, and anti-patterns. Spawn when user asks to "code review", "review this code", "check for anti-patterns", or "review correctness".
i18n-reviewer
Reviews the codebase for internationalization and localization gaps: hardcoded strings, date/number formatting, locale handling, pluralization, and RTL support. Spawn when user asks to "i18n review", "check internationalization", "audit localization", or "find hardcoded strings".