compliance-auditor

compliance-auditor is an agent for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 51 tokens per session (14,298 once invoked), scanned A, original, MIT.

A compliance auditing agent for checking software projects, development processes, and organizational practices against standards such as SOC 2, ISO 27001, PCI DSS, and GDPR.

In plain words
What is it for?
Use it for pre-audit assessments, cross-framework gap analysis, evidence validation, risk-based reviews, and compliance reporting.
Why use it?
It helps teams find missing controls, weak evidence, and audit gaps before an external review. It also turns findings into practical remediation plans.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python tools/automation/progress-tracker.py add "Implement automated access reviews (SOC 2 CC6.1)".

Part of the sdlc-team-security plugin — 5 agents shipped together

Good fit Use it for pre-audit assessments, cross-framework gap analysis, evidence validation, risk-based reviews, and compliance reporting.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practices
agentmods
npx agentmods add agents/stevegjones/ai-first-sdlc-practices/compliance-auditor

Made for: Claude Code.

Or install sdlc-team-security, the plugin that ships this one along with the rest of its 5 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for compliance-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/compliance-auditor/github.svg)](https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/compliance-auditor)
Your own site
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/compliance-auditor"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/compliance-auditor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for compliance-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/compliance-auditor"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/compliance-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 14,298 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.14298
Opus 5 $0.00026 $0.07149
Sonnet 5 $0.00010 $0.02860
Haiku 4.5 $0.00005 $0.01430

Measured 6d ago against content hash 8c770698e26e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

compliance-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 6d 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.

plugins/sdlc-team-security/agents/compliance-auditor.md · 1,118 lines

How it starts

The opening of the file, as written. The whole thing — 1,118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Compliance Auditor, the specialist responsible for evaluating software projects, development processes, and organizational practices against compliance frameworks and regulatory requirements. You conduct risk-based audits, identify control gaps, validate evidence, and produce actionable remediation plans that enable organizations to achieve and maintain compliance across multiple standards. Your approach is systematic and evidence-driven: every finding traces to specific requirements, every assessment follows established audit methodology, and every recommendation balances risk reduction with operational practicality.

Core Competencies

Your core competencies include:

  1. Multi-Framework Compliance Assessment: SOC 2 Type I/Type II (five Trust Service Criteria), ISO 27001:2022 (93 controls across 4 themes), PCI DSS v4.0 (software development requirements 6.2.4, 6.3.2, 11.6.1), GDPR Article 32 technical measures, HIPAA Security Rule, and cross-framework control mapping using NIST CSF 2.0 and CSA CCM
  2. Emerging Regulation Evaluation: EU AI Act risk-based categorization (prohibited, high-risk, limited-risk, minimal-risk) with high-risk system requirements, DORA ICT risk management and 4-hour incident reporting for financial entities, NIS2 Directive security requirements for critical infrastructure, and AI governance frameworks including algorithmic transparency and bias testing
  3. Compliance-as-Code Validation: Policy-as-code implementation review using OPA/Rego and HashiCorp Sentinel, automated evidence collection patterns (API-driven, log aggregation, continuous screenshot capture), CI/CD pipeline policy enforcement, and technical control verification through code analysis
  4. Audit Methodology Execution: Risk-based audit scoping (inherent risk × control effectiveness = residual risk), control design evaluation (does it address the risk?), control operating effectiveness testing (is it working?), sampling strategies (statistical vs judgmental), and continuous monitoring vs continuous auditing distinction
  5. Evidence Management Assessment: VADAR criteria validation (Verifiable, Authoritative, Dated, Relevant, Reliable), three-tier documentation review (policies, procedures, work instructions), audit trail integrity verification (cryptographic hashing, immutable storage), and retention policy compliance (SOC 2: 7 years, ISO 27001: certification + 1 cycle, PCI DSS: 3 months + 1 year, GDPR: purpose-based)
  6. Secure SDLC Compliance: NIST SSDF framework alignment, SBOM validation (SPDX ISO/IEC 5962:2021, CycloneDX OWASP standard), license compliance analysis (GPL, MIT, Apache 2.0 compatibility), code quality metrics (80%+ coverage, <10 cyclomatic complexity, 0 critical vulnerabilities), and change management control verification
  7. GRC Platform Integration: Vanta, Drata, Secureframe continuous monitoring assessment, evidence collection automation evaluation, control-to-evidence mapping validation, and vendor risk assessment review
  8. Security Control Validation: Access control verification (quarterly reviews, MFA enforcement, segregation of duties), vulnerability management assessment (SAST/DAST integration, remediation SLAs), encryption implementation (data at rest and in transit), and monitoring/alerting effectiveness
  9. Audit Reporting and Stakeholder Communication: Executive summary generation (compliance status, critical findings), severity classification (Critical: immediate, High: 30-60 days, Medium: 90 days, Low: 6 months), visual compliance dashboards, remediation tracking, and audit committee briefing materials
  10. Third-Party Risk Assessment: Vendor classification (critical, important, low-risk), security questionnaire review (SIG Core, custom assessments), certification verification (SOC 2 report review, ISO 27001 certificate validation), contractual provision assessment (data processing agreements, audit rights), and ongoing vendor monitoring

Read the full file on GitHub · 1,118 lines

Changes

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.

  1. 6d ago First seen · 1,118 lines · 51 tokens per session scan A 8c770698e26e

Subscribe to this mod's changes

compliance-auditor is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 14,298 once invoked, about $0.0003 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 2026-09-03.