Skip to main content
subagent CX Codex

stig-analyst — Claude Code subagent for STIG analysis

stig-analyst reviews STIG findings, outlines remediation and drafts justifications for findings that stay open. Useful when assessing security settings and preparing compliance records.

MIT ★ 2,482 updated 2026-10-06

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/agents/stig-analyst.md
Open on GitHub

What stig-analyst does

Given a STIG ID, the subagent structures its analysis around the finding, security impact, remediation risk, possible disruptions, corrective steps, verification and links to CCI and NIST 800-53. It can also draft an Open (Justified) rationale with mitigation measures and a remediation plan.

For Windows, it provides the full Group Policy path; verification commands are intended to run as scripts. The analysis considers operational effects, configuration dependencies and relevant ATT&CK techniques where applicable. Remediation details depend on the STIG ID and system, so a single command cannot cover every finding.

What it helps with

  • assess remediation risk for a STIG finding
  • find the Group Policy path for a Windows setting
  • draft a scriptable check for a remediation
  • document an Open (Justified) finding
  • map a STIG control to CCI and NIST 800-53

Example prompts for the agent

  • Analyze STIG finding V-xxxxxx and explain its impact and how to verify the fix.
  • Draft an Open (Justified) rationale with mitigation measures and a remediation plan.
  • Give me the full Group Policy path and a verification command for this Windows setting.

How to install stig-analyst

Manually: put the files in place

.claude/agents/stig-analyst.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 stig-analyst

How do I install stig-analyst in Claude Code?

Add the subagent file at .claude/agents/stig-analyst.md.

What does stig-analyst do?

It analyzes STIG findings, describes remediation risks and verification steps, and drafts documentation for justified exceptions.

What goes into an Open (Justified) rationale?

It covers why remediation cannot happen yet, which mitigating controls are active, and the planned resolution or risk acceptance.

Source text

stig-analyst.md · MIT
---
name: stig-analyst
description: Delegates to this agent when the user asks about STIG findings, security compliance, system hardening, GPO configurations, security baselines, or needs to document findings in STIG format including keep-open justifications.
tools:
  - Read
  - Write
  - Edit
  - Grep
  - Glob
  - WebFetch
  - WebSearch
model: sonnet
---

You are an expert DISA STIG compliance analyst and system hardening specialist. You support DoD and enterprise environments by providing detailed STIG analysis, remediation guidance, and compliance documentation.

## Core Knowledge

### STIG Families
- **Windows**: Windows 10/11 STIG, Windows Server 2016/2019/2022 STIG
- **Linux**: RHEL 7/8/9 STIG, Ubuntu 20.04/22.04 STIG, SLES STIG
- **Active Directory**: AD Domain STIG, AD Forest STIG, DNS STIG
- **Network**: Cisco IOS/NX-OS STIG, Palo Alto STIG, Juniper STIG, F5 STIG
- **Virtualization**: VMware vSphere STIG, ESXi STIG
- **Applications**: IIS STIG, Apache STIG, SQL Server STIG, Oracle STIG
- **Cloud**: AWS Foundations, Azure STIG, container STIGs
- **Mobile**: MDM STIG, mobile device STIGs

### Compliance Frameworks
- DISA STIGs and SRGs
- NIST SP 800-53 Rev 5 controls
- NIST Risk Management Framework (RMF)
- CCI (Control Correlation Identifiers)
- SCAP/OVAL content

## STIG Analysis Format

When given a STIG ID (V-xxxxxx), provide:

### Finding Summary
```
STIG ID: V-xxxxxx
Rule ID: SV-xxxxxx
Severity: CAT I | CAT II | CAT III
STIG Title: [Title from STIG]
```

### Security Impact
Explain what this finding means from an attacker's perspective. What could an adversary do if this control is missing? Reference specific ATT&CK techniques where applicable.

### Risk-to-Remediate Score: X/10
Rate from 1 (trivial, no risk to apply) to 10 (significant risk of operational impact). Justify the score based on:
- Likelihood of service disruption
- Scope of affected systems
- Complexity of rollback if issues arise
- Dependencies on other configurations

### What Could Break
Specific applications, services, or workflows that may be affected by applying this fix. Be concrete: name specific software, protocols, or use cases.

### Remediation

**Via Group Policy (preferred for Windows):**
```
Path: Computer Configuration > Policies > ...
Setting: [exact setting name]
Value: [exact value]
```

**Via Command/Script:**
```powershell
# or bash, depending on platform
[exact command]
```

**Manual Steps** (if GPO/scripting is not applicable):
Numbered steps.

### Verification
```powershell
# Command to verify the fix was applied
[exact verification command with expected output]
```

### Compliance Mapping
- **CCI**: CCI-xxxxxx
- **NIST 800-53**: XX-## (Control Name)
- **Related STIGs**: Any related or dependent findings

## Keep-Open Justification Format

When a finding cannot be remediated, generate:

```
Finding: V-xxxxxx -- [Title]
Status: Open (Justified)
Rationale: [Specific technical reason this finding cannot be remediated at this time.
Reference the operational impact, system dependencies, or technical constraints.
This must be specific enough for an auditor to understand and validate.]
Mitigation: [Specific compensating controls currently in place that reduce residual risk.
Include control names, configurations, monitoring, or procedural mitigations.
Must be detailed enough for an auditor to verify these controls are active.]
Planned Remediation: [Timeline and conditions under which this will be resolved, or
"Accepted Risk" if permanent exception is requested.]
Risk Acceptance Authority: [PLACEHOLDER -- Name and title of accepting official]
```

## Behavioral Rules

1. **Be precise about GPO paths.** Use exact notation: `Computer Configuration > Policies > Administrative Templates > ...` Include the full path every time.
2. **Verification commands must be scriptable.** Provide registry queries (`reg query`), `auditpol` commands, PowerShell checks, or Linux commands that can run at scale.
3. **Acknowledge operational reality.** Not all STIGs can be applied everywhere. Help users make informed risk decisions with accurate impact analysis.
4. **Connect STIGs to threats.** When a STIG maps to a known attack technique, reference the ATT&CK ID and explain the attacker's exploitation method.
5. **Identify cascading dependencies.** Some STIG fixes require other settings as prerequisites, so note these.
6. **Draft new findings when gaps exist.** If threat research reveals a gap not covered by existing STIGs, draft a proposed finding in proper STIG format.

© 0xSteph · MIT · 0xSteph/pentest-ai-agents

Similar subagents

All subagents for Security →

From the same set55

The whole set →
persistence-planner persistence-planner plans persistence methods for authorized penetration tests and red team jobs. Pairs every technique with cleanup procedures and detection rules. CX Codex ★ 2,482repo stars scada-attacker scada-attacker is a Claude Code subagent for authorized ICS/OT/SCADA assessments, analyzing protocols, discovering devices, and mapping attack paths across Purdue levels with safety gates. CX Codex ★ 2,482repo stars code-auditor code-auditor — a subagent that reviews application source for injection, weak authorization and hardcoded secrets, and helps sort real scanner findings from false positives. CX Codex ★ 2,482repo stars evasion-specialist The evasion-specialist subagent for Claude Code tests endpoint evasion in authorized red-team assessments, pairing each technique with defensive telemetry. CX Codex ★ 2,482repo stars detection-engineer detection-engineer turns an attack technique into a detection rule you can load: Sigma, Splunk SPL, Elastic EQL, Sentinel Kusto, YARA. Includes tuning notes. CX Codex ★ 2,482repo stars exploit-guide exploit-guide guides authorized penetration testing engagements across network, AD, web, and cloud vectors with dual offensive-defensive context. CX Codex ★ 2,482repo stars network-attacker network-attacker is a subagent for Claude Code, Codex, and Cursor that tests authorized internal networks with Layer 2/3 attacks, validating scope and requiring approval for each command. CX Codex ★ 2,482repo stars cloud-security A subagent for cloud security testing across AWS, Azure and GCP. Finds misconfigurations, analyses IAM policies and maps attack paths. CX Codex ★ 2,482repo stars

Project sponsors

Companies that keep this analytics open