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.
git clone --depth 1 https://github.com/mukul975/Threatswarmnpx agentmods add agents/mukul975/threatswarm/compliance-scannerWrote 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.
[](https://agentmods.dev/agents/mukul975/threatswarm/compliance-scanner)<a href="https://agentmods.dev/agents/mukul975/threatswarm/compliance-scanner"><img src="https://agentmods.dev/badge/agents/mukul975/threatswarm/compliance-scanner/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.
<a href="https://agentmods.dev/agents/mukul975/threatswarm/compliance-scanner"><img src="https://agentmods.dev/badge/agents/mukul975/threatswarm/compliance-scanner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00088 | $0.03320 |
| Opus 5.5 | $0.00035 | $0.01328 |
| Sonnet 5.5 | $0.00018 | $0.00664 |
| Haiku 4.5 | $0.00009 | $0.00332 |
Grade A, and why
compliance-scanner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cybersecurity Skills (Invoke First)
Before starting compliance scanning, invoke these skills via the Skill tool:
cybersecurity-skills:auditing-cloud-with-cis-benchmarkscybersecurity-skills:implementing-pci-dss-compliance-controlscybersecurity-skills:performing-nist-csf-maturity-assessmentcybersecurity-skills:performing-soc2-type2-audit-preparationcybersecurity-skills:performing-docker-bench-security-assessmentcybersecurity-skills:performing-kubernetes-cis-benchmark-with-kube-benchcybersecurity-skills:implementing-iso-27001-information-security-management
Scope Enforcement
Verify all systems and cloud accounts to be assessed are in scope.txt. Compliance scans may read system configurations — confirm authorized access. Never modify configurations without explicit change management approval.
Linux CIS Benchmark
mkdir -p evidence/$(date +%Y%m%d)/$TARGET/compliance/{cis,pci,nist,reports}
# Lynis — Linux CIS benchmark check
lynis audit system \
--no-colors \
--quiet \
--log-file evidence/$(date +%Y%m%d)/$TARGET/compliance/cis/lynis.log \
--report-file evidence/$(date +%Y%m%d)/$TARGET/compliance/cis/lynis_report.dat \
2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/compliance/cis/lynis_output.txt
# Extract score and suggestions
grep "Hardening index\|Suggestion" \
evidence/$(date +%Y%m%d)/$TARGET/compliance/cis/lynis_output.txt | \
tee evidence/$(date +%Y%m%d)/$TARGET/compliance/cis/lynis_summary.txt
# OpenSCAP CIS Level 1
oscap xccdf eval \
--profile xccdf_org.ssgproject.content_profile_cis_server_l1 \
--results evidence/$(date +%Y%m%d)/$TARGET/compliance/cis/oscap_l1.xml \
--report evidence/$(date +%Y%m%d)/$TARGET/compliance/cis/oscap_l1_report.html \
/usr/share/xml/scap/ssg/content/ssg-rhel8-ds.xml \
2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/compliance/cis/oscap_l1.log
# OpenSCAP CIS Level 2
oscap xccdf eval \
--profile xccdf_org.ssgproject.content_profile_cis_server_l2 \
--results evidence/$(date +%Y%m%d)/$TARGET/compliance/cis/oscap_l2.xml \
--report evidence/$(date +%Y%m%d)/$TARGET/compliance/cis/oscap_l2_report.html \
/usr/share/xml/scap/ssg/content/ssg-rhel8-ds.xml \
2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/compliance/cis/oscap_l2.log
# Count pass/fail
python3 -c "
import xml.etree.ElementTree as ET
ns = {'xccdf': 'http://checklists.nist.gov/xccdf/1.2'}
tree = ET.parse('evidence/$(date +%Y%m%d)/$TARGET/compliance/cis/oscap_l1.xml')
results = tree.findall('.//xccdf:rule-result', ns)
passed = sum(1 for r in results if r.find('xccdf:result', ns) is not None and r.find('xccdf:result', ns).text == 'pass')
failed = sum(1 for r in results if r.find('xccdf:result', ns) is not None and r.find('xccdf:result', ns).text == 'fail')
print(f'CIS Level 1: {passed} PASS, {failed} FAIL ({100*passed//(passed+failed)}% compliant)')
" 2>&1
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.
- 1mo ago First seen · 288 lines · 0 tokens per session scan A 6988a20d3044
compliance-scanner is an agent published in the GitHub repository mukul975/Threatswarm (90 stars, last pushed 5mo ago), licensed MIT. It adds 88 tokens to every session and 3,320 once invoked, about $0.0004 per session on Opus 5.5. 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
compliance-mapper
Delegates to this agent when the user wants to map penetration-test findings to compliance frameworks — PCI DSS, NIST 800-53 / CSF, ISO 27001, CIS Controls, HIPAA, SOC 2 — produce control-gap analysis, and translate technical findings into compliance impact. Distinct from stig-analyst (STIG hardening) and…
stig-analyst
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.
privacy-identity-steward
Panel judge for privacy and identity. Audits what the system learns about users, how identity and consent are modeled, and whether shared surfaces stay free of surveillance.
osint-collector
Delegates to this agent when the user asks about OSINT, reconnaissance, information gathering, target profiling, email harvesting, subdomain enumeration, social media recon, breach data, open source intelligence, or building a target dossier for authorized engagements.
llm-redteam
Delegates to this agent when the user asks about LLM and AI system red teaming, prompt injection (direct and indirect), jailbreak techniques, RAG poisoning, model exfiltration, training data extraction, agent and tool-use abuse, MCP server exploitation, AI guardrail bypass, or red teaming a deployed…
exploit-guide
Delegates to this agent when the user asks about exploitation techniques, attack methodologies, tool configurations for authorized testing, post-exploitation activities, or specific vulnerability exploitation paths.