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 skills add BagelHole/DevOps-Security-Agent-Skills --skill fedramp-compliancegit clone --depth 1 https://github.com/BagelHole/DevOps-Security-Agent-SkillsWrote 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/skills/bagelhole/devops-security-agent-skills/fedramp-compliance)<a href="https://agentmods.dev/skills/bagelhole/devops-security-agent-skills/fedramp-compliance"><img src="https://agentmods.dev/badge/skills/bagelhole/devops-security-agent-skills/fedramp-compliance/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/skills/bagelhole/devops-security-agent-skills/fedramp-compliance"><img src="https://agentmods.dev/badge/skills/bagelhole/devops-security-agent-skills/fedramp-compliance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 366 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00038 | $0.03690 |
| Opus 5 | $0.00019 | $0.01845 |
| Sonnet 5 | $0.00008 | $0.00738 |
| Haiku 4.5 | $0.00004 | $0.00369 |
Grade A, and why
fedramp-compliance 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 12d 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 — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FedRAMP Compliance
Implement FedRAMP (Federal Risk and Authorization Management Program) requirements for cloud service providers serving US federal agencies.
When to Use
- Pursuing FedRAMP authorization for a cloud service offering
- Implementing NIST 800-53 security controls for federal workloads
- Establishing continuous monitoring (ConMon) processes
- Managing Plan of Action and Milestones (POA&M) tracking
- Preparing for a Third-Party Assessment Organization (3PAO) audit
- Operating a FedRAMP-authorized system and maintaining authorization
Impact Levels
impact_levels:
low:
control_count: ~125
use_case: "Publicly available federal information"
examples:
- Public-facing websites with no sensitive data
- Open data portals
- Marketing and informational systems
data_types: "No PII, no CUI, publicly releasable only"
authorization_path: "FedRAMP Tailored (Li-SaaS) or standard Low"
moderate:
control_count: ~325
use_case: "Most federal systems, including CUI"
examples:
- Email and collaboration platforms
- Case management systems
- Financial management systems
- HR and personnel systems
data_types: "CUI, PII, law enforcement sensitive (LES)"
authorization_path: "Agency or JAB P-ATO"
note: "~80% of FedRAMP authorizations are at Moderate"
high:
control_count: ~425
use_case: "High-impact federal systems"
examples:
- Law enforcement and criminal justice systems
- Emergency services and public safety
- Financial systems with significant impact
- Healthcare systems with PHI
data_types: "Classified-adjacent, life-safety, critical infrastructure"
authorization_path: "JAB P-ATO required"
NIST 800-53 Control Families
control_families:
AC:
name: "Access Control"
key_controls:
AC-2: "Account Management - manage system accounts lifecycle"
AC-3: "Access Enforcement - enforce approved authorizations"
AC-6: "Least Privilege - employ principle of least privilege"
AC-17: "Remote Access - establish usage restrictions for remote access"
implementation_notes: "Map to IAM policies, RBAC, MFA enforcement"
AU:
name: "Audit and Accountability"
key_controls:
AU-2: "Audit Events - define auditable events"
AU-3: "Content of Audit Records - ensure records contain required info"
AU-6: "Audit Review, Analysis, and Reporting"
AU-12: "Audit Generation - generate audit records"
implementation_notes: "Map to CloudTrail, CloudWatch Logs, SIEM"
AT:
name: "Awareness and Training"
key_controls:
AT-2: "Security Awareness Training - provide training to users"
AT-3: "Role-Based Security Training - for personnel with security roles"
implementation_notes: "Annual security training, role-specific training"
CM:
name: "Configuration Management"
key_controls:
CM-2: "Baseline Configuration - develop and maintain baseline"
CM-6: "Configuration Settings - establish mandatory settings"
CM-7: "Least Functionality - restrict to essential capabilities"
CM-8: "Information System Component Inventory"
implementation_notes: "Map to AWS Config, SSM, hardened AMIs"
CP:
name: "Contingency Planning"
key_controls:
CP-2: "Contingency Plan - develop and maintain plan"
CP-4: "Contingency Plan Testing - test plan annually"
CP-9: "Information System Backup"
CP-10: "Information System Recovery and Reconstitution"
implementation_notes: "Map to DR plan, backup strategy, failover testing"
IA:
name: "Identification and Authentication"
key_controls:
IA-2: "Identification and Authentication (Org Users)"
IA-5: "Authenticator Management"
IA-8: "Identification and Authentication (Non-Org Users)"
implementation_notes: "Map to SSO, MFA, certificate-based auth, PIV/CAC"
IR:
name: "Incident Response"
key_controls:
IR-2: "Incident Response Training"
IR-4: "Incident Handling - implement incident handling capability"
IR-6: "Incident Reporting - report incidents to US-CERT"
IR-8: "Incident Response Plan"
implementation_notes: "US-CERT reporting within 1 hour for federal incidents"
MA:
name: "Maintenance"
key_controls:
MA-2: "Controlled Maintenance"
MA-4: "Nonlocal Maintenance - authorize nonlocal maintenance"
implementation_notes: "Patching procedures, remote maintenance controls"
MP:
name: "Media Protection"
key_controls:
MP-2: "Media Access - restrict access to media"
MP-6: "Media Sanitization - sanitize media prior to disposal"
implementation_notes: "Encryption at rest, secure disposal procedures"
PE:
name: "Physical and Environmental Protection"
key_controls:
PE-2: "Physical Access Authorizations"
PE-3: "Physical Access Control"
PE-6: "Monitoring Physical Access"
implementation_notes: "Inherit from CSP for IaaS/PaaS, document inheritance"
PL:
name: "Planning"
key_controls:
PL-2: "System Security Plan (SSP)"
implementation_notes: "SSP is the core FedRAMP deliverable"
PS:
name: "Personnel Security"
key_controls:
PS-3: "Personnel Screening"
PS-4: "Personnel Termination"
PS-5: "Personnel Transfer"
implementation_notes: "Background checks, access revocation on termination"
RA:
name: "Risk Assessment"
key_controls:
RA-3: "Risk Assessment - conduct risk assessment"
RA-5: "Vulnerability Scanning"
implementation_notes: "Annual risk assessment, monthly vulnerability scans"
CA:
name: "Security Assessment and Authorization"
key_controls:
CA-2: "Security Assessments"
CA-6: "Security Authorization"
CA-7: "Continuous Monitoring"
implementation_notes: "Annual assessment by 3PAO, ConMon program"
SC:
name: "System and Communications Protection"
key_controls:
SC-7: "Boundary Protection"
SC-8: "Transmission Confidentiality and Integrity"
SC-12: "Cryptographic Key Establishment and Management"
SC-13: "Cryptographic Protection - FIPS 140-2 validated"
SC-28: "Protection of Information at Rest"
implementation_notes: "FIPS 140-2 validated modules required"
SI:
name: "System and Information Integrity"
key_controls:
SI-2: "Flaw Remediation"
SI-3: "Malicious Code Protection"
SI-4: "Information System Monitoring"
SI-5: "Security Alerts, Advisories, and Directives"
implementation_notes: "Patching SLAs, antimalware, IDS/IPS, SIEM"
SA:
name: "System and Services Acquisition"
key_controls:
SA-4: "Acquisition Process - security requirements in contracts"
SA-9: "External Information System Services"
SA-11: "Developer Security Testing"
implementation_notes: "Supply chain risk management, SBOM"
PM:
name: "Program Management"
key_controls:
PM-1: "Information Security Program Plan"
PM-9: "Risk Management Strategy"
implementation_notes: "Organization-wide security program"
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.
- 12d ago First seen · 430 lines · 38 tokens per session scan A d1c4c957ce00
fedramp-compliance is a skill published in the GitHub repository BagelHole/DevOps-Security-Agent-Skills (1,084 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 3,690 once invoked, about $0.0002 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 skills, from other repositories
performing-soc2-type2-audit-preparation
Automates SOC 2 Type II audit preparation including gap assessment against AICPA Trust Services Criteria (CC1-CC9), evidence collection from cloud providers and identity systems, control testing validation, remediation tracking, and continuous compliance monitoring. Covers all five TSC categories (Security…
eu-nis2-expert
EU NIS2 Directive (Directive (EU) 2022/2555) expert. Reference-depth knowledge of essential vs important entity classification, Article 20 governance, the Article 21 ten cybersecurity risk-management measures, the Article 23 24h/72h/1mo incident-reporting timeline, and supervision/enforcement under Articles 32-34.…
gdpr-expert
GDPR expert for EU privacy compliance. Deep knowledge of General Data Protection Regulation including 99 articles, 7 principles, 6 lawful bases, data subject rights, DPO requirements, DPIA, breach notification, cross-border transfers, and enforcement.
glba-expert
GLBA expert for financial institutions. Deep knowledge of Gramm-Leach-Bliley Act including Safeguards Rule (16 CFR Part 314), Privacy Rule (16 CFR Part 313), FTC enforcement, information security program requirements, vendor management, and consumer privacy notices.
stateramp-expert
StateRAMP expert for state and local government cloud services. Deep knowledge of State Risk and Authorization Management Program including Low/Moderate impact levels, NIST 800-53 controls, state-specific requirements, FedRAMP alignment, and multi-state authorization strategies.
us-export-expert
US Export Controls expert covering ITAR and EAR. Provides comprehensive guidance on defense articles (USML), dual-use commercial items (CCL), jurisdiction determination, FIPS encryption, denied party screening, and cloud compliance strategies.