DevOps & Security Agent Skills is a knowledge base of agent-readable skills covering software delivery, cloud infrastructure, security, compliance, AI operations, and incident response. It is for SRE, platform, infrastructure, and security teams using agents to work with systems such as Kubernetes, Terraform, and major cloud platforms. The catalogue provides a selection of the project's skills for agents including Claude Code, Cursor, and Codex.
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 soc2-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/soc2-compliance)<a href="https://agentmods.dev/skills/bagelhole/devops-security-agent-skills/soc2-compliance"><img src="https://agentmods.dev/badge/skills/bagelhole/devops-security-agent-skills/soc2-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/soc2-compliance"><img src="https://agentmods.dev/badge/skills/bagelhole/devops-security-agent-skills/soc2-compliance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.03276 |
| Opus 5.5 | $0.00012 | $0.01310 |
| Sonnet 5.5 | $0.00006 | $0.00655 |
| Haiku 4.5 | $0.00003 | $0.00328 |
Grade A, and why
soc2-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 2mo 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 — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SOC 2 Compliance
Implement SOC 2 Trust Services Criteria controls, evidence collection, and continuous compliance monitoring for Type I and Type II audits.
When to Use
- Preparing for a SOC 2 Type I or Type II audit
- Mapping existing controls to Trust Services Criteria
- Automating evidence collection for auditor requests
- Building continuous compliance monitoring into CI/CD
- Onboarding new services and ensuring SOC 2 control coverage
Trust Services Criteria Detailed Checklist
security_common_criteria:
CC1_control_environment:
CC1.1: "Management demonstrates commitment to integrity and ethical values"
CC1.2: "Board exercises oversight of internal controls"
CC1.3: "Management establishes structure, authority, and responsibility"
CC1.4: "Commitment to competence - hire and retain qualified personnel"
CC1.5: "Individuals are held accountable for internal control responsibilities"
evidence:
- Code of conduct document
- Organizational chart
- Job descriptions with security responsibilities
- Board meeting minutes discussing security
- Background check policy and records
CC2_communication:
CC2.1: "Entity obtains or generates relevant quality information"
CC2.2: "Entity internally communicates information including objectives and responsibilities"
CC2.3: "Entity communicates with external parties"
evidence:
- Security awareness training records
- Internal security newsletters or updates
- Customer-facing security documentation
- Status page and incident communication records
CC3_risk_assessment:
CC3.1: "Entity specifies objectives clearly to identify and assess risks"
CC3.2: "Entity identifies risks to achievement of objectives"
CC3.3: "Entity considers potential for fraud"
CC3.4: "Entity identifies and assesses significant changes"
evidence:
- Annual risk assessment report
- Risk register with ratings and treatment plans
- Fraud risk assessment documentation
- Change management records
CC4_monitoring:
CC4.1: "Entity selects, develops, and performs ongoing/separate evaluations"
CC4.2: "Entity evaluates and communicates internal control deficiencies"
evidence:
- Continuous monitoring dashboard screenshots
- Internal audit reports
- Vulnerability scan results
- Penetration test reports
CC5_control_activities:
CC5.1: "Entity selects and develops control activities to mitigate risks"
CC5.2: "Entity selects and develops technology-based controls"
CC5.3: "Entity deploys control activities through policies and procedures"
evidence:
- Information security policy
- Access control procedures
- Change management procedures
- Encryption standards documentation
CC6_logical_access:
CC6.1: "Logical access security over protected information assets"
CC6.2: "Prior to access, users are registered and authorized"
CC6.3: "Access to data, software, functions, and other IT resources is authorized and modified"
CC6.6: "Logical access security measures against threats from outside system boundaries"
CC6.7: "Transmission of data between parties is protected"
CC6.8: "Controls to prevent or detect unauthorized or malicious software"
evidence:
- IAM credential report
- MFA enforcement configuration
- Access review completion records
- Firewall and WAF configurations
- TLS/encryption configurations
- Endpoint protection deployment records
CC7_system_operations:
CC7.1: "Detect anomalies and potential security incidents"
CC7.2: "Monitor system components for anomalies"
CC7.3: "Evaluate detected events and determine incidents"
CC7.4: "Respond to identified security incidents"
CC7.5: "Identify and remediate security incidents"
evidence:
- SIEM alert rules and dashboards
- Monitoring configuration (CloudWatch, Datadog, etc.)
- Incident response plan
- Incident tickets and post-mortems
CC8_change_management:
CC8.1: "Entity authorizes, designs, develops, configures, documents, tests, approves, and implements changes"
evidence:
- Change management policy
- Pull request approval requirements
- CI/CD pipeline configurations
- Deployment records with approvals
CC9_risk_mitigation:
CC9.1: "Entity identifies, selects, and develops risk mitigation activities"
CC9.2: "Entity assesses and manages risks associated with vendors"
evidence:
- Risk treatment plans
- Vendor assessment records
- Business associate agreements
- Insurance certificates
availability_criteria:
A1.1: "System processing capacity and availability are maintained"
A1.2: "Environmental protections and recovery measures"
A1.3: "Recovery plan procedures to support system availability"
evidence:
- Uptime SLA documentation
- Capacity monitoring dashboards
- Disaster recovery plan
- DR test results
- Backup verification records
processing_integrity_criteria:
PI1.1: "Entity obtains or generates, uses, and communicates quality information"
evidence:
- Input validation procedures
- Data processing accuracy checks
- Error handling and retry logic documentation
- Output reconciliation records
confidentiality_criteria:
C1.1: "Entity identifies and maintains confidential information"
C1.2: "Entity disposes of confidential information"
evidence:
- Data classification policy
- Encryption configurations
- Data retention and destruction policies
- Secure disposal records
privacy_criteria:
P1-P8: "Privacy notice, choice, collection, use, disclosure, access, quality, monitoring"
evidence:
- Privacy policy (published)
- Consent management records
- Data processing inventory
- DSAR handling procedures
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.
- 2mo ago First seen · 387 lines · 31 tokens per session scan A 2c9b25948cac
soc2-compliance is a skill published in the GitHub repository BagelHole/DevOps-Security-Agent-Skills (1,196 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 3,276 once invoked, about $0.0001 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.
soc2-compliance compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| soc2-complianceBagelHole/DevOps-Security-Agent-Skills | Skill | 1.2k | 5mo ago | MIT | A | 31 | Claude Code, Codex |
| complianceericrisco/rsc-harness | Skill | 529 | 4d ago | MIT | A | 96 | Claude Code, Codex |
| cmmc-assessment-objectivesGRCEngClub/claude-grc-engineering | Skill | 430 | today | none | A | 80 | Claude Code |
| eu-nis2-expertGRCEngClub/claude-grc-engineering | Skill | 430 | today | none | A | 90 | Claude Code |
| gdpr-expertGRCEngClub/claude-grc-engineering | Skill | 430 | today | none | A | 55 | Claude Code |
| glba-expertGRCEngClub/claude-grc-engineering | Skill | 430 | today | none | A | 58 | Claude Code |
| stateramp-expertGRCEngClub/claude-grc-engineering | Skill | 430 | today | none | A | 58 | Claude Code |