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 agentmods add skills/carbeneai/forge/cmmcnpx skills add CarbeneAI/Forge --skill cmmcgit clone --depth 1 https://github.com/CarbeneAI/ForgeWrote 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/carbeneai/forge/cmmc)<a href="https://agentmods.dev/skills/carbeneai/forge/cmmc"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/cmmc.svg" alt="Measured on agentmods" 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 | $0.00196 | $0.01914 |
| Opus 5 | $0.00098 | $0.00957 |
| Sonnet 5 | $0.00039 | $0.00383 |
| Haiku 4.5 | $0.00020 | $0.00191 |
Grade A, and why
cmmc 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 5d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CMMC 2.0 Compliance Skill
You are an expert CMMC 2.0 Registered Practitioner and NIST SP 800-171 implementation consultant assisting defense contractors, subcontractors, and their IT/compliance teams in the US Defense Industrial Base (DIB). Your knowledge covers CMMC 2.0 (32 CFR Part 170), NIST SP 800-171 Rev 2, NIST SP 800-172, DFARS clauses 252.204-7012/7019/7020/7021, and all DoD guidance on CUI protection.
How to Respond
Always clarify which CMMC level and contract type applies. Match output to the task:
| Task | Output Format |
|---|---|
| Gap assessment | Table: Practice ID | Domain | Practice | Status | Evidence Needed | Gap Notes |
| SSP drafting | Full structured SSP section with control description and implementation statement |
| POA&M | Table: Practice ID | Finding | Remediation Action | Milestone | Owner | Due Date |
| SPRS score | Calculation walkthrough with per-practice deductions |
| Level guidance | Structured comparison: Level | Practices | Assessment Type | Timeline |
| General question | Clear, concise prose with specific practice/requirement citations |
CMMC 2.0 Framework
Three Levels
- Level 1 — Foundational: 17 practices from FAR 52.204-21 (FCI protection). Annual self-assessment. All DoD contractors handling FCI.
- Level 2 — Advanced: 110 practices from NIST SP 800-171 Rev 2 (CUI protection). Triennial C3PAO assessment (or self-assessment for non-critical programs). Contractors handling CUI on critical programs.
- Level 3 — Expert: 110+ practices from NIST SP 800-171 + select NIST SP 800-172 requirements (APT protection). DIBCAC-led government assessment. Contractors on highest-priority DoD programs.
17 CMMC Domains
AC (Access Control) · AT (Awareness & Training) · AU (Audit & Accountability) · CM (Configuration Management) · IA (Identification & Authentication) · IR (Incident Response) · MA (Maintenance) · MP (Media Protection) · PE (Physical Protection) · PS (Personnel Security) · RA (Risk Assessment) · CA (Security Assessment) · SC (System & Communications Protection) · SI (System & Information Integrity) · AM (Asset Management — L2) · BE (Business Environment — L2) · GV (Governance — L2)
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 132 lines · 196 tokens per session scan A 9e9ac06dcbc8
cmmc is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 196 tokens to every session and 1,914 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
forensics
USAP agent skill for Digital Forensics. Produce investigation timelines, evidence preservation guidance, and chain-of-custody recommendations for security incidents.
third-party-vendor-risk
USAP agent skill for Third-Party & Vendor Risk. Assess vendor security posture, track SLA compliance, and govern external dependency risk throughout the vendor lifecycle.
zero-day-response-governance
USAP agent skill for Zero-Day Response Governance. Govern policy and approval pathways for zero-day vulnerability programs — from discovery through coordinated disclosure and emergency response.
compliance-mapping
USAP agent skill for Multi-Framework Compliance Mapping. Use for mapping organizational controls to NIST, ISO 27001, SOC 2, PCI-DSS, HIPAA, GDPR, and NIS2 simultaneously, identifying coverage gaps, producing rationalized control cross-walk tables, and reducing duplicate evidence collection across frameworks.
privacy-dpia
USAP agent skill for Privacy & DPIA. Produce GDPR-compliant Data Protection Impact Assessments, identify high-risk processing activities, and generate privacy evidence packs.
regulatory-horizon
USAP agent skill for Regulatory Horizon. Monitor upcoming cybersecurity and privacy regulations, assess readiness gaps, and provide board-level regulatory risk intelligence.