Cmmc Assessment Objectives
320 verbatim NIST 800-171A Rev 2 assessment objectives plus a Rev 2 to Rev 3 crosswalk
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 21, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · b9b48d9
Cloned the repo and installed into an isolated temp HOME; SKILL.md landed at ~/.claude/skills/cmmc-assessment-objectives/SKILL.md, frontmatter parsed via yaml.safe_load to name+description+allowed-tools, no hardcoded /Users or /home paths, no scripts or external file references, and no curl|sh, base64, credential or prompt-injection patterns. I script-counted the body: 110 control lines and 320 lettered objective lines, and all 14 per-family counts matched the skill's own header table exactly. Output test (both artifacts in scratchpad: cmmcao_baseline.md vs cmmcao_skill.md) was an objective-level Satisfied/Other-Than-Satisfied table for 3.12.4 and 3.7.5 — the baseline reconstructed 6 objectives for 3.12.4 and hedged "roughly 6", while the file has 8, and the two the baseline missed ([d] non-applicable requirements identified, and the split of [g] frequency-defined from [h] updated-at-that-frequency) are precisely the ones the scenario fails, so the baseline under-reported the POA&M scope; the baseline also dropped "via external network connections" from 3.7.5[b]. Docs lose a point for two contradictory rows: the MP crosswalk maps 3.8.8 to 03.08.06 "into 03.08.05" while the Quick Reference Withdrawn table says 03.08.08 "into 03.08.07" (same conflict for 3.8.6), plus a hardcoded "As of 2026-05-17" and a plugin.json calling CMMC 2.0 a 5-level model; the skill is otherwise unusually honest, flagging 11 of 14 crosswalk families as training-knowledge rather than PDF-verified.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 4/5
What Cmmc Assessment Objectives does
A single self-contained reference file carrying the full text of all 320 NIST SP 800-171A Rev 2 assessment objectives, indexed by control ID down to the lettered scoreable unit (3.1.1[c], 3.12.4[g]), together with a Rev 2 to Rev 3 control crosswalk, a withdrawn-controls table, and Examine/Interview/Test method definitions. Triggers on objective-level CMMC Level 2 lookups, evidence and POA&M planning, and questions about where a Rev 2 control lands in 800-171 Rev 3. Program-level CMMC topics such as SPRS scoring and scoping are deliberately routed to the companion cmmc-expert skill.
How to install Cmmc Assessment Objectives
git clone --depth 1 https://github.com/GRCEngClub/claude-grc-engineering.git /tmp/cmmc-assessment-objectives-src
mkdir -p ~/.claude/skills
cp -R /tmp/cmmc-assessment-objectives-src/plugins/frameworks/cmmc/skills/cmmc-assessment-objectives ~/.claude/skills/cmmc-assessment-objectives
# No dependencies, no API keys, no scripts. One self-contained 72KB SKILL.md.
# frontmatter: allowed-tools: Read, Glob, Grep, Write
# The body cross-references a companion skill for program-level CMMC topics
# (SPRS scoring, POA&M rules, scoping, C3PAO lifecycle). Install it too:
# cp -R /tmp/cmmc-assessment-objectives-src/plugins/frameworks/cmmc/skills/cmmc-expert ~/.claude/skills/cmmc-expert
# Plugin-marketplace alternative: the repo ships .claude-plugin/marketplace.json
# ("grc-engineering-suite") with a "cmmc" plugin at ./plugins/frameworks/cmmc
# that bundles both skills plus 5 slash commands (assess, level-select,
# practice-check, domain-guidance, evidence-checklist).
# Note: 72KB loads into context on trigger — heavy but functional.
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Cmmc Assessment Objectives
-
/cmmc-assessment-objectives320 verbatim NIST 800-171A Rev 2 assessment objectives plus a Rev 2 to Rev 3 crosswalk
It also activates on plain-language prompts like these:
-
Look up assessment objective 3.1.1[c] -
Map this Rev 2 control to Rev 3 -
Plan evidence for this CMMC assessment objective
Frequently asked questions
- Is the Cmmc Assessment Objectives skill free?
- Yes. The skill itself is free from GRCEngClub/claude-grc-engineering. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Cmmc Assessment Objectives work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Cloned the repo and installed into an isolated temp HOME; SKILL.md landed at ~/.claude/skills/cmmc-assessment-objectives/SKILL.md, frontmatter parsed via yaml.safe_load to name+description+allowed-tools, no hardcoded /Users or /home paths, no scripts or external file references, and no curl|sh, base64, credential or prompt-injection patterns. I script-counted the body: 110 control lines and 320 lettered objective lines, and all 14 per-family counts matched the skill's own header table exactly. Output test (both artifacts in scratchpad: cmmcao_baseline.md vs cmmcao_skill.md) was an objective-level Satisfied/Other-Than-Satisfied table for 3.12.4 and 3.7.5 — the baseline reconstructed 6 objectives for 3.12.4 and hedged "roughly 6", while the file has 8, and the two the baseline missed ([d] non-applicable requirements identified, and the split of [g] frequency-defined from [h] updated-at-that-frequency) are precisely the ones the scenario fails, so the baseline under-reported the POA&M scope; the baseline also dropped "via external network connections" from 3.7.5[b]. Docs lose a point for two contradictory rows: the MP crosswalk maps 3.8.8 to 03.08.06 "into 03.08.05" while the Quick Reference Withdrawn table says 03.08.08 "into 03.08.07" (same conflict for 3.8.6), plus a hardcoded "As of 2026-05-17" and a plugin.json calling CMMC 2.0 a 5-level model; the skill is otherwise unusually honest, flagging 11 of 14 crosswalk families as training-knowledge rather than PDF-verified.
- What is the Cmmc Assessment Objectives SkillProof Score?
- 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
- How do I install Cmmc Assessment Objectives?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Cmmc Assessment Objectives with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.