compliance-status
Skill0 starsChanged 19 days agoMITView on GitHub
Show the user's open compliance gaps (unimplemented measures + open findings), prioritized by what can be fixed from this repository
1 other project uses a version of this.
Adopted by
Most recently taken up by
- njt2810/claude-code-frameworktheir own version, first seen Sep 10, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- njt2810/claude-code-framework★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- evidence-checkSkill
- fixSkill
- framework-readinessSkill
- remediateSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Call listMeasures and keep the ones whose state is not IMPLEMENTED and not NOT_APPLICABLE — i.e.
- Very specific: line 11
Call listFindings and keep status OPEN or IN_PROGRESS.
- Very specific: line 12
Call listFrameworks so you can label each gap with the framework(s) it affects (SOC 2, ISO 27001, HIPAA, CMMC, …).
- Distinctive: line 25
Highlight cross-framework clusters: If one measure unblocks multiple frameworks, call it out: "Implementing *Encryption at rest* closes …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Show the user where they are out of compliance, ranked by what this plugin can help fix. Everything here runs against the user's own Vallorix instance (the VALLORIX_MCP_URL — self-hosted or app.vallorix.ai); their evidence never leaves their boundary.
Steps
- Fetch the gaps. In parallel:
- Call
listMeasuresand keep the ones whosestateis notIMPLEMENTEDand notNOT_APPLICABLE— i.e.NOT_STARTED,IN_PROGRESS,NOT_IMPLEMENTED,UNKNOWN. These are the control-implementation items still open. - Call
listFindingsand keepstatusOPENorIN_PROGRESS. Note each finding'spriority(HIGH/MEDIUM/LOW) andkind(MAJOR_NONCONFORMITY / MINOR_NONCONFORMITY / OBSERVATION / EXCEPTION). - Call
listFrameworksso you can label each gap with the framework(s) it affects (SOC 2, ISO 27001, HIPAA, CMMC, …).
- Call
- Map gaps to frameworks. For the top candidate measures, call
listMeasureControlsto see which controls (and therefore frameworks) each measure satisfies. A single unimplemented measure often blocks several frameworks at once — surface that. - Categorize into fix-tiers (mirror of how an engineer actually works):
Ready to fix from this repo — the gap maps to infrastructure this repository manages. Detect deployment code:
provider "aws"/aws_*in.tf,provider "google"/google_*,provider "azurerm"/azurerm_*,AWSTemplateFormatVersion(CloudFormation),cdk.json(CDK),Dockerfile/k8s/helmmanifests, or app config/code matching the control (e.g. a measure about "enforce MFA" when an IdP/Terraform config is present). Use multiple signals. Present these first — one command:/vallorix:fix <measureId|findingId>. Fixable with guidance — code-remediable but the matching code isn't in this repo (different system/provider). Offer/vallorix:remediate <id>for a grounded plan. Policy / process / manual — needs a document, an approval, an access review, or a config change in another tool. The plugin gives guidance, not code. - Present results — scannable, no raw API dumps. For each tier, a table:
- Gap (measure name or finding title)
- ID
- Type (Measure / Finding)
- Priority / state (HIGH finding, or
NOT_STARTEDmeasure) - Framework(s) affected
- For "Ready to fix":
Run /vallorix:fix <id>
- Highlight cross-framework clusters. If one measure unblocks multiple frameworks, call it out: "Implementing Encryption at rest closes gaps in SOC 2 CC6.1, ISO 27001 A.8.24, and HIPAA §164.312 at once — best bang for the buck."
- End with a clear next step: "Want me to fix the top one?" or "Run
/vallorix:framework-readinessto see how close you are to a specific framework."
Edge cases
- No open gaps: "No open findings and all measures are implemented. Nice posture." Don't show an empty table.
- Filter by framework ("show SOC 2 gaps"): resolve the framework via
listFrameworks/getFramework, then filter measures/findings to those mapped to it. - Filter by system ("show AWS gaps"): filter to gaps whose controls/measures reference that integration; if none match, say so and show the full list.
- "What should I fix first?": rank by (1) IaC-fixable in this repo, (2) HIGH-priority / MAJOR_NONCONFORMITY, (3) cross-framework clusters, (4) how long it's been open. Lead with the cluster that closes the most framework requirements.
- Very many gaps: group by framework and summarize counts; show the top 5–10 highest-impact items with "[N] more — want the full list or a specific framework?"
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

