agentleFS
Sign inStart free
BhenderlongBhenderlong/vallorix-mcp-plugin/skills/remediate/SKILL.md

remediate

Skill0 starsChanged 19 days agoMITView on GitHub

Produce a grounded remediation plan for a Vallorix compliance gap (measure or finding), using the real control requirement and evidence context

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. muon-m2/magento2-tools★ 6same name
    2. VoxTechnologies/transmute-framework★ 5same name
    3. inkwell-finance/claude-skills★ 2same 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.

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Always load the real context first: Call getMeasure/getFinding and listMeasureControls before proposing anything.

    line 20
  2. Very specific:

    Never weaken security: Do not disable encryption, remove access controls, open a group to 0.0.0.0/0, drop logging/MFA, or trade security …

    line 21
  3. Very specific:

    Supplement stale guidance with a web search: If the control or finding references an external console/tool/provider, web-search current …

    line 23
  4. Distinctive:

    Say what you can't do: If there's no matching code, say so plainly and give the manual steps + the config to change.

    line 24
  5. Very specific:

    Close the loop in Vallorix: After the fix, name the evidence the user should attach (listMeasureEvidences tells you what's expected) and …

    line 25

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Vallorix Remediation

Help the user close a compliance gap — an unimplemented measure or an open finding — with a plan grounded in what Vallorix actually requires, not generic LLM guesses. All context is pulled from the user's own Vallorix instance.

Key tools (from the Vallorix MCP)

  • getMeasure / getFinding — the gap itself: description, state/status, priority.
  • listMeasureControls — which controls (and frameworks) the measure satisfies. This is the "why" — it tells you the exact requirement the fix must meet.
  • listMeasureEvidences — what evidence currently proves (or fails to prove) the measure, incl. its automation state (FULLY / PARTIALLY / AUTOMATION_READY / MANUAL) and expiry. The fix usually needs to produce or refresh one of these.
  • listMeasureTasks — any tasks already defined for the measure.
  • getControl — the control's framework language, so remediation maps to the actual clause (e.g. SOC 2 CC6.1, ISO 27001 A.8.24).
  • listFindingAudits — history/context for a finding.

Response principles (apply to every remediation)

  1. Always load the real context first. Call getMeasure/getFinding and listMeasureControls before proposing anything. Ground the fix in the control requirement, never in general knowledge alone.
  2. Never weaken security. Do not disable encryption, remove access controls, open a group to 0.0.0.0/0, drop logging/MFA, or trade security for convenience. If a fix seems to require that, stop and flag it.
  3. Minimal change only. Make exactly what's needed to satisfy the control. No refactors, no cleanup.
  4. Supplement stale guidance with a web search. If the control or finding references an external console/tool/provider, web-search current docs — platform guidance ages fast.
  5. Say what you can't do. If there's no matching code, say so plainly and give the manual steps + the config to change.
  6. Close the loop in Vallorix. After the fix, name the evidence the user should attach (listMeasureEvidences tells you what's expected) and offer to update the item: updateMeasure (state → IMPLEMENTED) or updateFinding (status → MITIGATED/CLOSED) — only with the user's confirmation.
  7. Scannable output. Tables for lists, code blocks for diffs/commands, bold for the control it satisfies.
  8. Sovereign by default. Remind the user when relevant: this ran entirely against their Vallorix instance — no evidence or control data left their infrastructure.

Core workflow

  1. Resolve the target. Accept a measure ID, finding ID, or a description. If it's a description, call listMeasures/listFindings and fuzzy-match; if several match, show candidates and ask.
  2. Load context: getMeasure/getFinding + listMeasureControls + listMeasureEvidences (+ getControl for the clause language).
  3. State the requirement in one line: "Control CC6.1 requires encryption at rest on all data stores; this measure is NOT_IMPLEMENTED."
  4. Scan the repo for IaC/config matching the requirement (Terraform/CloudFormation/CDK/K8s/app config).
  5. Produce the plan: the minimal change (diff if code is present), the evidence to capture, and the control/framework it closes.
  6. Offer to apply: /vallorix:fix <id> to generate the PR, or walk the manual steps. Then offer to update the measure/finding state in Vallorix.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free