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

fix

Skill0 starsChanged 18 days agoMITView on GitHub

Fix a failing Vallorix compliance gap by generating the minimal code change and opening a pull request that references the control it satisfies

82 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use feature, frontend-code-review and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • bradtraversySkill

    feature

    Manage current feature workflow - start, review, explain or complete

    Also in 10 projects that use this

  • chendongqiSkill

    frontend-code-review

    Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`). Support both pending-change reviews and focused file reviews while applying the checklist rules.

    Also in 4 projects that use this

  • GoogleSkill

    pr-creator

    Also in 4 projects that use this

  • PJuniszewskiSkill

    cook

    Feature development with guardrails. Plan → Review → Code → Ship.

    Also in 3 projects that use this

  • vbrevikSkill

    work

    Use when the user says 'plan', 'todo', 'copy plan', 'append plan', 'resume plan', 'priorities', or 'what's next'.

    Also in 4 projects that use this

  • Microsoft AzureSkill

    test

    Also in 12 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 75 edited versions we read keep these.

  • 0

    Distinctive

    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
  1. Very specific:

    Parse the target: If the argument is a URL (e.g.

    line 9
  2. Very specific:

    Close the loop: After merge, remind the user to capture the evidence Vallorix expects (from listMeasureEvidences) and offer to update the …

    line 16
  3. Very specific:

    ID not found: call listMeasures/listFindings, fuzzy-match, present the closest matches ("Did you mean…?").

    line 19

“Common” is measured: kept by at least 6 in 10 of the 75 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

Fix the Vallorix gap identified by the argument (a measure ID, finding ID, or description).

Steps

  1. Parse the target. If the argument is a URL (e.g. https://app.vallorix.ai/.../measures/<id> or .../findings/<id>), extract the ID. Otherwise use it directly. If it's a description, call listMeasures/listFindings and fuzzy-match.
  2. Load remediation context (follow the remediate skill's workflow): getMeasure/getFinding + listMeasureControls + listMeasureEvidences (+ getControl). Ground the fix in the control requirement, never general knowledge.
  3. Scan the repo for the infrastructure/config that governs this control (Terraform, CloudFormation, CDK, Kubernetes/Helm, app config). Fix only the resources tied to the gap.
  4. Generate the minimal change. Make only what's required to satisfy the control. Never weaken a security setting to make a check pass — if that's the only way, stop and tell the user.
  5. Propose, then open a PR. Show the diff, then offer to create a branch and PR. In the PR body include attribution so the mapping is traceable and Vallorix can link the change back to the control: Satisfies: Vallorix <measure|finding> <id> — <control code> (<framework>) e.g. Satisfies: Vallorix measure m_abc123 — CC6.1 (SOC 2).
  6. Close the loop. After merge, remind the user to capture the evidence Vallorix expects (from listMeasureEvidences) and offer to update the item in Vallorix (updateMeasure state → IMPLEMENTED, or updateFinding status → MITIGATED/CLOSED) — with their confirmation.

Edge cases

  • ID not found: call listMeasures/listFindings, fuzzy-match, present the closest matches ("Did you mean…?"). Never dead-end.
  • Already implemented / closed: "This measure is already IMPLEMENTED" (or the finding is CLOSED). Then show the open gaps so the user can pick another (/vallorix:compliance-status).
  • No IaC in this directory: "I have the fix, but I don't see infrastructure code here." Offer: open Claude in the right repo, scaffold the config, or provide CLI steps.
  • IaC present but no matching resource: "Found Terraform, but nothing here manages the resource this control governs." Offer: import + fix, fix elsewhere, or manual steps.
  • Policy/process gap (not code): this isn't a code fix — hand off to /vallorix:remediate for the document/approval/access-review steps.

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