megalinter
01Plugin Claude Code
MegaLinter agent plugin: set up, run and fix MegaLinter from your coding agent.
Plugin Claude Code
MegaLinter agent plugin: set up, run and fix MegaLinter from your coding agent.
Plugin Claude Code
Set up, run and fix MegaLinter on any repository: 100+ linters for 69+ languages, 23+ formats and 21+ tooling formats, from CI or locally.
Agent Claude Code
Gather requirements for a MegaLinter change by asking clarifying questions until the problem is fully understood. Use before designing or implementing any change.
Agent Claude Code
Run and troubleshoot the MegaLinter build system that generates Dockerfiles, documentation, test classes, and schemas from YAML descriptors.
Agent Claude Code
Review MegaLinter Python code changes for quality, conventions, and correctness. Use after writing or modifying Python code in the megalinter package.
Agent Claude Code
Specialist for creating, editing, and validating MegaLinter YAML descriptor files. Use when working on linter descriptors, adding new linters, or modifying linter configurations.
Agent Claude Code
Design a MegaLinter solution and write a technical specification based on requirements analysis. Use after /analyze.
Agent Claude Code
Implement MegaLinter code changes following a technical specification or direct request. Use after /design, or directly for small focused changes.
Agent Claude Code
Poll a GitHub PR's CI status, classify failed jobs, and fetch the relevant log excerpts. Use to gather data about a PR's check state — does NOT decide fixes or edit code.
Agent Claude Code
Analyze a CVE or vulnerability finding (from trivy, osv-scanner, grype, etc.) to determine whether it applies to MegaLinter, the right remediation (upgrade vs. ignore), and the justification. Use when judgment calls on safety, exploitability, or scope are required.
Agent Claude Code
Debug failing MegaLinter linter tests. Use when tests fail, test fixtures need fixing, or Docker-based test execution needs troubleshooting.
Agent Claude Code
Build, lint, and run MegaLinter tests inside Docker to verify the implementation. Use after /implement.
Agent Claude Code
Mechanically bump a pinned tool/linter version in a YAML descriptor or Dockerfile ARG. Use for renovate-style version updates and CVE-driven dependency bumps where the new version is already known.
Settings file Claude Code
Agent settings declaring 12 allowed tools.
Skill Claude CodeCodex
Add a new MegaLinter flavor (language-specific Docker image). Use when creating a new specialized Docker image variant.
Skill Claude CodeCodex
Guided workflow for adding a new linter to MegaLinter. Use when a contributor needs to add support for a new linting tool.
Skill Claude CodeCodex
Add a new output reporter to MegaLinter. Use when adding support for a new CI system or output format.
Skill Claude CodeCodex
Gather requirements for a MegaLinter change by asking clarifying questions until the problem is fully understood. First step of the contribution workflow.
Skill Claude CodeCodex
Manage Datadog dashboards including listing, viewing, creating, updating, and deleting dashboards with their widgets and configurations. Official Datadog content, vendored from https://github.com/DataDog/datadog-api-claude-plugin (agents/dashboards.md), Apache-2.0.
Skill Claude CodeCodex
Design a MegaLinter solution and write a technical specification. Second step of the contribution workflow, use after /analyze.
Skill Claude CodeCodex
Diagnose MegaLinter .mega-linter.yml configuration issues. Use when linters aren't running as expected or configuration seems wrong.
Skill Claude CodeCodex
End-to-end workflow to fix a GitHub issue — collect context, analyze, implement on a branch, open a PR, then hand off to /pr-watch-fix until CI is green.
Skill Claude CodeCodex
Debug and fix a failing MegaLinter linter test. Use when a linter test fails in CI or locally.
Skill Claude CodeCodex
Handle CVE/vulnerability reports from security linters (trivy, osv-scanner, etc.). Tries to upgrade first; ignores only when safe and justified; disables an unmaintained linter (with user confirmation) when a dangerous CVE has no fix.