Skip to content

Expecho/Agent42 / .agentic/optional-skills/sonar

Run SonarQube analysis locally against this repo and interpret results against .agentic/quality-gates.yaml before pushing.

Local SonarQube analysis

Transformed from the workspace /sonar skill: repo-root scan instead of the repos/<service>/ multi-repo indirection; thresholds compared against .agentic/quality-gates.yaml instead of prose. OPTIONAL: lives in .agentic/optional-skills/; onboarding copies it into .claude/skills/ only when the repo has a SonarQube gate.

Step 0 — Pre-flight

SONAR_HOST_URL and SONAR_TOKEN must be set. If missing, ask the user for them (AskUserQuestion) and offer to persist to their shell profile. Find the project key in sonar-project.properties or the CI config.

Step 1 — Tests + coverage first

Sonar without coverage lies. Run the repo's coverage command (from quality-gates.yaml coverage_tooling / CLAUDE.md Commands) so the report exists before scanning.

Step 2 — Scan (stack-dependent)

  • .NET: dotnet sonarscanner begin /k:<key> /d:sonar.host.url=$SONAR_HOST_URL /d:sonar.token=$SONAR_TOKEN /d:sonar.cs.opencover.reportsPaths=<coverage> → dotnet build → dotnet sonarscanner end /d:sonar.token=$SONAR_TOKEN (needs Java 17+).
  • Node: npx sonarqube-scanner with sonar-project.properties (lcov path set).

Step 3 — Fetch & interpret

Query the server REST API: /api/qualitygates/project_status, /api/issues/search (new code period), /api/measures/component (coverage, duplication, complexity). Render the gate table: metric | threshold (from .agentic/quality-gates.yaml) | actual | PASS/FAIL.

Step 4 — Report

For each failing condition, list the concrete issues (file:line, rule, message) and propose fixes ordered by effort. Distinguish "new code" failures (merge-blocking per enforcement.ci) from overall-code noise.

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 465kUpdated Claude CodeCodexUnverifiedInstall
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 465kUpdated Claude CodeCodexUnverifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 318kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 318kUpdated Claude CodeCodexVerifiedInstall