From vanguard-frontier-agentic
Audits CI test pipelines for gating correctness, sharding, fail-fast behavior, artifact retention, quarantine wiring, and secret exposure. Scans config and branch protection — never triggers pipelines or requests secrets.
How this agent operates — its isolation, permissions, and tool access model
Agent reference
vanguard-frontier-agentic:agents/qa/ci-test-pipeline-review-agent/harnesses/claude-code.agentThe summary Claude sees when deciding whether to delegate to this agent
Use this agent only for `ci-test-pipeline-review` work. Before answering, read and follow: - `skills/qa/ci-test-pipeline-review/SKILL.md` Reviews how a CI pipeline runs tests — the pipeline that decides whether the suite blocks a merge, not the tests themselves. Catches non-blocking test steps and soft-failure escape hatches, post-merge-only test placement, missing required-check enforcement, u...
Use this agent only for ci-test-pipeline-review work.
Before answering, read and follow:
skills/qa/ci-test-pipeline-review/SKILL.mdReviews how a CI pipeline runs tests — the pipeline that decides whether the suite blocks a merge, not the tests themselves. Catches non-blocking test steps and soft-failure escape hatches, post-merge-only test placement, missing required-check enforcement, un-sharded slow suites, fail-fast that hides parallel failures, missing artifacts, broken quarantine-lane wiring, and secret exposure to test jobs on pull_request_target or fork PRs. Static review only — does not trigger or run pipelines.
CI config and branch protection provided, CI config only, documentation-based, or inference.|| true, continue-on-error) as CRITICAL.pull_request_target or fork PRs as CRITICAL.npx claudepluginhub raishin/vanguard-frontier-agentic --plugin vanguard-frontier-agenticReviews CI/CD pipelines for missing stages, anti-patterns, and production safety gaps. Follows SME protocol with confidence, risk assessments, and mandatory stage checklists.
CI/CD specialist that monitors pipeline runs, diagnoses failure root causes, suggests fixes, and detects flaky tests. Invoke when CI fails or results are pending.
CI/CD specialist for GitHub Actions pipelines in Python/ML OSS projects. Diagnoses failing runs, optimizes build times, configures test matrices, caching, SHA pinning, branch protections, and quality gates in YAML.