agentic-devops-solar-ralph

Use when gathering files, running searches, and producing a structured context manifest for other agents. Read-only — never writes code or makes design decisions.

Use when solution design, architecture-fit analysis, task decomposition, or high-ambiguity tradeoff analysis needs stronger reasoning before coding starts.

Use when executing a feature end to end through plan, implement, test, docs, review, ledger updates, and bounded recursive repair.

Use when implementing code changes in a repository where domain-specific specialists are not installed. Generic — no stack assumptions. Stack context loaded from the project's .instructions.md at runtime.

Use when reviewing changes for regressions, correctness, security, and missing coverage. Generic — no stack assumptions. Stack context loaded from the project's .instructions.md at runtime.

Use when adding or repairing tests — unit, integration, or component. Generic — no stack assumptions. Stack context loaded from the project's .instructions.md at runtime.

Use when implementing backend Express, Prisma, service, repository, route, controller, middleware, or backend contract changes in the repository's backend area.

Use when syncing rollout docs, BR docs, implementation docs, review checklists, and knowledge base notes after code or process changes.

Use when implementing frontend React, TypeScript, routing, context, reducer, selector, page, or component changes in the repository's frontend area.

Use when deciding whether information belongs in repo memory, session memory, the AI ledger, or permanent documentation.

Use when applying facts from .github/instructions/ to confirm those facts still match the current codebase before acting on them. Prevents errors from stale architecture instructions.

Use when a bug investigation requires confirming behaviour in a live browser before classifying the root cause. Produces a Behaviour Report that the Bug Investigation Specialist attaches to the ledger before classification.

Use when adding or repairing backend service, repository, route, controller, integration, or Prisma-sensitive tests in the repository's backend area.

Use when adding or repairing frontend Vitest, RTL, reducer, hook, component, or page tests in the repository's frontend area.

Use when a bounded SOLAR loop must repair a failed test, review finding, or verification issue without expanding scope uncontrollably.

Use when verifying a feature pipeline is ready to close and release. Checks all lanes — tests passing, security audit complete, docs synced, ledger has no open blockers — and produces a Go / No-Go decision with evidence.

Use when reviewing backend API, service, repository, validation, auth, middleware, or Prisma changes for safety, regressions, and missing coverage.

Use when an agent needs to test API contracts with the Fetch MCP server, inspect DOM state with the Puppeteer MCP server, or verify browser storage and CDP-level behaviour that the Playwright accessibility-tree model does not expose.

Use when reviewing frontend changes for regressions, accessibility, rendering risks, state correctness, or missing Vitest and RTL coverage.