anortham

Use when the user says "ask grok", "get grok's take", "grok review", "have grok look at this", "delegate to grok", or any variation naming Grok/xAI as the perspective they want.

Use when starting any creative work - creating a feature, building a component, adding functionality, or changing designed behavior - before writing code or invoking any implementation skill. Small defect repairs and tweaks triage through razorback:fixing-small-issues first.

Use when a design question resists discussion — a state model with more edge cases than fit in your head, a UI the user keeps flip-flopping on because nobody can picture it, or behavior only knowable by running it — before writing a design doc or implementation plan for that question.

Use when the user says "ask claude", "fresh claude review", "second opinion from another claude", "have another claude look at this", "delegate to a fresh claude", or any variation naming Claude as the second perspective they want.

Use when the user says "ask codex", "get codex's take", "codex review", "have codex look at this", "delegate to codex", or any variation naming Codex/OpenAI as the perspective they want. Also use for a generic "second opinion from a different model" when no other model is named.

Use when planning or reviewing non-trivial code changes, refactoring architecture, evaluating module boundaries, repeated findings reveal coupling, tests are hard to write because interfaces are unclear, or the user asks for codebase design improvements, complexity reduction, deduplication, or cleanup of existing code.

Use after all tasks are complete and branch verification passes, before finishing-a-development-branch, when a pre-merge external reviewer was chosen for the run (codex or claude).

Use when starting any conversation, before any response or action including clarifying questions.

Use before changing existing indexed files with Miller edit, especially symbol rewrites, text replacements, renames, or refactors.

Use when an agent needs extractor-recognized code-shape facts such as routes, htmx attributes, Alpine directives, SQL DDL/DML, or data-document structure.

Use when starting a Miller task, choosing a Miller tool, or choosing a Miller search mode.

Use when tracing Miller bridge paths in supported providers: dotnet-web URL literals and fetch/axios client requests to ASP.NET signals, client requests to Next.js route handlers or Nuxt server routes, Next.js/Nuxt route references to file routes, Vue/React references to route definitions, or backend-http client requests to Express/FastAPI/Flask/Django/Spring/Go/gin/echo/Rails/NestJS/Laravel/Phoenix/axum/actix/Symfony/Ktor route facts.

Use when orienting on an unfamiliar code area with Miller, explaining a module, finding entry points, or gathering context before a change.

Use when assessing blast radius with Miller, choosing tests for a change, answering who uses a symbol, or planning a refactor.

Use when resuming Miller-backed work from a handoff packet or validating a packet before continuing in another harness, model, or session.

Use when preparing to move active Miller-backed work to another harness, model, or session and the receiving agent needs a self-contained resume packet.

Use when auditing Julie for dead code, test-only code paths, stale helpers, graph gaps, or cleanup candidates before deleting, privatizing, or simplifying code.

Use before making changes to existing files. Routes to Julie's edit_file, rewrite_symbol, and rename_symbol tools without a Read + Edit loop. Trigger on fix, change, update, modify, refactor, rename, replace, add, remove, move, or any task involving an existing file.

Orient on a new codebase area using get_context for token-budgeted exploration. Use when the user asks "what does this module do", "explain this part", or wants to understand an unfamiliar area before making changes.

Analyze what would break if a symbol changes: finds callers, groups by risk level, assesses impact. Use when the user asks about blast radius, who uses a symbol, or is planning a refactor.

Diagnose why a Julie search returns unexpected results during Julie development. Analyze scoring factors, tokenization, and index health when dogfooding search quality.

Fetch web pages and index them locally for token-efficient research. Use when you need to read documentation, articles, or any web content. Fetches via browser39, saves as markdown, indexes via Julie's filewatcher, then uses Julie tools for selective reading. Requires browser39 (binary release from GitHub).

Use when auditing Julie for dead code, test-only code paths, stale helpers, graph gaps, or cleanup candidates before deleting, privatizing, or simplifying code.

Use when the user asks for a standup, daily update, progress summary, or cross-project report built from Goldfish briefs and checkpoints

Use when starting a new session, after context loss, searching for prior work, or when the user asks what happened previously and needs Goldfish memory restored

Use when starting multi-session work, capturing approved project direction, updating goals or constraints, or when the user asks for durable strategic context that should persist across sessions

Use when the user asks for progress against current project direction, wants a status check on the active brief, or needs evidence-backed assessment across briefs, checkpoints, and docs/plans

Save developer context to Goldfish memory — checkpoint at meaningful milestones, not after every action

Use when returning to a project after time away, switching harnesses, or handing work off to another agent, to produce a structured session-resumption summary from the active brief, recent checkpoints, and git delta.

Systematic bug hunting combining Sherpa's debugging workflow, Julie's execution tracing, and Goldfish's investigation tracking. Activates for bug fixes with methodical reproduction, test capture, fix, and verification. Use when debugging errors or fixing bugs.

Systematically explore unfamiliar codebases and document findings using Julie's code intelligence, Sherpa's exploration workflow, and Goldfish's documentation. Activates when learning new code with semantic search, architecture mapping, and persistent documentation.

Safe code refactoring combining Sherpa's refactor workflow, Julie's reference checking and safe renaming, and Goldfish's before/after checkpointing. Activates for code improvement with systematic testing, refactoring, and verification. Use when cleaning up or improving existing code.

Intelligent session initialization combining Goldfish memory recall, Julie workspace re-indexing, and Sherpa workflow suggestion. MANDATORY at session start - automatically restores context, suggests next steps, and resumes work seamlessly. Activates at the beginning of every coding session.

Complete Test-Driven Development workflow combining Sherpa guidance, Julie code intelligence, and Goldfish progress tracking. Automatically activates for feature implementation with systematic phases, semantic code search, and persistent checkpointing. Use when implementing new features with test-first discipline.

Use when user asks about error handling issues, exception swallowing, or silent failures. Finds catch blocks that ignore errors without logging or rethrowing. Triggers on "empty catch", "swallowed exception", "silent error", "error handling audit".

Use when user asks about security audits, credential leaks, hardcoded passwords, API keys in code, or secret detection. Triggers on "security scan", "leaked credentials", "hardcoded password", "API key exposed", "secrets in code".

Use when user asks about database performance, slow queries, N+1 patterns, or loop-based fetching. Triggers on "N+1", "query in loop", "slow database", "too many queries", "batch queries", "performance audit".

Use when generating standup reports, summarizing recent work across projects, or preparing for status meetings. Searches development memories from all Miller-registered projects.

Systematically debug issues using Sherpa's Bug Hunt workflow. Activates when fixing bugs, investigating errors, debugging broken functionality, or handling regressions. Prevents symptom-fixing by enforcing reproduction-first approach.

Use Sherpa's systematic development workflow for general coding tasks. Activates when starting development work, adding features, or implementing functionality. Ensures guide check before coding and guide done after completion for progress tracking and celebrations.

Follow strict TDD methodology using Sherpa's workflow enforcement. Activates when implementing new features, adding functionality, or building code that requires tests. Ensures RED-GREEN-REFACTOR discipline with guide check/done tracking.

Use when user asks for a standup, daily summary, weekly report, or "what did I work on" - requires koi MCP server