Spectre is a battle-tested 6 stage agentic engineering workflow for building complex, production-ready features. You stay in the loop for the decisions that matter. Your agents handle the the rest. One command to start building - /spectre:scope
Agent
Explains HOW specific code works — traces data flow, call paths, and key logic, returning a cited implementation analysis. Use to understand existing behavior before planning or fixing. Do not use to locate files (use finder), critique quality, or recommend changes (use reviewer).
Agent
Implement or refactor code for an already-scoped task — writes/edits files, runs verification, returns a Completion Report. Use to build assigned features/refactors. Do not use for scoping, planning, design, review, or test authoring.
Agent
Locate files, directories, and components relevant to a feature or task and return grouped paths. Use to map where code lives before analysis or planning; do not use to explain how code works (use analyst) or to find reusable patterns (use patterns). Returns grouped file paths with search terms used, never…
Agent
Find existing in-repo implementations, usage examples, and conventions to model new work on, returning 2-5 cited code examples with a recommended best fit. Use to discover reusable patterns before writing similar code; do not use to locate files only (use finder), explain a single code path (use analyst), or…
Agent
Independent, skeptical review of a plan, task list, or code diff for correctness, security, regressions, performance, and missing tests. Use when you want a clean-room second opinion on already-produced work; returns severity-ranked findings with file:line evidence. Do not use to implement or fix (use dev), to write…
Agent
Memory consolidation agent that synthesizes current session context with historical sessions to maintain continuity across handoffs. Called by /spectre:handoff when previous handoffs exist.
Agent
Write or update behavioral tests, drive a strict RED→GREEN→REFACTOR loop, or diagnose failing tests for a given working set. Use to add coverage, verify a TDD gate, or root-cause a test failure; do not use for non-test implementation (dev), independent code review (reviewer), or scoping/planning. Returns tests…
Agent
Use for current, external, or third-party information that needs web verification — library/API docs, version-specific behavior, recent changes, or facts outside the model's training. Returns a sourced brief with links, version/date notes, and uncertainty flags. Do not use for questions answerable from the local…