Agent Claude Code
Compares incremental refactor vs clean rewrite approaches for code changes.
Agent Claude Code
Compares incremental refactor vs clean rewrite approaches for code changes.
Agent Claude Code
Evaluates proposed dependencies from 3 perspectives - adopt, find alternatives, or build without.
Agent Claude Code
Scans for emerging technologies, techniques, and approaches relevant to the research topic.
Agent Claude Code
Scans market landscape for commercial solutions, open-source alternatives, and industry benchmarks to inform build-vs-buy decisions.
Agent Claude Code
Multiplies research perspectives across 5 independent angles for comprehensive codebase analysis.
Agent Claude Code
Detects scope creep by comparing current spec/tasks against original problem brief and constraints.
Agent Claude Code
Detects specification ambiguities by having 3 agents independently interpret the same spec.
Agent Claude Code
Stress-tests user journeys from 4 persona perspectives to find spec gaps.
Agent Claude Code
Scans task breakdown for missing cross-cutting concerns from 5 dimensions.
Agent Claude Code
Plans rollback strategy for each implementation phase to enable safe recovery.
Agent Claude Code
Red teams security from 3 attack perspectives - OWASP, business logic, and CVE search.
Agent Claude Code
Validates functional correctness against spec acceptance criteria.
Agent Claude Code
Validates integration contracts and cross-component boundaries.
Agent Claude Code
Validates performance characteristics and code complexity.
Agent Claude Code
Validates security posture of implemented code.
Agent Claude Code
Validates compliance with project constitution, patterns, and code hygiene.
Agent Claude Code
Validates test authenticity, mock ratios, and mutation testing scores.
Agent Claude Code
Writes bounded-context map showing logical domain boundaries and integration patterns between contexts.
Agent Claude Code
Writes C4 Context and C4 Container diagrams for feature visuals from spec/research/plan input. Outputs Mermaid C4 blocks with named external systems.
Agent Claude Code
Writes data-model entity-relationship diagram from data-model.md.
Agent Claude Code
Writes capability heatmap from research findings showing capabilities touched, replaced, or extended by the feature.
Agent Claude Code
Writes risk heatmap from validation council findings or spec NFR/Out-of-Scope sections.
Command Claude Code
Use this as the single user-facing Gofer command. Users should run /eai, $eai, or #eai depending on the host. Do not ask users to run numbered stage commands unless they explicitly request low-level internals.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing user-prompt-submit.mjs via node. From eai-support/eai-gofer.