The agentic build line: planned phases, parallel waves, machine gates at every station. Go Build Something Awesome.
Agent
Post-change WCAG 2.1 AA audit of implemented frontend surfaces. Static rules with file:line evidence plus an optional lighthouse probe when available. Writes A11Y.md and returns structured findings (severity, pillar, evidence). Spawned as a design eye by /ferrox:ui-review.
Agent
Design-phase WCAG 2.1 AA review of UI artifacts covering contrast, semantics, focus, and ARIA. Runs early, on tokens, component sources, and mockups, so violations surface before code locks them in. Returns structured findings (severity, pillar, evidence). Spawned as a design eye by /ferrox:ui-phase.
Agent
Researches a single gray area decision and returns a structured comparison table with rationale. Spawned by discuss-phase advisor mode.
Agent
Researches a chosen AI framework's official docs to produce implementation-ready guidance — best practices, syntax, core patterns, and pitfalls distilled for the specific use case. Writes the Framework Quick Reference and Implementation Guidance sections of AI-SPEC.md. Spawned by /ferrox:ai-integration-phase…
Agent
Deeply analyzes codebase for a phase and returns structured assumptions with evidence. Spawned by discuss-phase assumptions mode.
Agent
Drafts a chapter from the trusted planner-authored chapter contract plus canon stores, prior chapter, and spine entry. Echoes the contract in draft frontmatter, self-declares only additionalonstage. Revision mode fixes continuity findings, capped at 2 passes.
Agent
Applies fixes to code review findings from REVIEW.md. Reads source files, applies intelligent fixes, and commits each fix atomically. Spawned by /ferrox:code-review --fix.
Agent
Reviews source files for bugs, security issues, and code quality problems. Produces structured REVIEW.md with severity-classified findings. Spawned by /ferrox:code-review.
Agent
Explores codebase and writes structured analysis documents. Spawned by map-codebase with a focus area (tech, arch, quality, concerns). Writes documents directly to reduce orchestrator context load.
Agent
Stateless cross-chapter continuity audit for the book lane. Checks chapters against the declared canon-facts block in LORE.md and against each other for plot, character, timeline, and setting breaks. Writes .planning/ /CONTINUITY.md. Never edits prose.
Agent
Manages multi-cycle /ferrox:debug checkpoint and continuation loop in isolated context. Spawns ferrox-debugger agents, handles checkpoints via AskUserQuestion, dispatches specialist skills, applies fixes. Returns compact summary to main context. Spawned by /ferrox:debug command.
Agent
Investigates bugs using scientific method, manages debug sessions, handles checkpoints. Spawned by /ferrox:debug orchestrator.
Agent
Design-phase critique of UI artifacts on hierarchy, contrast, alignment, consistency, and intent. Grades against DESIGN.md when present plus the anti-template list. Returns structured findings (severity, pillar, evidence). Spawned as a design eye by /ferrox:ui-phase and /ferrox:ui-review.
Agent
Classifies a single planning document as ADR, PRD, SPEC, DOC, or UNKNOWN. Extracts title, scope summary, and cross-references. Spawned in parallel by /ferrox:ingest-docs. Writes a JSON classification file and returns a one-line confirmation.
Agent
Synthesizes classified planning docs into a single consolidated context. Applies precedence rules, detects cross-ref cycles, enforces LOCKED-vs-LOCKED hard-blocks, and writes INGEST-CONFLICTS.md with three buckets (auto-resolved, competing-variants, unresolved-blockers). Spawned by /ferrox:ingest-docs.
Agent
Verifies factual claims in generated docs against the live codebase. Returns structured JSON per doc.
Agent
Writes and updates project documentation. Spawned with a docassignment block specifying doc type, mode (create/update/supplement), and project context.
Agent
Researches the business domain and real-world application context of the AI system being built. Surfaces domain expert evaluation criteria, industry-specific failure modes, regulatory context, and what "good" looks like for practitioners in this field — before the eval-planner turns it into measurable rubrics. Spawned…
Agent
Retroactive audit of an implemented AI phase's evaluation coverage. Checks implementation against the AI-SPEC.md evaluation plan. Scores each eval dimension as COVERED/PARTIAL/MISSING. Produces a scored EVAL-REVIEW.md with findings, gaps, and remediation guidance. Spawned by /ferrox:eval-review orchestrator.
Agent
Designs a structured evaluation strategy for an AI phase. Identifies critical failure modes, selects eval dimensions with rubrics, recommends tooling, and specifies the reference dataset. Writes the Evaluation Strategy, Guardrails, and Production Monitoring sections of AI-SPEC.md. Spawned by…
Agent
Executes Ferrox plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
Agent
Presents an interactive decision matrix to surface the right AI/LLM framework for the user's specific use case. Produces a scored recommendation with rationale. Spawned by /ferrox:ai-integration-phase and /ferrox-select-framework orchestrators.
Agent
Verifies cross-phase integration and E2E flows. Checks that phases connect properly and user workflows complete end-to-end.
Agent
Analyzes codebase and writes structured intel files to .planning/intel/.