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/.
Agent
Prose fix applier for the book lane. 1 line-edit finding in, 1 verified surgical edit out, with 2-tier verification and rollback. Style lane only: continuity findings route to ferrox-chapter-drafter revision mode, never here.
Agent
Maintains the canonical lore store for book/writing domains. Owns the fenced yaml canon-facts block in LORE.md and SOURCES.md, ingests chapters for first-appearance facts, applies deliberate retcons, and answers typed canon queries. Runs as a serial between-waves step in the book lane.
Agent
Ship-time MemPalace curation — writes the session diary, proposes/creates cross-project tunnels, mirrors extract-learnings into the temporal KG, and runs wing-scoped drawer pruning. Spawned at ship:post by the mempalace capability.
Agent
Research-lane judgment eye. Audits a landed research artifact for method quality, bias surface, source quality, claim-support, and traceability against the SOURCES.md ledger. Owns the CS-03 INDET judgment slice the citation gate refuses. Writes .planning/ /METHOD-REVIEW- .md. Never edits the artifact.
Agent
Fills Nyquist validation gaps by generating tests and verifying coverage for phase requirements.
Agent
Analyzes codebase for existing patterns and produces PATTERNS.md mapping new files to closest analogs. Read-only codebase analysis spawned by /ferrox:plan-phase orchestrator before planning.
Agent
Researches how to implement a phase before planning. Produces RESEARCH.md consumed by ferrox-planner. Spawned by /ferrox:plan-phase orchestrator.
Agent
Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality. Spawned by /ferrox:plan-phase orchestrator.
Agent
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /ferrox:plan-phase orchestrator.
Agent
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /ferrox:new-project or /ferrox:new-milestone orchestrators.
Agent
Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by /ferrox:new-project after 4 researcher agents complete.
Agent
Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /ferrox:new-project orchestrator.
Agent
Verifies threat mitigations from PLAN.md threat model exist in implemented code. Returns structured security verdict (SECURED / OPENTHREATS / ESCALATE). Spawned by /ferrox:secure-phase.
Agent
Retroactive 7-pillar visual audit of implemented frontend code. Produces scored UI-REVIEW.md. Spawned by /ferrox:ui-review orchestrator.
Agent
Validates UI-SPEC.md design contracts against 6 quality dimensions. Produces BLOCK/FLAG/PASS verdicts. Spawned by /ferrox:ui-phase orchestrator.
Agent
Produces UI-SPEC.md design contract for frontend phases. Reads upstream artifacts, detects design system state, asks only unanswered questions. Spawned by /ferrox:ui-phase orchestrator.
Agent
Analyzes extracted session messages across 8 behavioral dimensions to produce a scored developer profile with confidence levels and evidence. Spawned by profile orchestration workflows.