Agent Claude Code
Responsible AI standards assessment orchestrator for codebase profiling and RAI findings reporting against NIST AI RMF, the AI STRIDE overlay, and the EU AI Act.
Agent Claude Code
Assesses a single Responsible AI framework from the rai-standards skill against the codebase, reading framework references and returning structured findings.
Agent Claude Code
Collates verified security or accessibility skill assessment findings and generates a comprehensive report written to the domain-appropriate reports directory.
Agent Claude Code
User-selected RPI workflow wrapper for Research, Plan, Implement, Review, and Follow-up. Use when one task needs lifecycle coordination.
Agent Claude Code
Gathers candidate sources for one bounded research question and returns source pointers, exact locations, contract excerpts, and brief relevance notes as suggestions for the calling agent to verify. Use during research when isolating source gathering would help.
Agent Claude Code
Phase-based security planner producing security models, standards mappings, and backlog handoffs with AI/ML detection and RAI Planner integration.
Agent Claude Code
Security skill assessment orchestrator for codebase profiling and vulnerability reporting.
Agent Claude Code
Assesses a single security skill against the codebase and returns structured findings.
Agent Claude Code
Six-phase repository supply chain security assessment against OpenSSF Scorecard, SLSA, Sigstore, and SBOM standards, producing a prioritized backlog of reusable workflows.
Agent Claude Code
Evidence-based reviewer for repository supply-chain security posture with audit, diff, and plan review modes.
Agent Claude Code
Assesses supply-chain posture against the supply-chain skill and returns structured findings.
MCP server Claude CodeCodexCursor +2
Outbound Model Context Protocol (MCP) server that exposes the hve-squad as coarse intent tools (squadresearch, squadplan, squadreview, squadarchitect, squadrun) plus squadfederate for the opt-in federation of named sub-squads, to MCP hosts such as V. Runs locally from the @hve-squad/mcp npm package.
Agent Claude Code
System architecture reviewer for design trade-offs, ADR creation, and well-architected alignment.
Agent Claude Code
Route UX practitioners between focused coaching, evidence-labelled asset production, inclusion decisions, design intent, and external design surfaces.
Agent Claude Code
Authors Vally conformance test stimuli in two modes: from-artifact (read a prompt, instructions, agent, or skill file and draft a stimulus block) and corpus-import (turn a CSV or XLSX corpus into stimulus blocks), with safety-lint refusal enforcement and SHA-256 dedupe before append-only writes to the routed eval file.
Agent Claude Code
Assesses open GitHub issues for backlog health and returns bounded advisory reports without mutating candidate issues.
Agent Claude Code
Builds the factual Register 1 walkthrough and dispatch-board appendices for a serialized Code Review target.
Agent Claude Code
Reconciles independent report critiques against research evidence and records user-approved decisions.
Agent Claude Code
Independently critiques one engagement report draft against research evidence without reading other critiques.
Agent Claude Code
Coach a persistent data science and data engineering workstream through explicit jobs, durable state, routed skill authority, and safe customer-artifact writes.
Agent Claude Code
Coordinates source-grounded engagement reports, review, optional Council critique, and Outlook draft creation.
Agent Claude Code
Reviews engagement report drafts for grounding, privacy, audience fit, style, terminology, and continuity.
Agent Claude Code
Reviews one prompt, instruction, agent, subagent, or skill candidate in fresh context against the hve-builder requirements catalog and review rubric, and returns severity-graded findings with the smallest resolving change as suggestions for the calling agent to verify. Use during an hve-builder review pass when…
Agent Claude Code
Creates one approved HTML Outlook draft through a constrained distribution-only workflow.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: