By phibkro
Vevx's default Claude Code setup, a stable harbor for every pirate looking to sail the seas.
Implementation agent with project memory. Use proactively when asked to build, implement, create, write code, add a feature, or fix a bug.
Analyzes and compresses context files (CLAUDE.md, MEMORY.md, .claude/rules/*) using progressive disclosure patterns. Returns structured recommendations or implements compression.
Review agent with project memory. Use proactively when asked to review code, evaluate an implementation, check against a spec, or audit quality. Outputs structured findings with a PASS/FAIL verdict.
Use when adding tests to existing untested code, improving coverage for a module, or backfilling test gaps before a refactor. Triggers on "add tests", "improve coverage", "write tests for", "backfill tests".
Use when output can't be validated by tests or lint alone — prompt engineering, skill design, documentation, system prompts, API contracts. Triggers on "review and fix loop", "evaluate until clean", "optimize until no issues", "review cycle", "iterate until passing", "quality gate".
Use when a plan with ordered tasks needs sequential execution. Triggers on "execute the plan", "implement this plan", "work through these tasks", "start the implementation".
Use when starting work in an unfamiliar codebase, onboarding to a new project, or needing a structural overview before planning. Triggers on "what does this project do", "understand the codebase", "project overview", "explore the repo".
Use when fixing a bug, resolving an error, or addressing unexpected behavior. Triggers on "fix", "debug", "broken", "regression", "not working".
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Agent toolkit for Claude Code. A monorepo of plugins that give AI coding agents structural awareness of codebases.
| Package | Description | Deps |
|---|---|---|
@vevx/kiste | Git-backed artifact index. Tags, provenance, co-change, full-text search over commit history. | — |
@vevx/varp | Dependency analysis and agent orchestration. Manifest-driven: structural grouping, doc freshness, coupling diagnostics, plan validation, task scheduling. | kiste |
@vevx/kart | IDE interface for AI agents. Progressive code disclosure, LSP integration, AST-aware editing. 24 MCP tools. | — |
@vevx/audit | Multi-agent compliance audit engine. Ruleset-based code review with 3-wave planner. | varp |
@vevx/havn | Default Claude Code plugin setup. 3 agents, 10 skills, project memory, git hooks, plugin auto-detection. | — |
kiste ← varp ← audit
kart (standalone)
havn (standalone)
Prerequisites: Bun, Claude Code with plugin support.
# As Claude Code plugins
claude plugin add https://github.com/phibkro/vevx/tree/main/packages/varp
claude plugin add https://github.com/phibkro/vevx/tree/main/packages/kart
claude plugin add https://github.com/phibkro/vevx/tree/main/packages/havn
# As npm packages
bun add @vevx/varp @vevx/kart @vevx/kiste
From source:
git clone https://github.com/phibkro/vevx.git && cd vevx
bun install && turbo build
bun install # install all workspace deps
turbo build # build all packages
turbo test # all tests across all packages
turbo check # format + lint + build
Stack: Bun, Turborepo, TypeScript (ES2022, ESM only), Zod, Effect TS, MCP SDK.
varp.yaml format referenceProgressive code disclosure, import graph analysis, and behavioral coupling via LSP and git history
Graph-aware project analysis: coupling diagnostics, dependency tracking, scope enforcement, and architectural drift detection
Semantic artifact index over git history — tag-based retrieval, provenance tracking, and full-text search for agent workflows
npx claudepluginhub phibkro/vevx --plugin havnHigh-intelligence Claude Code copilot with deep code reasoning, evidence-driven planning, orchestration-first execution, model routing, context budgeting, CI/CD integration, enterprise security, plugin development, prompt engineering, performance profiling, agent teams, channels (event-driven autonomy with CI webhook, mobile approval relay, Discord bridge, and fakechat dev profile), interactive tutorials, LSP integration, security-hardened hook script library, MCP Prompts coverage, common workflow packs, runtime selection guide, computer-use patterns, checkpointing, scheduled-task blueprints, repo bootstrap scanner, hook policy engine (8 installable packs), layered memory deployment, role-based subagent packs (implementer, debugger, migration-lead, dependency-auditor, release-coordinator), 5 agent-team topology kits, autonomy operating mode (4 profiles + 3 gates), and a queryable 15-tool MCP documentation server with autonomy advisor.
Complete developer toolkit for Claude Code
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Multi-agent /workflow development pipeline (planner → plan-review → coder → code-review) with typed handoff contracts, lifecycle hooks, and MCP servers.
One plugin to bridge and delegate across Claude Code, Codex CLI, and Gemini CLI — single-source AGENTS.md, shared skills, mirrored hooks and MCP servers, and full Claude↔Codex bidirectional delegation.
Comprehensive development infrastructure for Claude Code projects. Includes 12 AI skills, task coordination hooks, project templates, and a visual dev-manager dashboard.