Claude Tools / MCP Servers / bkit

MCP Servers · popup-studio-ai/bkit-claude-code

bkit

A Claude Code plugin that verifies AI-generated code against its own design specs.

CLEARED_STATICmcp-portablev2.1.34

Pipeline results

Coverage

CLEARED_STATIC

Tests run

7 / 8

Portability

MCP-portable

Type

MCP Servers

Tests & results

What the pipeline checked

TestStateResult or reason
eligibilityranall eligibility checks passed
dedupranunique -- no near-duplicate found
clocranno code measured
secretsranno secret patterns matched
egressran20 lexical match(es) — FLAG-INFO (C-01: semantic analysis deferred to v2)
injectionranno patterns matched (confidence: STANDARD)
required-fieldsranrequired fields present: name, version, description
behaviouraldeferredbehavioural assessment deferred (v1): 3 JS/TS entry point(s)

What's inside

Components found

agents/bkend-expert.md
componentmedium
agents/bkit-impact-analyst.md
componentmedium
agents/cc-version-researcher.md
componentmedium
agents/code-analyzer.md
componentmedium
agents/cto-lead.md
componentmedium
agents/design-validator.md
componentmedium
agents/enterprise-expert.md
componentmedium
agents/frontend-architect.md
componentmedium
agents/gap-detector.md
componentmedium
agents/infra-architect.md
componentmedium
agents/pdca-iterator.md
componentmedium
agents/pipeline-guide.md
componentmedium
agents/pm-discovery.md
componentmedium
agents/pm-lead-skill-patch.md
componentmedium
agents/pm-lead.md
componentmedium
agents/pm-prd.md
componentmedium
agents/pm-research.md
componentmedium
agents/pm-strategy.md
componentmedium
agents/product-manager.md
componentmedium
agents/qa-debug-analyst.md
componentmedium

Coverage

Not assessed

  • behavioural execution not run
  • egress patterns logged (FLAG-INFO): 20 lexical match(es)

README

From the repository

# bkit — AI Native Development OS

> A Claude Code plugin that verifies AI-generated code against its own design specs.

**Three commands. Anyone — even someone vibe-coding for the first time — can ship robust, production-quality software.** bkit turns Claude Code into a *Context Engineering system*: 44 skills, 34 specialist agents, 11 quality gates, and a memory that survives across sessions deliver the right context to the AI at the right moment, so you don't have to know prompts, commands, or PDCA to get high-quality results.

[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
[![Claude Code](https://img.shields.io/badge/Claude%20Code-v2.1.143+-purple.svg)](https://code.claude.com)
[![Version](https://img.shields.io/badge/Version-2.1.34-green.svg)](CHANGELOG.md)
[![Author](https://img.shields.io/badge/Author-POPUP%20STUDIO-orange.svg)](https://popupstudio.ai)

> **Requirement**: bkit requires Claude Code **v2.1.143 or later** (the strict plugin-manifest path recognizes the official `displayName` field only from v2.1.143). On older Claude Code you will see `Validation errors: Unrecognized key: "displayName"` during

← Back to MCP Servers