bkit

A compatibility command hub for bkit and demokit, development workflows that provide commands for planning, design, implementation, testing, review, optimisation, and quality checks.

In plain words
What is it for?
Use it to plan and document features, generate common application layers, run tests, review or optimise code, perform quality checks, and track development progress.
Why use it?
It gives existing users a familiar entry point for finding and running the same demokit-style commands under the bkit name.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/demodev-lab/claude-code-plugin-demokit/bkit
Clone the repo
git clone --depth 1 https://github.com/demodev-lab/claude-code-plugin-demokit
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 687 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00031 $0.00687
Opus 5 $0.00015 $0.00344
Sonnet 5 $0.00006 $0.00137
Haiku 4.5 $0.00003 $0.00069

Measured 2d ago against content hash cab6f89790e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bkit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/bkit.md · 76 lines

What it actually says

bkit Functions (Demokit Compatibility)

/bkitdemokit 플러그인의 동일한 명령 허브를 보여줍니다.

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  bkit / demokit Help Hub
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

핵심 워크플로우
  /pdca plan <feature>       기능 계획 수립
  /pdca design <feature>     설계 문서 생성
  /pdca do <feature>         구현 가이드 / 실행
  /pdca analyze <feature>    설계-구현 gap 분석
  /pdca iterate <feature>    자동 개선 반복
  /pdca report <feature>     완료 보고서 생성
  /pdca archive <feature>    작업 기록을 아카이브로 이동
  /pdca cleanup              완료/임시 문서 정리
  /pdca status               현재 상태 조회
  /pdca next                 다음 단계 제안

생성/개발
  /crud <Domain>             CRUD 일괄 생성
  /entity <Domain>
  /repository <Domain>
  /service <Domain>
  /controller <Domain>
  /dto <Domain>

테스트
  /test <Domain|all>

품질/분석
  /review [target] [--deep]     정적 코드 리뷰 (--deep: 보안 심층)
  /review full [target] [--fix] [--deep]  통합 품질 파이프라인
  /optimize [target] [--fix]    성능 최적화 (N+1/인덱스/트랜잭션)
  /qa [build|test|log|summary]  동적 품질 검증 (빌드/테스트/로그)

운영
  /pipeline <feature>        9단계 파이프라인 가이드
  /plan-plus <feature> [--deep]  5단계 브레인스토밍 강화 계획
  /loop <task>               반복 실행
  /cancel-loop               loop 중단

스타일/문서
  /output-style-setup        output style 설치/적용 안내

호환 alias
  /code-review               = /review
  /zero-script-qa            = /qa
  /development-pipeline      = /pipeline
  /starter /dynamic /enterprise
  /phase-1-schema ... /phase-9-deployment

권장 시작 순서
  1) /init
  2) /pdca plan <feature>
  3) /pdca design <feature>
  4) /pdca do <feature>
  5) /pdca analyze <feature>
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

/bkit은 앞으로도 유지되며, /demokit으로 동일한 기능을 사용할 수 있습니다.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 76 lines · 31 tokens per session scan A cab6f89790e4

Subscribe to this mod's changes

bkit is a command published in the GitHub repository demodev-lab/claude-code-plugin-demokit (2 stars, last pushed 6mo ago), licensed MIT. It adds 31 tokens to every session and 687 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.