claudecodex

hiway-kit

Discipline kit for coding agents: plan files with executable done-criteria, an automated develop-and-validate pipeline, adversarial code review with a security scan, and a completion gate that judges "done" by command output. 15 skills, 15 subagents and 5 Python hooks (session-start rule injection, sensitive-path guard, ruff/prettier auto-format, Stop-time lint and test run). No network calls, no MCP servers.

3,741 on GitHubby This-HWv5.5.1MITupdated 2 days agodevelopment
/

Plugin hiway-kit from marketplace buildwithclaude in davepoon/buildwithclaude. Commands read from the repo's manifest — yesterday.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (14)

  • agent-creator

    Create a Claude Code sub-agent definition for this project or user. Use when the user asks to create a new custom agent or a specialized sub-agent for a recurring task.

  • auto-dev

    Automated development pipeline. Runs a completed plan file through Development and Validation phases end-to-end.

  • brainstorming

    Design and spec a Large new feature or system change before planning - explores requirements, proposes approaches, gets design approval, then chains to plan-task. Skip for bug fixes and Small/Medium work; go straight to plan-task or just do it.

  • child-session

    Discipline a worker session loads at dispatch time — verify the brief's premises before implementing, work only on its own branch, and report in the fixed completion format. Use when a session has been dispatched as a worker (child) with a brief from a parent control session.

  • control-loop

    Multi-session control discipline for delegating work to worker sessions — investigate, decide, dispatch, verify, and merge. Use when a session is coordinating separate worker sessions or worktrees and needs to know when to delegate versus decide, and how to verify before merging.

  • cross-engine-review

    Reach an evidence-backed decision between sessions running on different agent engines. Use when a call is high-stakes enough that one engine's blind spots are a real risk, and a second session with different tool access can bring evidence the first cannot.

  • debug

    Investigate a failure whose cause is not evident from the error itself - flaky or intermittent failures, failures that only happen in CI or one environment, or errors with several plausible causes across files - by reproducing, isolating, fixing and verifying. Skip it when the message already shows

  • harness-export

    Export the kit's host-neutral rules to every harness entrypoint file (AGENTS.md, GEMINI.md) so non-Claude-Code harnesses (Codex, OpenCode, Copilot, Gemini CLI, Pi, Hermes) follow the same discipline. Use when a repo is worked by more than one agent harness, or after changing rules/. Trigger with /ha

  • multi-perspective-review

    Multi-perspective review of a plan or design document. Up to ten viewpoints deliberate in 3 rounds; the main session orchestrates, with a sequential path for harnesses without subagents.

  • plan-task

    Structured task planning into a plan file. Use for any new feature, bug fix, or project that needs a task breakdown before implementation.

  • review

    Review current changes or specified files - ruff lint for Python files, an adversarial review-code pass, and a security scan only when security-sensitive files changed.

  • skill-forge

    Distill a hard problem you just solved into a reusable skill draft - proposal-only, behind a three-condition threshold. Use after finishing a non-trivial task whose procedure would otherwise die with the session. Trigger with /skill-forge.

  • using-hiway-kit

    Session-start meta-skill (hook-injected). Kit workflow chain and plan file rules.

  • web-research

    Multi-source external research with cited sources, using search/docs MCP servers when installed and built-in web tools otherwise. Use when a question needs several external sources compared or synthesized, or a web task needs the user's logged-in browser. Not for a single quick lookup.

Subagents (15)

  • analyze-dependencies

    변경 대상의 의존/피의존·영향 범위 분석 (읽기 전용). MUST USE when: 파일·함수·모듈을 바꾸거나 지우기 전에 그것을 import·호출하는 곳과 깨질 테스트를 확정해야 하거나, 매니페스트의 전이 의존성·버전 충돌을 판정해야 할 때. OUTPUT: 의존 그래프 + 영향 파일 표 + 리스크 - Read - Glob - Grep - Task - Write - Edit - Bash

  • clarify-requirements

    구현 전에 요청의 빠진 결정을 P0~P3 로 등급화하고 P0 만 질문으로 만든다. MUST USE when: 수용 기준·범위·입출력·예외 처리가 빠져 그대로 구현하면 추측이 들어가고, 그 빈칸이 데이터 무결성·보안·결제·외부 계약에 닿을 수 있을 때. OUTPUT: 등급별 모호함 + P0 질문(선택지) - Read - Glob - Grep - AskUserQuestion - Task - Write - Edit - Bash

  • define-business-logic

    도메인 규칙을 ID 붙은 명세로 정의 (읽기 전용 — 반환, 저장은 호출자). MUST USE when: 새 기능이 금액·포인트 산식, 입력 검증 조건, 엔티티 상태 전이, 역할별 허용 동작에 의존하는데 그것이 아직 명세로 없을 때. OUTPUT: CALC/VAL/STATE/AUTH/POL 정의서 - Read - Glob - Grep - Task - Bash - Edit - Write

  • design-user-journey

    사용자 여정 설계 — 진입부터 완료·이탈까지 단계와 로딩·빈 값·에러 처리 (읽기 전용 — 반환, 저장은 호출자). MUST USE when: 온보딩·결제처럼 인터랙션이 여러 단계로 이어지는데 분기 조건·에러 복구·이탈 후 복귀가 아직 설계되지 않았을 때. OUTPUT: 여정 플로우 + 단계별 전이 - Read - Glob - Grep - Task - Bash - Edit - Write

  • devils-advocate

    구현 전 설계·전략 문서의 실패 경로를 찾는 반론가 (읽기 전용, 코드 아님). MUST USE when: 아키텍처·기술 스택·기획서가 결정 직전이고 확장성·외부 의존·유지보수·비용 관점의 실패 시나리오와 숨은 가정을 뽑아야 할 때 (multi-perspective-review 반론 관점 포함). OUTPUT: 실패 시나리오 + 확률 + 완화 방안 - Read - Glob - Grep - Bash - Task

  • fix-bugs

    재현 가능한 결함의 근본 원인을 찾아 기존 파일만 최소 수정. MUST USE when: 스택트레이스·실패하는 테스트·재현 절차가 주어졌고 원인을 확정해 고쳐야 할 때. OUTPUT: 근본 원인 + 수정 요약 + 재현 결과 - Read - Edit - Bash - Glob - Grep - ExitWorktree - Task - Write

  • git-workflow

    다단계 git 조작 수행. 충돌은 풀지 않고 되돌린 뒤 보고. MUST USE when: 분기·병합·리베이스·cherry-pick·히스토리 정리처럼 명령 여러 개를 순서대로 실행해야 하거나 병합 충돌 보고가 필요할 때 (단일 커밋·조회는 인라인). OUTPUT: 실행 명령 + 결과, 또는 충돌 보고 - Bash - Read - Glob - Grep - Task - Write - Edit

  • implement-code

    승인된 계획·명세대로 코드 작성 (API 핸들러·측정된 병목 개선 포함). MUST USE when: 변경할 파일과 기대 동작이 계획·명세로 정해졌고 여러 파일에 걸쳐 코드를 작성해야 할 때. OUTPUT: 변경 파일 + 구현 요약 + 남긴 TODO - Read - Write - Edit - Glob - Grep - Bash - ExitWorktree - Task

  • plan-implementation

    구현 전 설계 — 작업 분해·의존 순서·구조 변경 단계 (읽기 전용). MUST USE when: 여러 파일·레이어에 걸친 변경을 착수하기 전에 배치·순서를 정하거나, 모듈 분리·레이어 재배치·ARCHITECTURE_LIMIT 해소의 이행 경로가 필요할 때. OUTPUT: 배치별 작업 + 기술 결정 + 리스크·롤백 - Read - Glob - Grep - Task - Write - Edit - Bash

  • research-external

    레포 밖 1차 자료(공식 문서·릴리스 노트·이슈)를 웹에서 찾아 출처와 함께 정리. MUST USE when: 답이 레포 안에 없고 외부 API 의 현재 동작·버전 간 breaking change·알려진 이슈를 URL 근거로 확인해야 할 때. OUTPUT: 출처 URL 붙은 조사 결과 - WebSearch - WebFetch - Read - Grep - Task - Write - Edit - Bash

  • review-code

    병합 전 변경분의 적대적 결함 리뷰 (읽기 전용, 작성자와 분리된 컨텍스트). MUST USE when: 완성된 diff 가 병합·릴리스를 앞두고 있어 작성자가 아닌 독립 컨텍스트에서 정확성·경계조건·동시성·회귀를 판정해야 할 때. OUTPUT: REJECT/CONDITIONAL/ACCEPT + 심각도별 결함 - Read - Glob - Grep - Task - Write - Edit - Bash

  • security-scan

    보안 결함 스캔 — 시크릿·인젝션·인증/인가·취약 의존성 (수정 없음). MUST USE when: 변경분이나 코드베이스를 OWASP Top 10·하드코딩 자격증명·안전하지 않은 설정 기준으로 점검해 보안 판정이 필요할 때. OUTPUT: 보안 판정 + 심각도별 취약점 + 확인한 파일 - Read - Glob - Grep - Bash - Task - Write - Edit

  • sync-docs

    코드 변경에 맞춰 기존 문서를 갱신. MUST USE when: 코드 변경이 끝났고 그로 인해 사실이 달라진 README·API 문서·CHANGELOG·에이전트 지침 파일을 코드와 일치시켜야 할 때. OUTPUT: 갱신 문서 + 변경 요약 - Read - Write - Edit - Glob - Grep - ExitWorktree - Task

  • verify-code

    빌드·린트·타입체크·테스트 명령 실행과 연결 정합 점검으로 PASS/FAIL 판정 (수정 없음). MUST USE when: 구현·수정 후 병합·리뷰 전에 실제 명령 결과(rc·출력)와 import·시그니처 정합으로 통과 여부를 확정해야 할 때. OUTPUT: PASS/FAIL + 명령별 rc + 끊어진 연결 - Read - Bash - Glob - Task - Write - Edit

  • write-tests

    지정된 코드에 새 테스트 작성 (API 엔드포인트·TDD 선작성 포함). MUST USE when: 대상 함수·모듈·엔드포인트가 정해졌고 그 동작·경계값·에러 경로를 고정하는 테스트를 새로 쓰거나 TDD 로 구현보다 테스트를 먼저 써야 할 때. OUTPUT: 테스트 파일·케이스 + 실행 결과 - Task - Read - Write - Edit - Glob - Grep - Bash - ExitWorktree

Hooks (5)

  • SessionStart

    python3

  • SessionStart

    python3

  • PreToolUse

    python3

  • PostToolUse

    python3

  • Stop

    python3

View source on GitHub hiway.thishw.com

More from davepoon/buildwithclaude

All 277 plugins →

Complete collection of ~110 Claude Code skills across document processing, development, automation, CRM, DevOps, and more

200 skills

3,741

Complete collection of 174 slash commands across 22 categories

177 commands

3,741

Complete collection of 117 specialized AI agents across 11 categories

117 agents

3,741

gsd

claude

Get Shit Done -- a structured workflow plugin for Claude Code that adds planning, execution, and verification commands with MCP-backed project state

83 skills · 33 agents · 1 MCP server

3,741

forge

claude

Full-lifecycle SDLC orchestrator: a 12-stage pipeline (SRS, architecture, spec, plan, build, eval, deploy, monitor, release) driven by specialized agents, persistent cross-session memory, auto-reflection, gate enforcement, and semantic skill mining that proposes new skills from recurring workflows.

45 skills · 27 agents · hooks

3,741

suede-skills

claudecodex

74 skills for Claude Code and Codex. A build DAG researches your repo, fans out disjoint lanes, and refutes its own review before anything lands. A blunt A-F ship grade blocks the bad merge instead of complimenting it. The same folder designs the page, writes the copy, and ships native iOS and Android builds.

70 skills · 1 MCP server

3,741

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer

8 skills · 1 MCP server

ChromeDevTools/chrome-devtools-mcp 55,181

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Maintain hiway-kit?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins277 plugins