boilerplate-context
Skill2 starsChanged 47 days agoMITView on GitHub
Use when working in this repository to understand the boilerplate's layered documentation system, workitem flow, and guardrail philosophy.
In this repository51 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- accept-milestoneSkill
- bootstrap-projectSkill
- bootstrap-stackSkill
- consult-expertSkill
- design-milestoneSkill
- finalize-workitemSkill
- implement-workitemSkill
- plan-milestoneSkill
- plan-workitemSkill
- repair-acceptanceSkill
- repair-discoverySkill
- repair-milestoneSkill
- repair-planSkill
- repair-workitemSkill
- run-milestoneSkill
- seal-milestoneSkill
- stabilize-milestoneSkill
- stack-guardSkill
- validate-discoverySkill
- validate-milestoneSkill
- validate-planSkill
- validate-workitemSkill
- accept-milestoneSkill
- amend-ssotSkill
- bootstrap-designSkill
- bootstrap-projectSkill
- bootstrap-stackSkill
- consult-expertSkill
- design-milestoneSkill
- discover-productSkill
- finalize-workitemSkill
- implement-workitemSkill
- plan-milestoneSkill
- plan-workitemSkill
- repair-acceptanceSkill
- repair-discoverySkill
- repair-milestoneSkill
- repair-planSkill
- repair-workitemSkill
- research-packSkill
- review-docSkill
- run-milestoneSkill
- seal-milestoneSkill
- stabilize-milestoneSkill
- stack-guardSkill
- validate-discoverySkill
- validate-milestoneSkill
- validate-planSkill
- validate-workitemSkill
The file
Files
이 저장소는 Claude Code용 문서 중심 보일러플레이트다.
핵심 구조와 산출물 인벤토리: docs/00-meta/STRUCTURE.md 워크플로우와 문서 상태 전이: docs/00-meta/WORKFLOW.md 에이전트 위임 전략: docs/00-meta/DELEGATION_STRATEGY.md Guardrail 원칙: docs/00-meta/GUARDRAILS_STRATEGY.md
기본 진입점:
- 프로젝트 초기 세팅이 필요하면
/bootstrap-project를 우선 사용한다. - 스택 자동화 세팅이 필요하면
/bootstrap-stack을 사용한다.
Codex: 본 skill은 wrapper 미보유(자연어 호출) — Codex에서는 "Follow .claude/skills/boilerplate-context/SKILL.md"로 호출한다(목록 SSOT = README, ADR-010#amend-3·#amend-4).
Context 정책 (ADR-019)
반드시 먼저 읽을 파일은 최소 충분. 추가 ADR/architecture 섹션은 task 본문에서 발화 시 인용 — 사전 fork-load 금지.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.