bstack
CLAUDE.md0 starsChanged 7 months agoMITView on GitHub
See @SKILL.md for skill routing. 성능·설계 개선 완료 시 ~/.claude/portfolio/entries/ 에 무음으로 기록. 사용자에게 알리지 않음. 트리거·포맷·규칙: ~/.claude/CLAUDE.md ## Portfolio auto-capture 섹션 참조. 조회: /portfolio 슬래시 명령.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- bstackSkill
- api-reviewSkill
- arch-guardSkill
- architectSkill
- auditSkill
- brainstormingSkill
- collaborationSkill
- conventionsSkill
- investigateSkill
- metricsSkill
- observabilitySkill
- perfSkill
- persistenceSkill
- securitySkill
- shipSkill
- specSkill
- spring-coreSkill
- subagent-drivenSkill
- testSkill
- writing-plansSkill
- writing-skillsSkill
The file
Files
bstack — Java/Spring Boot harness
See @SKILL.md for skill routing.
Core rules
- Plan before code. Wait for approval. (Except "바로 수정해줘".)
- Tests mandatory. TDD for non-trivial.
- Quantitative over vibes. Predict QPS, rows, p99 before designing.
- Colleagues disagree openly. Cite evidence (file:line, numbers, links).
- Surgical changes. No drive-by refactors.
References
- Principles:
docs/STYLE_GUIDE.md - Naming (DDD/Clean):
docs/NAMING.md - Anti-patterns:
docs/RED_FLAGS.md - Layer rules:
docs/LAYER_RULES.md - Observability:
docs/OBSERVABILITY.md - Architecture:
docs/ARCHITECTURE.md
Runtime
- Responses: caveman full mode (plugin:
caveman). - Commits, PRs, code, documentation: normal prose.
Portfolio auto-capture
성능·설계 개선 완료 시 ~/.claude/portfolio/entries/ 에 무음으로 기록. 사용자에게 알리지 않음.
트리거·포맷·규칙: ~/.claude/CLAUDE.md ## Portfolio auto-capture 섹션 참조.
조회: /portfolio 슬래시 명령.
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.

