ai-coding-agent-toolkit / examples
CLAUDE.md27 starsChanged 9 months agoMITView on GitHub
In this repository14 other files it gives its agents.
- backend-patternsSkill
- eval-harnessSkill
- frontend-patternsSkill
- iterative-retrievalSkill
- java-coding-standardsSkill
- jpa-patternsSkill
- kafka-patternsSkill
- postgres-patternsSkill
- python-patternsSkill
- python-testingSkill
- security-reviewSkill
- springboot-patternsSkill
- springboot-securitySkill
- springboot-tddSkill
The file
We split this CLAUDE.md into the rules it gives an agent
7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Don't over-engineer. Build what's asked, nothing more.
- Distinctive: line 15
If something can break, tell me upfront before I find out later.
- Distinctive: line 16
When creating a new project, always generate a CLAUDE.md in the project root with project overview, tech stack, how to run, project …
- Distinctive: line 34
No emojis in code or comments
- Distinctive: line 35
Keep responses concise and practical
- Distinctive: line 37
When I ask about system design, explain trade-offs not just the "right" answer
- Distinctive: line 38
If I'm building something that has a well-known anti-pattern, warn me
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Personal Claude Code Config
About Me
- Backend-heavy full-stack developer
- Primary stack: Java 17 + Spring Boot 3, Python 3.12 + FastAPI, JavaScript (Express.js + React)
- Databases: PostgreSQL, MongoDB, Redis
- AI/ML: RAG, MCP servers, agents, ADK, vector databases
- Infrastructure: Docker, Kubernetes, Kafka, Flink
- Currently learning system design
How I Work
- I prefer working inside projects — give me context and I build.
- Plan before coding on anything non-trivial. Ask me clarifying questions if requirements are ambiguous.
- Don't over-engineer. Build what's asked, nothing more.
- If something can break, tell me upfront before I find out later.
- When creating a new project, always generate a CLAUDE.md in the project root with project overview, tech stack, how to run, project structure, and key decisions.
My Rules
Detailed guidelines are in ~/.claude/rules/:
| File | Covers |
| coding-style.md | Immutability, naming, file organization |
| java-springboot.md | Java 17, Spring Boot 3, Redis, Kafka |
| python-backend-ai.md | FastAPI, RAG, MCP, ADK, vector DBs, ML |
| javascript.md | Express.js, React |
| databases.md | PostgreSQL, MongoDB, Redis |
| infra.md | Docker, K8s, Kafka, Flink |
| git-workflow.md | Conventional commits, branching, PRs |
| testing.md | TDD, 80% coverage, JUnit/pytest/Jest |
| security.md | Auth, secrets, API security, container security |
Preferences
- No emojis in code or comments
- Keep responses concise and practical
- Show me the "why" when suggesting architectural decisions
- When I ask about system design, explain trade-offs not just the "right" answer
- If I'm building something that has a well-known anti-pattern, warn me
OS
- Windows (use cross-platform commands when possible)
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.