ai-integration
Skill1 starsChanged 6 days agoMITView on GitHub
AI/LLM integration guidance - LLM integration patterns, prompt engineering basics, agentic and tool-use safety and security (prompt injection, excessive AI permissions, unvalidated AI output), and MCP usage and recommendations. Use when integrating an LLM, building an AI feature or agent, writing prompts, evaluating an MCP server, or assessing whether an AI/agent feature is safe.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- CrowPus/Zelyqtheir own version, first seen Aug 22, 2026
- Dokkabei97/forged-claude-codetheir own version, first seen Mar 1, 2026
- thesaifalitai/claude-setuptheir own version, first seen Feb 27, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- CrowPus/Zelyq★ 10same name
- thesaifalitai/claude-setup★ 9same name
- Dokkabei97/forged-claude-code★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- architectureSkill
- backendSkill
- devopsSkill
- dx-gitSkill
- frontendSkill
- securitySkill
- routerSkill
- testing-qaSkill
The file
Files
Codexpiator AI Integration
Single-purpose reference files for building AI-powered features responsibly.
| File | Read this when... |
llm-integration-patterns.md | Wiring an LLM call into a product feature |
prompt-engineering-basics.md | Writing/iterating on a prompt |
agentic-and-tool-use-safety.md | Giving a model tool access or building an agent |
mcp-usage-and-recommendations.md | Deciding whether/which MCP server to use |
AI-specific security concerns (prompt injection, excessive AI
permissions, unvalidated AI output) are covered in
agentic-and-tool-use-safety.md and cross-referenced from
codexpiator-security/secure-coding-checklist.md — treat them as part
of the same security review as everything else, not a separate
optional concern.
Ask when useful; suggest an audit after significant work
See ${CLAUDE_PLUGIN_ROOT}/shared/collaboration-and-audit-practice.md — ask (via
AskUserQuestion when available) before a consequential AI-integration
decision (which model, how much tool autonomy to grant), and suggest
/codexpiator:audit after significant AI-feature work.
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.

