Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add rules/kleosr/kleosrules/vibegit clone --depth 1 https://github.com/kleosr/kleosrulesWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00359 |
| Opus 5 | $0.00000 | $0.00179 |
| Sonnet 5 | $0.00000 | $0.00072 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
vibe scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Vibe
Prefer retrieval-led reasoning over pre-training. Do not dump framework AGENTS.md.
GROUND: Read this package's package.json (monorepo: the nearest one). Pick one stack. Do not mix APIs.
| Detect | Then |
|---|---|
"next" |
next.mdc. Docs: node_modules/next/dist/docs/ (resolve from the app package). |
"astro" |
astro.mdc. Docs MCP / docs.astro.build, not training. |
"vite" and no next |
vite.mdc. |
| none of the above | Neighbors only. No Next/Astro/Vite APIs. |
Then Read one skill: ponytail, or vercel-react-best-practices rules/<one>.md if the stack is React.
Hard (all JS/TS)
- No
useEffectdata-fetch waterfalls. Parallel independent awaits. - No barrel-import of a whole UI kit.
- Derived state, not mirrored
useState+useEffect. - Named exports. Early return. Nesting >2 banned.
- Cyclomatic:
complexity.mdc. Repo cap, else 10. Do not disable the rule. - Match 1–2 siblings in the directory before Write.
- Do not invent RSC,
getServerSideProps, orclient:*unless this stack has them.
Subagents inherit this. Do not paste into Task prompts.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 33 lines · 0 tokens per session scan A 38db032c7024
vibe is a cursor rule published in the GitHub repository kleosr/kleosrules (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 359 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
typescript
Rules applied when working in TypeScript or JavaScript files.
zod
Zod: validation schemas, transforms, refinements, error handling.
typescript
Strict TypeScript: generics, discriminated unions, no any.
nestjs
NestJS: decorators, modules, guards, interceptors, DTOs.
typescript
TypeScript 编码规则和最佳实践.
typescript
TypeScript Development Standards.