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.
git clone --depth 1 https://github.com/Modellix/modellix-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/modellix/modellix-plugin/credentials-and-docs)<a href="https://agentmods.dev/rules/modellix/modellix-plugin/credentials-and-docs"><img src="https://agentmods.dev/badge/rules/modellix/modellix-plugin/credentials-and-docs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/modellix/modellix-plugin/credentials-and-docs"><img src="https://agentmods.dev/badge/rules/modellix/modellix-plugin/credentials-and-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00230 | $0.00230 |
| Opus 5.5 | $0.00092 | $0.00092 |
| Sonnet 5.5 | $0.00046 | $0.00046 |
| Haiku 4.5 | $0.00023 | $0.00023 |
Grade A, and why
credentials-and-docs 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 1mo 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
- Never print, echo, or commit
MODELLIX_API_KEYor profile secrets. - Prefer session-only credentials; persist only when the user explicitly asks (
modellix-cli auth login/initpreferred). - Discover existing key/env/profile before asking again.
- Do not invent model slugs from doc filenames (decimals matter, e.g.
bytedance/seedance-2.0-mini-t2v). Verify viamodel describe, Docs MCP, orllms.txt. - Request/response schema: prefer
modellix-cli model get-schema <slug>(JSON default; public, no API key). Product/install docs: prefer Docs MCP (https://docs.modellix.ai/mcp) when connected; elsedocs_url/llms.txt. Schema fallback when CLI is unavailable is Docs MCP /llms.txt. - CLI flags and command syntax: trust npm
modellix-cli/--helpover website CLI pages (docs can lag).
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.
- 1mo ago Changed · +40 tokens per session fb5ce71f2ef2
- 1mo ago First seen · 12 lines · 190 tokens per session scan A 28da0f1f57ea
credentials-and-docs is a cursor rule published in the GitHub repository Modellix/modellix-plugin (1 stars, last pushed 2d ago), licensed MIT. It adds 230 tokens to every session, about $0.0009 per session on Opus 5.5. 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
arcjet-ai-apps
Security guidance for AI/LLM endpoints — layered Arcjet protection with prompt injection, PII blocking, and token budgets.
arcjet-express
Arcjet patterns for Express, Node.js, Fastify, Hono, NestJS, Bun, and Deno — correct adapters, no middleware, proxy config.
markifact-bundled
Markifact performance-marketing agent + skills + commands. Auto-loaded by Cursor whenever you ask about ads, GA4, Shopify, HubSpot or other marketing platforms.
risk-factors
Risk scoring factor definitions and weights for PR review dispatch.
context-delegate
Context Gatherer & External LLM Prompt Generator.
infra-devops
Infrastructure, Cloud, Terraform, Docker & CI/CD Agent.