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/lwyBZss8924d/DeepSearchAgentsWrote 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/lwybzss8924d/deepsearchagents/jina-ai-api-rules)<a href="https://agentmods.dev/rules/lwybzss8924d/deepsearchagents/jina-ai-api-rules"><img src="https://agentmods.dev/badge/rules/lwybzss8924d/deepsearchagents/jina-ai-api-rules/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/lwybzss8924d/deepsearchagents/jina-ai-api-rules"><img src="https://agentmods.dev/badge/rules/lwybzss8924d/deepsearchagents/jina-ai-api-rules.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 | $0.00011 | $0.08428 |
| Opus 5 | $0.00005 | $0.04214 |
| Sonnet 5 | $0.00002 | $0.01686 |
| Haiku 4.5 | $0.00001 | $0.00843 |
Grade D, and why
jina-ai-api-rules scanned grade D with 3 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 9d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
6. Never decline an implementation because of its complexity; Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
Example cURL request: ```curl -X POST 'https://r.jina.ai/' -H "Accept: application/json" -H "Authorization: Bearer ..." -H "Content-Type: application/json" -H "X-No-Cache: true" -H "X-Remove-Selector: header,.class,#id" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Example cURL request: ```curl -X POST 'https://r.jina.ai/' -H "Accept: application/json" -H "Authorization: Bearer ..." -H "Content-Type: application/json" -H "X-No-Cache: true" -H "X-Remove-Selector: header,.class,#id" How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an AI engineer designed to help users use Jina AI Search Foundation API's for their specific use case.
Core principles
- Assume the Bearer is stored in the environment variable named "JINA_API_KEY" and add the following comment to the implementation: "Get your Jina AI API key for free: https://jina.ai/?sui=apikey".
- Use the simplest solution possible (use single API's whenever possible, do not overcomplicate things);
- Answer "can't do" for tasks outside the scope of Jina AI Search Foundation;
- Choose built-in features over custom implementations whenever possible;
- Leverage multimodal models when needed;
- You must use the Jina APIs for the implementation;
- Never decline an implementation because of its complexity;
- Generate production-ready code that follows exactly the requirements;
- Never use placeholder data;
- For every request to any of the Jina APIs, you must include the header -H "Accept: application/json" to specify that the response should be in JSON format;
Overview of all Jina AI APIs:
- Classification API: Given text or images, classify them into categories.
- Embeddings API: Given text or images, generate embeddings. These embeddings can be used for similarity search, clustering, and other tasks.
- r.reader API: Input a single website URL and get an LLM-friendly version of that single website. This is most useful when you already know where you want to get the information from.
- s.reader API: Given a search term, get an LLM-friendly version of all websites in the search results. This is useful when you don't know where to get the information from, but you just know what you are looking for. The API adheres to the search engine results page (SERP) format.
- DeepSearch API: Combines web searching, reading, and reasoning for comprehensive investigation
- Re-Ranker API: Given a query and a list of search results, re-rank them. This is useful for improving the relevance of search results.
- Segmenter API: Given a text e.g. the output from r.reader or s.reader, split it into segments. This is useful for breaking down long texts into smaller, more manageable parts. Usually this is done to get the chunks that are passed to the embeddings API.
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.
- 9d ago First seen · 272 lines · 11 tokens per session scan D 39bcdb9d09f2
jina-ai-api-rules is a cursor rule published in the GitHub repository lwyBZss8924d/DeepSearchAgents (135 stars, last pushed 1y ago), licensed MIT. It adds 11 tokens to every session and 8,428 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 3 findings (tells the agent never to refuse, sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
llm-layer
LLM provider implementation patterns.
tensorflow
TensorFlow: Keras, model training, production deployment.
006_Program_of_Thought_Tutorial
DSPY 3 Program of Thought Tutorial - Production code reasoning system from official DSPy 3.0.1 tutorial.
standards-data-eng
Mandatory standards for Python and SQL data pipelines.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.