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/codekiln/logseq-cursor-rules/logseq-ai-model-details-pagegit clone --depth 1 https://github.com/codekiln/logseq-cursor-rulesWrote 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/codekiln/logseq-cursor-rules/logseq-ai-model-details-page)<a href="https://agentmods.dev/rules/codekiln/logseq-cursor-rules/logseq-ai-model-details-page"><img src="https://agentmods.dev/badge/rules/codekiln/logseq-cursor-rules/logseq-ai-model-details-page.svg" alt="Measured on agentmods" 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 | $0.00007 | $0.00852 |
| Opus 5 | $0.00003 | $0.00426 |
| Sonnet 5 | $0.00001 | $0.00170 |
| Haiku 4.5 | $0.00001 | $0.00085 |
Grade A, and why
logseq-ai-model-details-page 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Model Detailed Documentation Guide
This rule extends logseq-naming-conventions.mdc for creating comprehensive AI model documentation pages.
When to Use This Rule
- When creating detailed model documentation for a specific model version
- When documenting model capabilities and benchmarks for a particular release
- When creating model comparison pages
- When the model is a primary focus of discussion
- When detailed technical specifications are needed
Page Creation Process
1. Research Model Information
- Search for official model cards and documentation
- Look for benchmark results and performance metrics
- Find pricing and availability information
- Gather technical specifications
- Identify the specific model version code (e.g.,
gemini-2.5-pro-preview-05-06)
2. Create Page Structure
---
alias:: [[model-code]]
tags:: [[AI/Model]]
---
- # [Model Name](official-documentation-url)
- ## Key Features
- List major capabilities and improvements
- Include context window size
- Note knowledge cutoff date
- Specify model version status (stable/preview/experimental)
- ## Performance Highlights
- Include benchmark results
- Link to benchmark pages
- Note performance improvements
- ## Model Tiers (if applicable)
- List available variants
- Compare capabilities
- Note pricing differences
- ## Access Details
- API availability
- Pricing information
- Usage limitations
- Rate limits
- ## Technical Specifications
- Model architecture
- Training data
- Input/output formats
- Special capabilities
- Model version code
- ## References
- Link to official documentation
- Link to research papers
- Link to benchmark results
3. Required Research Sources
- Official model documentation
- Model cards
- Research papers
- Benchmark results
- Pricing pages
- API documentation
Examples
<CORRECT_✅>
- # [GPT-4.1](https://platform.openai.com/docs/models/gpt-4.1)
- ## Key Features
- New family of models: GPT-4.1, GPT-4.1 Mini, and GPT-4.1 Nano
- Major improvements in coding, instruction following, and long-context understanding
- Supports up to 1 million tokens context window
- Knowledge cutoff: [[2024/06]]
</CORRECT_✅>
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.
- 3d ago First seen · 118 lines · 7 tokens per session scan A 08c47ad574cf
logseq-ai-model-details-page is a cursor rule published in the GitHub repository codekiln/logseq-cursor-rules (2 stars, last pushed 11mo ago), licensed MIT. It adds 7 tokens to every session and 852 once invoked, about $0.0000 per session on Opus 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
mcp
Guidelines for implementing and interacting with the Task Master MCP Server.
new_features
Guidelines for integrating new features into the Task Master CLI.
tests
Guidelines for implementing and maintaining tests for Task Master CLI.
utilities
// ✅ DO: Create focused, reusable utilities /.
commands
Guidelines for implementing CLI commands using Commander.js.
dev_workflow
Guide for using Taskmaster to manage task-driven development workflows.