What is logseq-ai-model-reference?

A Logseq naming rule for briefly linking to AI models, such as models from OpenAI, Anthropic, Google, DeepSeek, or xAI.

Use it when writing changelogs, comparisons, model lists, or stub pages for AI models.

It keeps model references consistent without requiring a full documentation page for every mention.

logseq-ai-model-reference — Cursor rule by codekiln

Install

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.

agentmods

npx agentmods add rules/codekiln/logseq-cursor-rules/logseq-ai-model-reference

Clone the repo

git clone --depth 1 https://github.com/codekiln/logseq-cursor-rules

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 670 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00013	$0.00670
Opus 5	$0.00006	$0.00335
Sonnet 5	$0.00003	$0.00134
Haiku 4.5	$0.00001	$0.00067

Measured yesterday against content hash 072c312f6f3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

logseq-ai-model-reference 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 yesterday.

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.

logseq-ai-model-reference.mdc · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Model Reference Quick Guide

This rule extends logseq-naming-conventions.mdc for quickly referencing AI models in the knowledge graph without creating detailed pages.

When to Use This Rule

When mentioning a model in passing
When creating changelog entries
When comparing models
When listing available models
When creating stub pages for future detailed documentation

Quick Reference Format

Provider Namespaces

[[OpenAI/Model/...]] - For OpenAI models
[[Anthropic/Model/...]] - For Anthropic models
[[Google/AI/Model/...]] - For Google models
[[DeepSeek/Model/...]] - For DeepSeek models
[[xAI/Model/...]] - For xAI/Grok models

Version Format

Use forward slashes for version hierarchy
Example: [[OpenAI/Model/GPT/4/1]] for GPT-4.1
Example: [[Anthropic/Model/Claude/3.5/Sonnet]] for Claude 3.5 Sonnet

Quick Stub Page Creation

When creating a stub page for a new model:

Create the page with minimal frontmatter:

---
alias:: [[model-name]]
tags:: [[AI/Model]]
---

Add a basic structure:

- # Model Name
  - *Stub page - detailed documentation pending*

Add the model to the appropriate provider's model list page if it exists

Examples

<CORRECT_✅>

- ### New models
  - Added [[Google/AI/Model/Gemini/2.5/Pro]], [[Google/AI/Model/Gemini/2.5/Flash]]
  - Added [[xAI/Model/Grok/3]], [[xAI/Model/Grok/3/Mini]]
  - Added [[OpenAI/Model/GPT/4/1]], [[OpenAI/Model/o3]] and [[OpenAI/Model/o4/Mini]]

</CORRECT_✅>

<INCORRECT_❌>

- ### New models
  - Added Gemini 2.5 Pro, Gemini 2.5 Flash
  - Added Grok 3, Grok 3 Mini
  - Added GPT-4.1, o3 and o4-mini

</INCORRECT_❌>

Best Practices

Always use the full namespace path when referencing models
Create stub pages for new models to maintain consistency
Use aliases for common model references
Link to existing model pages when available
Follow the singular naming convention from logseq-naming-conventions.mdc

Read the full file on GitHub · 83 lines

Changes

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.

yesterday First seen · 83 lines · 13 tokens per session scan A 072c312f6f3b

Subscribe to this mod's changes

logseq-ai-model-reference is a cursor rule published in the GitHub repository codekiln/logseq-cursor-rules (2 stars, last pushed 10mo ago), licensed MIT. It adds 13 tokens to every session and 670 once invoked, about $0.0001 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.

Data and AI Writing and docs cursor-ai cursor-ai-project-rules cursorai logseq

logseq-ai-model-reference

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AI Model Reference Quick Guide

When to Use This Rule

Quick Reference Format

Provider Namespaces

Version Format

Quick Stub Page Creation

Examples

Best Practices

What this file has done since we first saw it

Other cursor rules, from other repositories

new_features

utilities

dev_workflow

mcp

tests

commands