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-directory-structuregit clone --depth 1 https://github.com/codekiln/logseq-cursor-rulesWhat 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 | $0.00010 | $0.00344 |
| Opus 5 | $0.00005 | $0.00172 |
| Sonnet 5 | $0.00002 | $0.00069 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
logseq-directory-structure 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.
What it actually says
Logseq Directory Structure
logseq-graph- the root of the logseq graph. In some projects, this is the root of the git repo. In others, the logseq root is a folder inside of the git root directory. The name of this is unique to the graph.logseq-graph/pages/*.md- All the pages in the graph that are not journal pages are stored here.- Logseq will not create markdown files in subfolders of
pages/*/*.md, but if a markdown file is placed in a subfolder ofpages, logseq will be able to read and edit it. Logseq has a requirement that each page have a unique file name across the whole graph. Ifpages/cars.mdexists, if acars.mdfile is placed anywhere else in the repository, Logseq will display an error. - logseq supports special hierarchies called "namespaces". A page with the title or "namespace"
[[Project/Tasks]]is stored asProject___Tasks.mdinpages/. Triple underscores delimit the hierarchical components.
- Logseq will not create markdown files in subfolders of
logseq-graph/journals/YYYY_MM_DD.md- Contains daily journal entrieslogseq-graph/assets/- Stores images, pdfs and other attachments that are referenced in markdown files via relative links.logseq-graph/logseq/- Configuration directory for the logseq graph. You typically shouldn't edit this..gitignore- Standard Git ignore file (if using Git)
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 · 15 lines · 10 tokens per session scan A 77f24043873f
logseq-directory-structure is a cursor rule published in the GitHub repository codekiln/logseq-cursor-rules (2 stars, last pushed 10mo ago), licensed MIT. It adds 10 tokens to every session and 344 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.
Other cursor rules, from other repositories
new_features
Guidelines for integrating new features into the Task Master CLI.
utilities
// ✅ DO: Create focused, reusable utilities /.
dev_workflow
Guide for using Taskmaster to manage task-driven development workflows.
mcp
Guidelines for implementing and interacting with the Task Master MCP Server.
tests
Guidelines for implementing and maintaining tests for Task Master CLI.
commands
Guidelines for implementing CLI commands using Commander.js.