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/typical-week-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 | $0.00000 | $0.02000 |
| Opus 5 | $0.00000 | $0.01000 |
| Sonnet 5 | $0.00000 | $0.00400 |
| Haiku 4.5 | $0.00000 | $0.00200 |
Grade A, and why
typical-week-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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Once a week setup to prepare week markdown files
- be familiar with logseq-directory-structure.mdc
- Look at the files that match the glob
pages/2025___t1___w14*.mdto find the pattern of what the pages should look like.
Preparation - Setting up the links
- the first step is to update Logseq___Template___Today___Link.md to the next week. the user will tell you which week to update this to.
- the next step is to have the user instantiate the current week logseq template Logseq___Template___Week___Current.md inside the current week's markdown page, which will follow the template of
pages/YYYY___tT___wWW.md, where YYYY is the year, T is the trimester (1, 2, 3), and WW is the week number of the trimester (zero-padded). - The user may ask you to fill in the days of the week in the current week's page so they can take some notes under them.
Filling out the day page headers
- given the user's requested week number, set up the week's day pages to match the pattern of week 14
- important note: the agendas and days for the current week will likely be different than week 14!
- there should be two files created for each day of the week, 1-7. The first will be for the day, the second will be for the todos for that day.
- for each day's page I instantiate the logseq template [Logseq___Template___Today___Page Skeleton.md](mdc:pages/Logseq___Template___Today___Page Skeleton.md)
- for each day's today page I instantiate the logseq template Logseq___Template___Today___Todos___Skeleton.md
- DO NOT INVENT PAGE LEVEL ATTRIBUTES - I'm hoping you can basically simulate instantiating the logseq template for each day.
- in particular, note the links to the next and previous day in the header, particularly at d1 and d7 since those will reference the previous and next week, respectively. Also, note the relationship between the day files and the week files.
- "up" in the page properties refers to the page "up" in the logseq namespace.
- for example, [[2025/t1/w07]] is "up" from [[2025/t1/w07/Todos]]
- Special note for trimester boundaries:
- Trimester 1: Jan 1 to the day before Memorial Day
- Trimester 2: Memorial Day to the day before Labor Day
- Trimester 3: Labor Day to Dec 31
- When a week is at the end or beginning of a trimester, the
prevandnextlinks in the week and day pages should point to the last week of the previous trimester or the first week of the next trimester, respectively. For example, the week before Memorial Day (end of T1) should have itsnextlink point to the first week of T2, and the week before Labor Day (end of T2) should have itsnextlink point to the first week of T3. Similarly, the first week of a trimester should have itsprevlink point to the last week of the previous trimester.
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 · 94 lines · 0 tokens per session scan A c79cf01e8dd7
typical-week-structure is a cursor rule published in the GitHub repository codekiln/logseq-cursor-rules (2 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,000 tokens. 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.