journaling-rules

journaling-rules is a cursor rule for Cursor from TimoBakx/ai-journaling-template. It costs 639 tokens per session, scanned A, original, MIT.

Rules for keeping a brief daily journal in a project knowledge base. Entries record factual events, plans, observations, and links to related projects.

In plain words
What is it for?
Use it when creating or filling daily journal files, recording work and events, linking projects, summarizing the day, or checking emerging patterns.
Why use it?
It keeps daily notes specific and consistent so they can support later reflection and pattern analysis.

Cursor rule for Cursor

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/timobakx/ai-journaling-template/journaling-rules
Clone the repo
git clone --depth 1 https://github.com/TimoBakx/ai-journaling-template

Made for: Cursor.

Wrote 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.

agentmods badge for journaling-rules

README.md
[![agentmods](https://agentmods.dev/badge/rules/timobakx/ai-journaling-template/journaling-rules.svg)](https://agentmods.dev/rules/timobakx/ai-journaling-template/journaling-rules)
Your own site
<a href="https://agentmods.dev/rules/timobakx/ai-journaling-template/journaling-rules"><img src="https://agentmods.dev/badge/rules/timobakx/ai-journaling-template/journaling-rules.svg" alt="Measured on agentmods" height="20"></a>
Per session 639 This file is loaded in full into every session.
When invoked 639 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00639 $0.00639
Opus 5 $0.00319 $0.00319
Sonnet 5 $0.00128 $0.00128
Haiku 4.5 $0.00064 $0.00064

Measured 4d ago against content hash 9fe81b3a46e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

journaling-rules 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 4d 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.

.cursor/rules/journaling-rules.mdc · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

📝 Journaling Rules - Daily Workflow

Purpose of Daily journaling

Daily journaling is brief and specific - what happened, short observations, concrete facts. This forms the foundation for deeper analysis during evaluations.

Daily Routine

  1. Keep project open long - this knowledge base stays active
  2. Daily chat sessions - fill journal file together
  3. Throughout the day - processing and probing when needed
  4. End of day - summarize and check patterns

Template Structure

Daily Template File

Use journal/daily-journal-template.md when creating new daily journal files.

Structure Elements

🎯 Planned
  • Simple planning with emoji
  • No extensive energy/feeling checks
  • Tasks can contain project links: - [ ] ([Project Name](../../projects/project.md)) task
📝 Daily Flow - Events
  • Brief facts without forced substructure or timestamps
  • No timestamps - many people switch frequently between projects
  • Direct project links in headers: ### ([Project](/link)) Activity
  • Running text instead of bullet point structures where possible
  • No sub-sub headers that are bold, make it a running story.
  • What really happened? Factual observations per activity
🔍 End of Day - Reflection
  • Minimal reflection section, space for filling in together
  • See reflection-rules.mdc for extensive reflection methodology
📋 Tasks for Later
  • Important tasks that don't happen today

Template Design Principles

  • Clean and practical - no quotes, footers or excessive structure
  • Direct project links in headers: ### ([Project](/link)) Activity
  • Inline cross-linking - no separate "Tags & Projects" sections
  • Real subheaders instead of bold "fake headers"
  • Running text instead of bullet point structures where possible

File Naming & Location

  • Templates in /journal/ - more logical than separate folder
  • Daily files: [DAY_NUMBER]-[day]-[DATE].md (e.g. 1-monday-2025-10-27.md)
  • Journal is "namespaced" by year and week: journal/[YEAR]/[WEEK_NUMBER]/

Read the full file on GitHub · 71 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.

  1. 4d ago First seen · 71 lines · 639 tokens per session scan A 9fe81b3a46e2

Subscribe to this mod's changes

journaling-rules is a cursor rule published in the GitHub repository TimoBakx/ai-journaling-template (32 stars, last pushed 8mo ago), licensed MIT. It adds 639 tokens to every session, about $0.0032 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 2026-08-30.