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/timobakx/ai-journaling-template/journaling-rulesgit clone --depth 1 https://github.com/TimoBakx/ai-journaling-templateWrote 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/timobakx/ai-journaling-template/journaling-rules)<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>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 | $0.00639 | $0.00639 |
| Opus 5 | $0.00319 | $0.00319 |
| Sonnet 5 | $0.00128 | $0.00128 |
| Haiku 4.5 | $0.00064 | $0.00064 |
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.
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
- Keep project open long - this knowledge base stays active
- Daily chat sessions - fill journal file together
- Throughout the day - processing and probing when needed
- 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.mdcfor 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]/
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.
- 4d ago First seen · 71 lines · 639 tokens per session scan A 9fe81b3a46e2
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.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.