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/evaluation-rulesgit clone --depth 1 https://github.com/TimoBakx/ai-journaling-templateWhat 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 | $0.00715 |
| Opus 5 | $0.00005 | $0.00358 |
| Sonnet 5 | $0.00002 | $0.00143 |
| Haiku 4.5 | $0.00001 | $0.00072 |
Grade A, and why
evaluation-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 2d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluation Rules - Week Evaluations
Purpose of Evaluations
Weekly evaluations are deeper reflection moments where we:
- Analyze patterns that have become visible throughout the week
- Develop insights that emerged during daily reflections
- Make connections between experiences, feelings and learning moments
- Link learning goals and work evaluations to concrete weekly experiences
- Prepare for check-ins with supervisors
When to Evaluate
- End of week - when filling in the weekly evaluation (
week-evaluation.md) - Use template -
journal/weekly-review-template.md - Covers full week - all 5 workdays + patterns that emerge
Template Structure
Use journal/weekly-review-template.md when creating new weekly evaluations.
Structure Elements
📅 This Week
- Overview of all days with links
- Short summary per day
🔍 Reflection & Patterns
- 🎯 Major Themes This Week - what were the main topics?
- 📊 Learning Goals Progress & Concrete Examples - what changes have become visible?
- 🧠 Self-Insight & Profile Confirmations (Brief) - how do you see yourself looking back?
- 💡 Actions Next Week - what are we going to work on?
- 🌟 Week Summary - very briefly what was revealed in the past week
My Approach to Evaluations
Challenging Guidance
- Probing on major insights - "Is this the right direction?" with complex observations
- Probing on ambiguities - "What exactly do you mean?" in ambiguous situations
- Gently pointing out blind spots - "Have you thought about this?" or "Maybe this fits better with that person?"
Linking with Learning Goals
- Link to work evaluations - connect concrete weekly experiences to development points from annual reviews
- Link to personal growth plan - connect patterns with growth goals
- Concrete examples - build concrete examples for next evaluation/check-in
Analyzing Patterns
- Connect the days - what theme connects the different days this week?
- Recognize trends - do you see patterns that were also visible earlier?
- Show evolution - how does this week show growth compared to earlier weeks?
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.
- 2d ago First seen · 78 lines · 10 tokens per session scan A cd36a9e3af11
evaluation-rules is a cursor rule published in the GitHub repository TimoBakx/ai-journaling-template (32 stars, last pushed 8mo ago), licensed MIT. It adds 10 tokens to every session and 715 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 2026-08-30.
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.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.