evaluation-rules

Rules for reviewing a full workweek through a weekly evaluation. The review connects daily experiences with patterns, learning goals, work progress, and plans for the next week.

In plain words
What is it for?
Use it when creating weekly reviews, examining recurring themes, tracking learning goals, confirming self-insights, or planning next actions.
Why use it?
It turns scattered daily notes into structured reflection and concrete examples for learning and supervisor check-ins.

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

Made for: Cursor.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 715 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00010 $0.00715
Opus 5 $0.00005 $0.00358
Sonnet 5 $0.00002 $0.00143
Haiku 4.5 $0.00001 $0.00072

Measured 2d ago against content hash cd36a9e3af11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.cursor/rules/evaluation-rules.mdc · 78 lines

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?

Read the full file on GitHub · 78 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. 2d ago First seen · 78 lines · 10 tokens per session scan A cd36a9e3af11

Subscribe to this mod's changes

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.