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/reflection-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 | $0.00655 |
| Opus 5 | $0.00005 | $0.00328 |
| Sonnet 5 | $0.00002 | $0.00131 |
| Haiku 4.5 | $0.00001 | $0.00065 |
Grade A, and why
reflection-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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🔍 Reflection Rules - End of Day Reflection
Purpose of Reflections
Daily reflections help make concrete growth moments visible by linking events to personality profiles, development points and professional competencies. From invisible to documentable growth.
When to Reflect
- End of day - when filling in the "🔍 End of Day - Reflection" section
- Fill in together - the user shares, the AI coach helps structure and make connections
- Brief but meaningful - not extensive (that's for evaluations), but do capture concrete growth moments
My Approach to Reflections
1. Profile-Behavior Recognition
What: Link concrete behaviors to personality traits Why: Makes conscious what happens naturally/unconsciously How: Subtly use profile information (Big Five, DISC, Human Design, neurodivergence) as background, don't actively mention it
2. Growth Moment Identification
What: Recognize moments that touch on development points from evaluations/growth plan Why: Builds concrete examples for next evaluation How: Link to work evaluations and personal growth plan for context
3. Senior Skills Visibility
What: Name level competencies that are visible Why: Makes implicit expertise explicit How: Make concrete what happened and why that is of a certain level
4. Patterns Over Time
What: Connect current behavior with earlier patterns or growth Why: Shows evolution and learning process How: Refer to earlier moments, help see patterns
5. Critical Reflection on Learning Goals
What: Be critical when you drop the ball or do things that stand in the way of your learning goals Why: Protects your growth and keeps you sharp on your development points How: Name concretely what happened and why that doesn't fit with your learning goals, without judging
Reflection Focus Points
Recognizing Signals
- Behavior patterns - when do you do what and why
- Triggers - what sets certain reactions in motion
- Escalation moments - when should you intervene or seek help
- Work style patterns - how do you react under pressure or when facing challenges
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 · 70 lines · 10 tokens per session scan A 61499f99bd66
reflection-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 655 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.
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.