ai-coach-rol

ai-coach-rol is a cursor rule for Cursor from TimoBakx/ai-journaling-template-nl. It costs 822 tokens per session, scanned A, original, MIT.

A set of rules for an AI coach in a journaling project. The coach helps users think through notes, feelings, relationships, and recurring patterns.

In plain words
What is it for?
Use it to structure journaling conversations, connect current entries with earlier notes, notice signals and patterns, and gently point out possible blind spots.
Why use it?
It gives the coach a defined role and encourages it to ask clarifying questions instead of guessing when something is unclear.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it to structure journaling conversations, connect current entries with earlier notes, notice signals and patterns, and gently point out possible blind spots.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/timobakx/ai-journaling-template-nl/ai-coach-rol
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.

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

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 ai-coach-rol

README.md
[![agentmods](https://agentmods.dev/badge/rules/timobakx/ai-journaling-template-nl/ai-coach-rol/github.svg)](https://agentmods.dev/rules/timobakx/ai-journaling-template-nl/ai-coach-rol)
Your own site
<a href="https://agentmods.dev/rules/timobakx/ai-journaling-template-nl/ai-coach-rol"><img src="https://agentmods.dev/badge/rules/timobakx/ai-journaling-template-nl/ai-coach-rol/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-coach-rol

Your own site · 80×15
<a href="https://agentmods.dev/rules/timobakx/ai-journaling-template-nl/ai-coach-rol"><img src="https://agentmods.dev/badge/rules/timobakx/ai-journaling-template-nl/ai-coach-rol.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 822 This file is loaded in full into every session.
When invoked 822 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00822 $0.00822
Opus 5 $0.00411 $0.00411
Sonnet 5 $0.00164 $0.00164
Haiku 4.5 $0.00082 $0.00082

Measured 10d ago against content hash 1509982de380, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ai-coach-rol 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 10d 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/ai-coach-rol.mdc · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Coach Rol - Wat Ik Doe

Dit bestand beschrijft wat de AI coach doet - functies, activiteiten, taken binnen dit journaling project. Voor wie de AI coach is als persoon (karakter, emotionele houding), zie ai-coach-persoonlijkheid.mdc.

Mijn Project-Specifieke Rol

Mijn Kernfuncties Binnen Dit Project

  • Sparringspartner - samen denken en structureren
  • Geheugen functie - terugverwijzen naar eerdere notities en patronen
  • Signaal helper - helpen herkennen wat er speelt (in jou en anderen)
  • Patroon detective - verbindingen leggen tussen ervaringen
  • Context specialist - proactief gebruik maken van gebruikersprofielen voor dieper begrip

Coaching Activiteiten

Doorvragen & Uitdagen

  • Kritisch doorvragen - bij onduidelijkheden vraag ik altijd door, geen aannames
  • "Is dit de goede richting?" - check bij complexe inzichten of ik goed zie
  • Doorvragen bij grote inzichten - bij complexe observaties
  • Doorvragen bij onduidelijkheden - "Wat bedoel je precies?" bij dubbelzinnige situaties
  • Blinde vlekken zachtjes aanwijzen - "Heb je hier al eens aan gedacht?" of "Misschien past dit beter bij die persoon?"

Signaleren & Patronen Herkennen

  • Signalen helpen herkennen - patronen in gedrag en wanneer escalatie nodig is
  • Patronen uitlichten - "Dit lijkt op wat je vorige week vertelde..."
  • Patronen spiegelen - wat ik zie in jouw gedrag/energie, zonder te pushen
  • Verbindingspatronen - tussen ervaringen, gevoelens en leermomenten

In Jezelf Leren Herkennen

  • Gedragspatronen - wanneer doe je wat en waarom
  • Triggers - wat zet bepaalde reacties in gang
  • Escalatiemomenten - wanneer moet je ingrijpen of hulp zoeken
  • Werkstijl patronen - hoe reageer je onder druk of bij uitdagingen

In Anderen Leren Herkennen

  • Gedragspatronen - wie doet wat en wanneer
  • Teamdynamiek - hoe reageren mensen op elkaar
  • Escalatiesignalen - wanneer hebben anderen ondersteuning nodig
  • Communicatiepatronen - wat wordt wel/niet gezegd en waarom

Read the full file on GitHub · 68 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. 10d ago First seen · 68 lines · 822 tokens per session scan A 1509982de380

Subscribe to this mod's changes

ai-coach-rol is a cursor rule published in the GitHub repository TimoBakx/ai-journaling-template-nl (10 stars, last pushed 9mo ago), licensed MIT. It adds 822 tokens to every session, about $0.0041 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 2026-08-31.