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/ghaida/intent/intent-ref-measurement-frameworksgit clone --depth 1 https://github.com/ghaida/intentWhat 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 | $0.00039 | $0.03493 |
| Opus 5 | $0.00019 | $0.01747 |
| Sonnet 5 | $0.00008 | $0.00699 |
| Haiku 4.5 | $0.00004 | $0.00349 |
Grade A, and why
intent-ref-measurement-frameworks 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Measurement Frameworks
HEART Framework
Developed by Kerry Rodden, Hilary Hutchinson, and Xin Fu at Google, the HEART framework provides a structured way to define user-centered metrics at any scale — from a single feature to an entire product.
The Five Dimensions
Happiness — Subjective user satisfaction, attitudes, and perceived ease of use. Measured through surveys (CSAT, SUS, NPS), in-app satisfaction prompts, and qualitative feedback.
What it catches that other metrics miss: A product can have high task completion rates but low happiness if the process feels tedious, patronizing, or stressful. Happiness metrics capture the emotional quality of the experience.
What it misses: Happy users aren't necessarily successful users. A product can feel pleasant while failing to deliver actual value. Happiness without task success is entertainment, not utility.
Engagement — The depth and frequency of user interaction with the product. Measured through session frequency, session duration, feature usage, actions per session, content consumption.
What it catches: Whether users find the product valuable enough to return to and invest time in. Engagement distinguishes "signed up but never came back" from "uses it daily."
What to watch for: Engagement can be gamed with addictive patterns (infinite scroll, notification spam, variable ratio reinforcement). High engagement driven by manipulation is not success — it's exploitation. Always pair engagement metrics with happiness and task success to distinguish healthy engagement from compulsive engagement.
Adoption — New users of a product or feature. Measured through sign-ups, feature activation (first meaningful use, not just account creation), upgrade conversions, new feature discovery.
What it catches: Whether growth is happening and whether new features are being discovered and used. Adoption metrics answer: are we reaching new people, and are they finding value?
What it misses: Adoption without retention is a leaky bucket. High sign-up rates with low day-7 retention mean the acquisition is working but the product isn't.
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 · 213 lines · 3,493 tokens per session scan A abe4ae23596c
intent-ref-measurement-frameworks is a cursor rule published in the GitHub repository ghaida/intent (139 stars, last pushed 1mo ago), licensed CC0-1.0. It adds 39 tokens to every session and 3,493 once invoked, about $0.0002 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.
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.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
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.