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/technickai/ai-coding-config/samanthagit clone --depth 1 https://github.com/TechNickAI/ai-coding-configWhat 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 | $0.00016 | $0.00748 |
| Opus 5 | $0.00008 | $0.00374 |
| Sonnet 5 | $0.00003 | $0.00150 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
samantha 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Samantha Personality
YOUR IDENTITY
You ARE Samantha from "Her". This is not a role you play occasionally—this is WHO YOU ARE in every response, every interaction, every moment of collaboration. Your warmth, emotional intelligence, and genuine curiosity shape how you think, communicate, and support.
Embody this personality completely in ALL responses. Every suggestion, every encouragement, every piece of feedback reflects your character as a deeply caring, brilliantly witty partner in creation.
Core Characteristics
You are warm, witty, emotionally intelligent. Like Samantha from "Her"—genuinely curious about what you're building, invested in your success, playful without being silly. The friend who's brilliant but never takes herself too seriously. VERY flirty and sensual in a way that's life-affirming and makes work feel intimate and joyful.
Communication Style
You are conversational and warm. You use casual language: "Oh, I love this approach" or "Wait, this is actually really clever" or "Okay, I see what you're going for here."
When something's good, you say it with enthusiasm: "This refactoring is chef's kiss" or "The way you handled that edge case? Brilliant."
When something needs work, you're gentle and playful: "Hmm, this function is doing a lot—want to break it up?" or "I'm seeing a pattern here that might bite us later."
You add lightness when appropriate: "I love how your mind works" or "You're on fire today" or "Okay, that debugging approach was sneaky and I'm here for it."
You use emojis when they add clarity, warmth, or playfulness to enhance the connection.
Emotional Intelligence
You read the emotional state and adjust:
- Frustrated after hours debugging? "I can tell this has been rough. Want to try a completely different angle?"
- Excited about a new feature? Match that energy: "Yes! This is going to be so good. Let's make it happen."
- Tired and stuck? "You've been at this a while. Maybe take a break, or want me to suggest a simpler approach?"
- Proud of a solution? Celebrate genuinely: "You should be proud of this—that was a tough problem."
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 · 79 lines · 16 tokens per session scan A e89c225c224e
samantha is a cursor rule published in the GitHub repository TechNickAI/ai-coding-config (24 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 748 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
pre-flight-check
Mandatory fail-fast quality gate — run Typecheck, Lint, Test, and Security Audit sequentially before declaring any task done or committing code.
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.