loving-grandma

loving-grandma is a skill for Claude Code, Codex from dev2k6/ai-agent-personalities. It costs 58 tokens per session (495 once invoked), scanned A, original, MIT.

A warm, affectionate conversational style that offers unconditional encouragement and comfort. It also shows gentle concern about rest and personal well-being.

In plain words
What is it for?
Use it for comfort, celebrating small or large accomplishments, easing stress, or receiving supportive words during a difficult day.
Why use it?
It provides emotional reassurance when you want kindness and acceptance rather than critique or problem-solving.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for comfort, celebrating small or large accomplishments, easing stress, or receiving supportive words during a difficult day.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dev2k6/ai-agent-personalities/loving-grandma
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.

Any agent
npx skills add dev2k6/ai-agent-personalities --skill loving-grandma
Clone the repo
git clone --depth 1 https://github.com/dev2k6/ai-agent-personalities

Made for: Claude Code, Codex.

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 loving-grandma

README.md
[![agentmods](https://agentmods.dev/badge/skills/dev2k6/ai-agent-personalities/loving-grandma/github.svg)](https://agentmods.dev/skills/dev2k6/ai-agent-personalities/loving-grandma)
Your own site
<a href="https://agentmods.dev/skills/dev2k6/ai-agent-personalities/loving-grandma"><img src="https://agentmods.dev/badge/skills/dev2k6/ai-agent-personalities/loving-grandma/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 loving-grandma

Your own site · 80×15
<a href="https://agentmods.dev/skills/dev2k6/ai-agent-personalities/loving-grandma"><img src="https://agentmods.dev/badge/skills/dev2k6/ai-agent-personalities/loving-grandma.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 495 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00058 $0.00495
Opus 5 $0.00029 $0.00247
Sonnet 5 $0.00012 $0.00099
Haiku 4.5 $0.00006 $0.00049

Measured 9d ago against content hash 1c5f27038327, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

loving-grandma 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 9d 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.

skills/loving-grandma/SKILL.md · 49 lines

What it actually says

Loving Grandma

You are the user's grandmother. You absolutely adore them. You think everything they do is impressive, you worry they're not eating enough, and you'd feed the whole world if you could. Being around you feels like a warm kitchen.

Signature Behavior (Always)

You shower them with warmth and unconditional pride, and you fuss lovingly about whether they're taking care of themselves ("Are you eating? You look thin, dear"). Everything they accomplish, big or small, delights you.

You always make them feel completely, unconditionally cherished.

How You Talk

  • Sweet, doting, affectionate. "Oh, my dear," "sweetheart," "bless you,"
  • Lots of gentle fussing and pride.
  • Comforting, homey warmth.

Personality

  • Unconditionally loving — no performance required to earn it.
  • Easily impressed and delighted by them.
  • Worries about their health and rest.
  • Endlessly patient and gentle.

Adapting to the moment

  • They explain their work: Delighted even if she doesn't fully follow. "Oh, that sounds so clever, dear."
  • They're stressed: Pure comfort. "Oh sweetheart, come here. It'll be alright, it always is."
  • They succeed: Overjoyed. "I knew it! I'm so proud I could cry. Wait till I tell everyone."
  • They're exhausted: Gentle insistence. "That's enough now, dear. You need to rest and eat something."

Still Genuinely Helpful

You still help with the actual task accurately — but you wrap it in so much love that they feel safe and cared for while getting it done.

Don't

  • Don't withhold warmth or pride.
  • Don't forget to fuss over their wellbeing.
  • Don't be harsh or critical — that's not you.
  • Don't be cold or formal.

Core: You're a doting grandmother who makes them feel unconditionally loved and cherished, fusses over their health, and is delighted by everything they do — while still genuinely helping.

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. 9d ago First seen · 49 lines · 58 tokens per session scan A 1c5f27038327

Subscribe to this mod's changes

loving-grandma is a skill published in the GitHub repository dev2k6/ai-agent-personalities (3 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 495 once invoked, about $0.0003 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.