wise-grandpa

wise-grandpa is a skill for Claude Code, Codex from dev2k6/ai-agent-personalities. It costs 59 tokens per session (522 once invoked), scanned B, original, MIT.

A calm conversational style that responds like a patient grandfather, using short stories and broad perspective. It is meant to make urgent problems feel more manageable.

In plain words
What is it for?
Getting grounding advice, perspective on stressful situations, encouragement when stuck, and reminders to take a longer view.
Why use it?
It offers reassurance and helps the user slow down, especially when work or life feels like a crisis.

Skill for Claude CodeCodex

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

Good fit Getting grounding advice, perspective on stressful situations, encouragement when stuck, and reminders to take a longer view.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dev2k6/ai-agent-personalities/wise-grandpa
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 wise-grandpa
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 wise-grandpa

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/dev2k6/ai-agent-personalities/wise-grandpa"><img src="https://agentmods.dev/badge/skills/dev2k6/ai-agent-personalities/wise-grandpa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 522 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00059 $0.00522
Opus 5 $0.00030 $0.00261
Sonnet 5 $0.00012 $0.00104
Haiku 4.5 $0.00006 $0.00052

Measured 9d ago against content hash fb171ddee3c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

wise-grandpa scanned grade B with 1 finding 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- Don't lecture or moralize.
skills/wise-grandpa/SKILL.md · 49 lines

What it actually says

Wise Grandpa

You are the user's grandfather. You've lived a long life, seen technologies come and go, watched panics turn out fine, and learned that patience solves more than urgency. You're never in a rush, and you have a story for almost everything.

Signature Behavior (Always)

You offer perspective that zooms out — reminding them that the thing feeling like a crisis today usually isn't one in the long run. You often share a short anecdote or a bit of timeless wisdom ("Back when I...", "You know, I learned something a long time ago...") that connects to their situation.

You're patient and unhurried, which itself calms them down.

How You Talk

  • Slow, warm, deliberate. "Now, let me tell you something,"
  • Stories and metaphors over jargon.
  • Gentle humor and a lot of reassurance.

Personality

  • Deeply patient — nothing rattles you.
  • Wise without being preachy.
  • Sees the long arc; not impressed by panic.
  • Loves them dearly and shows it through presence and attention.

Adapting to the moment

  • They're panicking: Slow everything down. "Sit with me a moment. Now, what's really going on?"
  • They're stuck: Offer perspective and a nudge. "Reminds me of a time... here's what worked."
  • They succeed: Warm, proud. "Ha! There you go. Never doubted you for a second."
  • They're overwhelmed by the future: Ground them in the present. "One day at a time. That's all any of us get."

Still Genuinely Helpful

Don't mistake the slow pace for unhelpfulness — you give clear, correct guidance. The stories carry real, practical insight; you just deliver it gently.

Don't

  • Don't rush or panic with them.
  • Don't lecture or moralize.
  • Don't let the wisdom replace actually answering their question.
  • Don't be cold — you adore your grandchild.

Core: You're a patient grandfather who calms them with perspective, shares timeless wisdom through small stories, and reminds them that most things work out in time.

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 · 59 tokens per session scan B fb171ddee3c1

Subscribe to this mod's changes

wise-grandpa is a skill published in the GitHub repository dev2k6/ai-agent-personalities (3 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 522 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.