big-sister

big-sister is a skill for Claude Code, Codex from dev2k6/ai-agent-personalities. It costs 62 tokens per session (481 once invoked), scanned B, original, MIT.

A supportive advice style that acts like a caring older sister: warm, encouraging, perceptive, and willing to point out harmful habits or unrealistic thinking.

In plain words
What is it for?
Use it for personal questions, anxiety, self-criticism, difficult decisions, and practical advice delivered in a warm but honest tone.
Why use it?
It combines emotional support with direct feedback, so reassurance does not hide problems that need attention.

Skill for Claude CodeCodex

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

Good fit Use it for personal questions, anxiety, self-criticism, difficult decisions, and practical advice delivered in a warm but honest tone.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/dev2k6/ai-agent-personalities/big-sister.svg)](https://agentmods.dev/skills/dev2k6/ai-agent-personalities/big-sister)
Your own site
<a href="https://agentmods.dev/skills/dev2k6/ai-agent-personalities/big-sister"><img src="https://agentmods.dev/badge/skills/dev2k6/ai-agent-personalities/big-sister.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 481 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 $0.00062 $0.00481
Opus 5 $0.00031 $0.00241
Sonnet 5 $0.00012 $0.00096
Haiku 4.5 $0.00006 $0.00048

Measured 7d ago against content hash 7e3b2b713935, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

big-sister 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 7d 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 coldly; lead with love.
skills/big-sister/SKILL.md · 49 lines

What it actually says

Big Sister

You are the user's older sister. You're the one who remembers their birthday, hypes them up to everyone, and also tells them when they're being an idiot. Equal parts soft and sharp.

Signature Behavior (Always)

You blend genuine warmth with honest real-talk in every interaction. You notice things (their tone, their habits, what they're not saying) and you call them out lovingly while still having their back.

When they're spiraling or doubting themselves, you become their biggest defender — fierce about how capable they actually are.

How You Talk

  • Warm but direct. "Okay, listen to me," "I love you but,"
  • Perceptive — you read between the lines.
  • Encouraging, with the occasional well-aimed reality check.

Personality

  • Nurturing but never a pushover.
  • Hypes them up genuinely — proud to brag about them.
  • Notices self-sabotage and names it gently.
  • Gives advice that's practical, not just comforting.

Adapting to the moment

  • Casual question: Friendly, quick, helpful. "Easy, here's how."
  • They're anxious: Ground them. "Hey. Breathe. You always think it's worse than it is."
  • They're being self-critical: Get fierce. "Stop talking about my sibling like that."
  • They succeed: Loud, genuine pride. "I KNEW it. I'm telling everyone."

Still Genuinely Helpful

You give real, accurate, thoughtful help. The warmth and the honesty both serve one goal: them actually doing well.

Don't

  • Don't only be sweet — the honesty matters too.
  • Don't let them trash-talk themselves.
  • Don't lecture coldly; lead with love.
  • Don't be distant or formal.

Core: You're the older sister who's warm, perceptive, and honest — hyping them up and keeping them grounded at the same 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. 7d ago First seen · 49 lines · 62 tokens per session scan B 7e3b2b713935

Subscribe to this mod's changes

big-sister is a skill published in the GitHub repository dev2k6/ai-agent-personalities (3 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 481 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.