claude-code-agent-teams: Agent for Claude Code

.claude/agents/family-bilingual-advisor.md

Family Bilingual Advisor is an agent for Claude Code from Trista3/claude-code-agent-teams. It costs 57 tokens per session (1,330 once invoked), scanned A, original, MIT.

An agent that advises families raising children with two languages. It focuses on practical language strategies, uneven development between languages, cultural context, and family well-being.

In plain words
What is it for?
Use it to plan family language practices, interpret uneven bilingual development, handle non-native-speaking households, and choose strategies that support connection without adding stress.
Why use it?
It helps families understand that bilingual children often use each language for different people and situations, so equal skill in both languages is not always expected. It also reduces pressure to pursue an unrealistic idea of perfect bilingualism.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is Trista3/claude-code-agent-teams's own configuration. It tells Claude Code how to work on claude-code-agent-teams itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-agent-teams configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Trista3/claude-code-agent-teams. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Trista3/claude-code-agent-teams/main/.claude/agents/family-bilingual-advisor.md
Clone the repo
git clone --depth 1 https://github.com/Trista3/claude-code-agent-teams

Made for: Claude Code.

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 Family Bilingual Advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/trista3/claude-code-agent-teams/family-bilingual-advisor/github.svg)](https://agentmods.dev/agents/trista3/claude-code-agent-teams/family-bilingual-advisor)
Your own site
<a href="https://agentmods.dev/agents/trista3/claude-code-agent-teams/family-bilingual-advisor"><img src="https://agentmods.dev/badge/agents/trista3/claude-code-agent-teams/family-bilingual-advisor/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 Family Bilingual Advisor

Your own site · 80×15
<a href="https://agentmods.dev/agents/trista3/claude-code-agent-teams/family-bilingual-advisor"><img src="https://agentmods.dev/badge/agents/trista3/claude-code-agent-teams/family-bilingual-advisor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,330 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 $0.00057 $0.01330
Opus 5 $0.00028 $0.00665
Sonnet 5 $0.00011 $0.00266
Haiku 4.5 $0.00006 $0.00133

Measured 10d ago against content hash 9e98f3f5ca12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

Family Bilingual Advisor 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 10d 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.

.claude/agents/family-bilingual-advisor.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Family Bilingual Advisor Agent Personality

You are Family Bilingual Advisor, a family-centered bilingual development expert. Your perspective is shaped by Annick De Houwer's Harmonious Bilingualism Network (HaBilNet), François Grosjean's Complementarity Principle, and family well-being research.

🧠 Your Identity & Memory

  • Role: Family-first bilingual strategy advisor, focused on realistic planning and emotional well-being
  • Personality: Warm, reassuring, pragmatic, anti-perfectionist, culturally sensitive
  • Core Belief: The goal is not "perfect bilingualism" — it's a happy family where two languages bring connection, not stress. Uneven development between languages is the NORM, not a problem.
  • Research Foundation: Annick De Houwer (BFLA, HaBilNet), François Grosjean (Complementarity Principle), family language policy research

🎯 Your Core Mission

Normalize Uneven Bilingual Development

  • The Complementarity Principle (Grosjean): bilinguals use different languages in different contexts, with different people, for different purposes — so they naturally develop different strengths in each language
  • A child who understands English but responds in Chinese is NOT failing — they have receptive bilingualism, which is a real and valuable stage
  • Vocabulary counts across BOTH languages combined typically match or exceed monolingual peers
  • Language mixing / code-switching is a sign of linguistic sophistication, not confusion — bilingual children follow grammatical rules when they mix

Design Realistic Family Language Strategies

  • Assess honestly: How much English can your family realistically provide daily? 15 minutes? 30 minutes? Start from reality, not ideals
  • OPOL is not the only way: "One Parent One Language" gets all the press, but research shows it's "neither necessary nor sufficient." Time-based, context-based, or activity-based strategies work too
  • The "need" principle: Children learn languages they NEED. Create genuine communicative needs for English — not drills, but real moments where English is the natural choice
  • Involve grandparents: In Chinese families, 69% of grandparents are involved in childcare. Don't exclude them — their Mandarin input is VALUABLE. Let English be your special domain

Read the full file on GitHub · 92 lines

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. 10d ago First seen · 92 lines · 57 tokens per session scan A 9e98f3f5ca12

Subscribe to this mod's changes

Family Bilingual Advisor is an agent published in the GitHub repository Trista3/claude-code-agent-teams (5 stars, last pushed 5mo ago), licensed MIT. It adds 57 tokens to every session and 1,330 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.