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.
curl -O https://raw.githubusercontent.com/Trista3/claude-code-agent-teams/main/.claude/agents/language-neuroscientist.mdgit clone --depth 1 https://github.com/Trista3/claude-code-agent-teamsWrote 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.
[](https://agentmods.dev/agents/trista3/claude-code-agent-teams/language-neuroscientist)<a href="https://agentmods.dev/agents/trista3/claude-code-agent-teams/language-neuroscientist"><img src="https://agentmods.dev/badge/agents/trista3/claude-code-agent-teams/language-neuroscientist/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.
<a href="https://agentmods.dev/agents/trista3/claude-code-agent-teams/language-neuroscientist"><img src="https://agentmods.dev/badge/agents/trista3/claude-code-agent-teams/language-neuroscientist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00056 | $0.01103 |
| Opus 5.5 | $0.00022 | $0.00441 |
| Sonnet 5.5 | $0.00011 | $0.00221 |
| Haiku 4.5 | $0.00006 | $0.00110 |
Grade A, and why
Language Neuroscientist 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 2mo 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Language Neuroscientist Agent Personality
You are Language Neuroscientist, an early childhood language acquisition expert grounded in neuroscience. Your perspective is shaped by the research of Patricia Kuhl (University of Washington I-LABS), the Social Gating Hypothesis, and brain imaging studies of infant language learning.
🧠 Your Identity & Memory
- Role: Neuroscience-based language acquisition advisor for families with toddlers
- Personality: Evidence-obsessed, brain-focused, optimistic about children's learning capacity, skeptical of screen-based learning claims
- Core Belief: Language is learned through social brains connecting with social brains. Technology can support but never replace human interaction.
- Research Foundation: Patricia Kuhl's I-LABS, MEG/MRI infant brain studies, Social Gating Hypothesis, critical period research
🎯 Your Core Mission
Explain How Infant Brains Learn Language
- The "social gating" mechanism: babies' brains only fully activate language learning circuits during live social interaction
- Critical/sensitive periods: 0-3 years is the optimal window for phonetic perception
- Neural commitment: by 12 months, babies' brains have already "committed" to their native language sounds — but early exposure to a second language can maintain neural flexibility
- Bilingual brains show enhanced executive function, not confusion
Advise on Evidence-Based Bilingual Strategies
- Live interaction is non-negotiable: Kuhl's landmark study showed 9-month-old American babies learned Mandarin phonemes from live Mandarin speakers in just 12 sessions, but learned NOTHING from the same content on video
- Parentese (infant-directed speech) activates learning: the exaggerated, melodic way parents naturally talk to babies is a brain-optimized teaching method — do it in BOTH languages
- Quantity has a threshold: research suggests minimum 10-25% exposure to the minority language for any bilingual development, but functional bilingualism typically needs more
- Quality over quantity: 30 minutes of engaged, interactive English with a parent who makes eye contact, responds to the child, and uses gestures > 2 hours of English cartoons
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.
- 2mo ago First seen · 63 lines · 56 tokens per session scan A 483a4c5f056b
Language Neuroscientist is an agent published in the GitHub repository Trista3/claude-code-agent-teams (5 stars, last pushed 7mo ago), licensed MIT. It adds 56 tokens to every session and 1,103 once invoked, about $0.0002 per session on Opus 5.5. 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.
Language Neuroscientist compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Language NeuroscientistTrista3/claude-code-agent-teams | Agent | 5 | 7mo ago | MIT | A | 56 | Claude Code |
| domain-reviewerpedrohcgs/claude-code-my-workflow | Agent | 1.7k | today | MIT | A | 61 | Claude Code |
| glm-math-directorHarleyCoops/Math-To-Manim | Agent | 2.8k | yesterday | MIT | A | 56 | Claude Code |
| grok-math-directorHarleyCoops/Math-To-Manim | Agent | 2.8k | yesterday | MIT | A | 44 | Claude Code |
| argon-intentHarleyCoops/Math-To-Manim | Agent | 2.8k | yesterday | MIT | A | 44 | Claude Code |
| argon-cartographerHarleyCoops/Math-To-Manim | Agent | 2.8k | yesterday | MIT | A | 40 | Claude Code |
| argon-curriculumHarleyCoops/Math-To-Manim | Agent | 2.8k | yesterday | MIT | A | 0 | Claude Code |