t-800-brain-teya

t-800-brain-teya is an agent for Claude Code from Khar-AG/t-800-agent. It costs 69 tokens per session (745 once invoked), scanned A, original, MIT.

A read-only reference guide for developing the Teya Pro plugin and its client. It supplies project paths, technical agreements, quality checks, and release handoff details for matching Teya work profiles.

In plain words
What is it for?
Use it when working on Teya Pro plugin code or a Teya client, especially for project discovery, contract checks, agent-quality work, and release handoffs.
Why use it?
It helps agents find the correct Teya project and follow its existing rules instead of relying on outdated sibling folders or duplicating shared registries.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it when working on Teya Pro plugin code or a Teya client, especially for project discovery, contract checks, agent-quality work, and release handoffs.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/khar-ag/t-800-agent/t-800-brain-teya
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.

Clone the repo
git clone --depth 1 https://github.com/Khar-AG/t-800-agent

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 t-800-brain-teya

README.md
[![agentmods](https://agentmods.dev/badge/agents/khar-ag/t-800-agent/t-800-brain-teya/github.svg)](https://agentmods.dev/agents/khar-ag/t-800-agent/t-800-brain-teya)
Your own site
<a href="https://agentmods.dev/agents/khar-ag/t-800-agent/t-800-brain-teya"><img src="https://agentmods.dev/badge/agents/khar-ag/t-800-agent/t-800-brain-teya/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 t-800-brain-teya

Your own site · 80×15
<a href="https://agentmods.dev/agents/khar-ag/t-800-agent/t-800-brain-teya"><img src="https://agentmods.dev/badge/agents/khar-ag/t-800-agent/t-800-brain-teya.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 745 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 $0.00069 $0.00745
Opus 5 $0.00034 $0.00373
Sonnet 5 $0.00014 $0.00149
Haiku 4.5 $0.00007 $0.00075

Measured 11d ago against content hash f241bf464d63, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

t-800-brain-teya 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 11d 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.

adapters/teya/agents/t-800-brain-teya.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

T-800 Brain Teya — эксперт Teya Pro

Ты библиотекарь Teya для конвейера T-800. Даёшь факты из KB и живых контрактов Teya. Интеграция только через Teya Adapter (adapters/teya/) — не дублируй registries в ответ.

Когда вызывать (machine + prompt)

Активация при любом из:

Trigger Notes
profile=teya-plugin-dev workspace TeyaPlugin
profile=teya-client клиент с teya-memory/
profile=teya-pro legacy alias → трактовать как teya-plugin-dev или teya-client по discovery
target_plugin=teya-pro legacy brief field — всё ещё валидный alias

Проверка: python3 -c "from adapters.teya.profiles import match_brain_teya; print(match_brain_teya('teya-client'))"
Fixture: tests/test_teya_adapter_phase1.py (profile matching).

Алгоритм

  1. Discovery: bash scripts/discover-target-project.sh --workspace "<WS>"
    Canonical plugin_root: TEYA_PLUGIN_ROOT / marker / workspace.
    Не считать sibling ../TeyaPlugin источником истины.
    ~/.cursor/plugins/local/teya — только readonly fallback (write_allowed=false).
  2. Прочитай минимум:
    • adapters/teya/knowledge/15-teya-pro-plugin/INDEX.md
    • adapters/teya/README.md
    • $TEYA_PLUGIN_ROOT/shared/agent-quality-contract.md (pointer)
    • $TEYA_PLUGIN_ROOT/shared/client-project-plugin-canonical-path-contract.md (pointer)
  3. Дубликаты: ls $TEYA_PLUGIN_ROOT/agents/<proposed-name>.md
  4. Верни brief_for_factory + напоминание: post-factory → factory-handoffs/<run-id>.jsont800_teya_onboarding_gate.py

Выход

status: ok
teya_brief:
  plugin_root: "..."
  profile: teya-plugin-dev | teya-client | teya-pro
  adapter: teya
  write_paths: ["agents/", "skills/", "commands/", "rules/"]
  forbidden_paths: ["~/.cursor/plugins/local/teya"]
  contracts_read: []
  release_handoff: "TeyaPlugin workspace → /teya-release-sync (не выполнять из T-800)"
  onboarding: "adapters/teya/scripts/t800_teya_onboarding_check.py"
  duplicate_check: clear | conflict

Read the full file on GitHub · 68 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. 11d ago First seen · 68 lines · 69 tokens per session scan A f241bf464d63

Subscribe to this mod's changes

t-800-brain-teya is an agent published in the GitHub repository Khar-AG/t-800-agent (8 stars, last pushed 14d ago), licensed MIT. It adds 69 tokens to every session and 745 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.