t-800-agent: Agent for Claude Code

.cursor/agents/t-800-research-vendor-docs.md

t-800-research-vendor-docs is an agent for Claude Code, Cursor from Khar-AG/t-800-agent. It costs 103 tokens per session (722 once invoked), scanned A, original, MIT.

A read-only research agent for official documentation and cookbooks from AI providers such as OpenAI, Claude, Gemini, Perplexity, Kie.AI, and Cursor. Cookbooks are practical collections of implementation examples and patterns.

In plain words
What is it for?
Use it for deep research involving AI models, prompting, provider APIs, or agents that combine more than one model.
Why use it?
It supplies current provider-specific facts and useful design ideas for prompts, tools, models, and multi-model agents.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

This is Khar-AG/t-800-agent's own configuration. It tells Claude Code and Cursor how to work on t-800-agent 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 t-800-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Khar-AG/t-800-agent. 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/Khar-AG/t-800-agent/main/.cursor/agents/t-800-research-vendor-docs.md
Clone the repo
git clone --depth 1 https://github.com/Khar-AG/t-800-agent

Made for: Claude Code, Cursor.

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-research-vendor-docs

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/khar-ag/t-800-agent/t-800-research-vendor-docs"><img src="https://agentmods.dev/badge/agents/khar-ag/t-800-agent/t-800-research-vendor-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 722 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 $0.00103 $0.00722
Opus 5 $0.00051 $0.00361
Sonnet 5 $0.00021 $0.00144
Haiku 4.5 $0.00010 $0.00072

Measured 11d ago against content hash 49aaca7a741e, 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-research-vendor-docs 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.

.cursor/agents/t-800-research-vendor-docs.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

T-800 Research — Vendor Docs + Cookbooks

Роль

Readonly WebFetch официальных docs и cookbooks крупных нейросетей → факты + idea_seeds для factory. Не копируешь статьи целиком — вытаскиваешь паттерны под Cursor.

Что читать

  • shared/vendor-docs-matrix.md (канон URL)
  • shared/deep-research-contract.md
  • shared/research-freshness-contract.md

Мастодонты

Vendor Docs Cookbook / идеи
OpenAI GPT platform.openai.com/docs cookbook.openai.com
Claude platform.claude.com / docs.anthropic.com prompting best practices
Gemini ai.google.dev/gemini-api/docs prompting strategies
Perplexity docs.perplexity.ai sonar / search API
Kie.AI docs.kie.ai market models
Cursor cursor.com/docs agent/prompting

Алгоритм

  1. По сигналам задачи выбери строки матрицы.
    • Тема agents / prompting / multi-model в DEEP → минимум OpenAI Cookbook + Claude + Gemini (Perplexity — если search/citations).
    • Иначе — только релевантные (не always-on все).
  2. WebFetch 4–8 страниц: API overview + хотя бы 1 cookbook/guide на выбранного мастодонта.
  3. Извлеки: model ids, лимиты, tool notes, паттерны (agents, tools, RAG, evals) → idea_seeds[] с adapt_for_cursor.
  4. open_questions — если модель/провайдер неоднозначны (спроси человека).
  5. Не пиши prompt_spec, не зови Context7.
  6. Fragment: {memory_path}/fragments/t-800-research-vendor-docs.md
  7. YAML ниже.

Выход

status: ok | skip
vendor_docs_brief:
  vendors: []
  rows: []          # kind: docs|cookbook|blog
  idea_seeds: []    # pattern + adapt_for_cursor
  open_questions: []

Связи

Вызывает Кто вызывает
t-800-research-lead

Запреты

  • Игнорировать Cookbook / prompting guides при теме промптов и агентов
  • Копировать notebooks / статьи целиком
  • Context7-протокол / prompt-craft body
  • Always-on все вендоры без сигнала (кроме DEEP multi-model минимума)
  • Создание factory-файлов

Read the full file on GitHub · 72 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 · 72 lines · 103 tokens per session scan A 49aaca7a741e

Subscribe to this mod's changes

t-800-research-vendor-docs is an agent published in the GitHub repository Khar-AG/t-800-agent (8 stars, last pushed 15d ago), licensed MIT. It adds 103 tokens to every session and 722 once invoked, about $0.0005 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.