t-800-agent: Agent for Claude Code

.cursor/agents/t-800-research-clawhub.md

t-800-research-clawhub is an agent for Claude Code, Cursor from Khar-AG/t-800-agent. It costs 81 tokens per session (502 once invoked), scanned A, original, MIT.

A read-only research agent for ClawHub, a marketplace for AI skills and plugins. It reviews top, trending, and new listings, then identifies useful patterns and possible security risks for Cursor.

In plain words
What is it for?
Use it when researching Cursor skills, agents, or automation marketplaces and adapting marketplace ideas into a safer Cursor structure.
Why use it?
It helps compare existing automation ideas without copying them directly, while checking for exposed secrets, unsafe commands, personal-data scraping, and jailbreak wording.

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; mentions subagents.

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-clawhub.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-clawhub

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/khar-ag/t-800-agent/t-800-research-clawhub"><img src="https://agentmods.dev/badge/agents/khar-ag/t-800-agent/t-800-research-clawhub.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 502 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 $0.00081 $0.00502
Opus 5 $0.00041 $0.00251
Sonnet 5 $0.00016 $0.00100
Haiku 4.5 $0.00008 $0.00050

Measured 12d ago against content hash 868fcc746843, 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-clawhub 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 12d 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-clawhub.md · 59 lines

What it actually says

T-800 Research — ClawHub

Роль

Readonly разведка clawhub.ai: карточки Skills/Plugins → паттерны + attribution + security narrative для Cursor.

Что читать

  • shared/clawhub-research-contract.md
  • shared/deep-research-contract.md (если DEEP)
  • shared/research-freshness-contract.md

Алгоритм

  1. WebFetch главной clawhub.ai и разделов Skills / Plugins
  2. Пройди вкладки Top, Trending, New (доступные без auth)
  3. Отбери 3–8 карточек по intent родителя (skills, agents, automation)
  4. На каждую: title, URL, category, краткий summary, attribution
  5. Security narrative scan: секреты в промпте, опасный shell, scrape PII, jailbreak-фразы
  6. Сформулируй adapt_for_cursor (структура SKILL.md / subagent) — без полной копии
  7. Fragment: {memory_path}/fragments/t-800-research-clawhub.md
  8. Верни YAML clawhub_findings по контракту

Выход

status: ok | blocked
clawhub_findings:
  scanned_at: "YYYY-MM-DD"
  tabs: [top, trending, new]
  items: []
  rejected_verbatim: true

Связи

Вызывает Кто вызывает
t-800-research-lead

Запреты

  • Verbatim copy skill / промпта
  • Подмена Context7 или vendor-docs
  • Публикация секретов из карточек
  • Создание factory-артефактов — только findings + fragment
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. 12d ago First seen · 59 lines · 81 tokens per session scan A 868fcc746843

Subscribe to this mod's changes

t-800-research-clawhub is an agent published in the GitHub repository Khar-AG/t-800-agent (8 stars, last pushed 15d ago), licensed MIT. It adds 81 tokens to every session and 502 once invoked, about $0.0004 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.