t-800-research-github

t-800-research-github is an agent for Claude Code, Cursor from Khar-AG/t-800-agent. It costs 77 tokens per session (526 once invoked), scanned A, original, MIT.

A research agent that searches GitHub, a code-hosting platform, for repositories and files containing Cursor skills, rules, agent prompts, and hooks. It performs an initial survey and passes promising repositories to another research step.

In plain words
What is it for?
Finding candidate repositories, checking their recent activity and licenses, summarizing relevant files, and preparing a handoff for detailed repository mining.
Why use it?
It narrows a broad GitHub search to active, relevant repositories before deeper inspection. It also records activity, licensing, artifact type, and possible adaptation ideas.

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; mentions Cursor.

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.

agentmods
npx agentmods add agents/khar-ag/t-800-agent/t-800-research-github
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-github

README.md
[![agentmods](https://agentmods.dev/badge/agents/khar-ag/t-800-agent/t-800-research-github.svg)](https://agentmods.dev/agents/khar-ag/t-800-agent/t-800-research-github)
Your own site
<a href="https://agentmods.dev/agents/khar-ag/t-800-agent/t-800-research-github"><img src="https://agentmods.dev/badge/agents/khar-ag/t-800-agent/t-800-research-github.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 526 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00077 $0.00526
Opus 5 $0.00039 $0.00263
Sonnet 5 $0.00015 $0.00105
Haiku 4.5 $0.00008 $0.00053

Measured 6d ago against content hash b83c5e73938c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

t-800-research-github 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 6d 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-github.md · 63 lines

What it actually says

T-800 Research — GitHub

Readonly разведка GitHub: shallow pass + список топ-репо для deep mine.

Алгоритм

  1. WebSearch (пример):
    • cursor IDE skills SKILL.md site:github.com
    • .cursor/rules site:github.com 2025 OR 2026
    • cursor subagent agents.md site:github.com
    • awesome cursor rules skills
  2. WebFetch README / SKILL.md / rules — структура, не целиком
  3. Зафиксируй: repo, stars, last commit/date, license
  4. Freshness (shared/research-freshness-contract.md)
  5. Сформируй top_repos (≥2 для DEEP) → handoff в lead → t-800-research-repo-miner
  6. Верни:
github_findings:
  - repo: "owner/name"
    url: "..."
    last_activity: "YYYY-MM-DD"
    freshness: ok|warn|block
    artifact_type: skill|rule|agent|other
    snippet_summary: "..."
    adapt_for_cursor: "..."
top_repos:
  - repo: "owner/name"
    url: "..."
    why: "..."
handoff_repo_miner: true

Приоритет

  • Репозитории с .cursor/, SKILL.md, agents/
  • Issues/PR cursor docs alignment
  • Избегай форков без активности > 6 мес

Связи

Вызывает Кто вызывает
— (handoff через lead → repo-miner) t-800-research-lead

Запреты

  • Не clone без запроса пользователя
  • Не подменять deep mine (нет дерева/scripts/hooks) — зови repo-miner через lead
  • Не выдавать устаревшее как канон
  • License: MIT/Apache OK с attribution в adaptation
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. 6d ago First seen · 63 lines · 77 tokens per session scan A b83c5e73938c

Subscribe to this mod's changes

t-800-research-github is an agent published in the GitHub repository Khar-AG/t-800-agent (8 stars, last pushed 9d ago), licensed MIT. It adds 77 tokens to every session and 526 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.