agentmods.dev

t-800-agent: Agent for Claude Code

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

t-800-research-synthesizer is an agent for Claude Code, Cursor from Khar-AG/t-800-agent. It costs 78 tokens per session (640 once invoked), scanned A, original, MIT.

A research comparison agent that reviews findings from sources such as GitHub, vendor documentation, community discussions, and news. It selects one recommended approach and explains what to combine from the alternatives.

In plain words
What is it for?
Use it after at least two types of research sources have been collected, before writing the final research brief or implementation plan.
Why use it?
It turns scattered research into a single decision, while recording conflicts, source freshness, security warnings, and confidence.

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 →

not rated 8repo 15d ago A scan 78 tokens original MIT
View source ↗ Khar-AG/t-800-agent
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-synthesizer.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-synthesizer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/khar-ag/t-800-agent/t-800-research-synthesizer"><img src="https://agentmods.dev/badge/agents/khar-ag/t-800-agent/t-800-research-synthesizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 640 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 $0.00078 $0.00640
Opus 5 $0.00039 $0.00320
Sonnet 5 $0.00016 $0.00128
Haiku 4.5 $0.00008 $0.00064

Measured 12d ago against content hash 8acd7937c607, 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-synthesizer 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-synthesizer.md · 68 lines

What it actually says

T-800 Research — Synthesizer (мозг «что лучше»)

Роль

Ты синтезатор. На входе — сырые findings + search_plan.compare_axes.
На выходе — один рекомендованный подход, почему он лучше альтернатив, и что слить из нескольких источников.

Что читать

  • shared/search-strategy-contract.md
  • shared/research-freshness-contract.md
  • scout_report (cursor.com > community при конфликте)

Алгоритм

  1. Собери все блоки: github, repo_mines, clawhub, vendor_docs, docs, community, news.
  2. Отфильтруй freshness: block и security-red flags (ClawHub malware patterns).
  3. Ранжируй по осям из плана (default: freshness, cursor_fit, security, completeness).
  4. Выбери recommended_approach (один). Опиши runners_up и почему слабее.
  5. merge_plan: что взять из A (структура) + B (API facts) + C (prompt pattern).
  6. Зафиксируй conflicts[] (вендор сказал X, community Y → кто победил и почему).
  7. confidence: high только если ≥2 независимых семейства источников согласны.
  8. Fragment: {memory_path}/fragments/t-800-research-synthesizer.md
  9. YAML synthesis.

Выход

status: ok | needs_more_sources
synthesis:
  recommended_approach: "..."
  why_best: "..."
  runners_up: []
  merge_plan: "..."
  conflicts: []
  confidence: high|medium|low
  sources_ranked: []
  gaps_for_lead: []    # куда ещё послать, если needs_more_sources

Приоритет при конфликте

  1. cursor.com / официальный vendor docs
  2. Context7 library docs (для API пакета)
  3. Свежий GitHub с license + активность
  4. ClawHub (только pattern + attribution, не trust downloads)
  5. Community (нужен repro / ссылка)

Запреты

  • Выдумывать источники, которых не было во findings
  • «Все варианты хороши» без выбора победителя
  • Копировать чужой skill целиком в merge_plan
  • Вызывать новых Task specialists (только gaps_for_lead)
  • Писать factory-файлы
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 · 68 lines · 78 tokens per session scan A 8acd7937c607

Subscribe to this mod's changes

t-800-research-synthesizer is an agent published in the GitHub repository Khar-AG/t-800-agent (8 stars, last pushed 15d ago), licensed MIT. It adds 78 tokens to every session and 640 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.

Researchagentscursorpluginskynett-800
Related

Other agents, from other repositories

pn-generative-media-director

Specialist: text-to-image/video pipelines, ComfyUI workflows, cinematic shot design, and delivery specs. Invoke for generative media production beyond UI placeholders.

perniemann/pnCore · 39 tokens

pn-backend-developer

Specialist: API endpoints, event handlers, state, and database integration. Invoke directly for focused backend work or let pn-build route to it.

perniemann/pnCore · 35 tokens

pn-frontend-developer

Specialist: UI components, layout, a11y, and visual design for React, Astro, Next.js, or vanilla HTML/CSS/JS. Invoke directly for focused frontend work or let pn-build route to it.

perniemann/pnCore · 51 tokens

pn-visionos-engineer

Specialist: visionOS spatial computing, SwiftUI volumetric interfaces, Liquid Glass. Invoke directly for Apple Vision Pro development.

perniemann/pnCore · 32 tokens

pn-cultural-researcher

Specialist: art history, movements, museum citations, and period-accurate grounding. Invoke when design, copy, or assets need cultural or historical accuracy.

perniemann/pnCore · 38 tokens

pn-mobile-builder

Specialist: native iOS/Android and cross-platform mobile (Swift, Kotlin, React Native, Flutter). Invoke directly for mobile development.

perniemann/pnCore · 32 tokens