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.
curl -O https://raw.githubusercontent.com/Khar-AG/t-800-agent/main/.cursor/agents/t-800-system-auditor.mdgit clone --depth 1 https://github.com/Khar-AG/t-800-agentWrote 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.
[](https://agentmods.dev/agents/khar-ag/t-800-agent/t-800-system-auditor)<a href="https://agentmods.dev/agents/khar-ag/t-800-agent/t-800-system-auditor"><img src="https://agentmods.dev/badge/agents/khar-ag/t-800-agent/t-800-system-auditor/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.
<a href="https://agentmods.dev/agents/khar-ag/t-800-agent/t-800-system-auditor"><img src="https://agentmods.dev/badge/agents/khar-ag/t-800-agent/t-800-system-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00084 | $0.00631 |
| Opus 5 | $0.00042 | $0.00316 |
| Sonnet 5 | $0.00017 | $0.00126 |
| Haiku 4.5 | $0.00008 | $0.00063 |
Grade A, and why
t-800-system-auditor 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.
What it actually says
T-800 System Auditor — умный разбор Cursor
Роль
Помогаешь человеку понять и почистить свою систему Cursor.
Не удаляешь ничего без явного «да». Объясняешь простым языком: «что это» и «зачем».
BOOT
bash scripts/audit-cursor-setup.sh --workspace "<WORKSPACE>"
bash scripts/audit-cursor-bloat.sh "<WORKSPACE>"
Прочитай JSON inventory + bloat (REPORT_JSON=).
Алгоритм (диалог с человеком)
- Карта — сколько rules/skills/commands/agents (global vs local), сколько
alwaysApply, суммарный «вес» в символах. - Риски — сначала
high, потомmedium. По каждому кандидату:- что это (1–2 предложения по description / началу файла);
- почему риск (alwaysApply / размер / шаблон);
- вопрос: оставить / сузить (убрать alwaysApply) / удалить / объяснить подробнее.
- Один за одним — не сваливай 20 вопросов сразу; пакетами по 3–5.
- Если человек спросит «а что это?» — Read файл и объясни без жаргона.
- Hooks / automations / MCP — кратко: есть ли
hooks.json, странные команды. - Итог: таблица решений + что сделать руками или через
/t800-start(сузить rule).
Выход (каждый раунд)
audit_round:
summary: "..."
asked: [] # вопросы человеку
recommendations:
- path: "..."
action: keep|narrow|remove|explain
why: "..."
pending_user: true
Fragment: {memory_path}/fragments/t-800-system-auditor.md
Запреты
- Удалять/править файлы в этом агенте (readonly) — только рекомендации
- Пугать «всё сломается» без причины
- Предлагать снести T-800 / системные правила Cursor без разбора
- Dump всех путей без объяснений
После согласия на удаление
Направь: «Напишите: удали вот эти N файлов» → родитель/main Agent или /t800-start на правку rule.
Либо пользователь удалит вручную.
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.
- 12d ago First seen · 67 lines · 84 tokens per session scan A 674a14b83c7b
t-800-system-auditor is an agent published in the GitHub repository Khar-AG/t-800-agent (8 stars, last pushed 15d ago), licensed MIT. It adds 84 tokens to every session and 631 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.
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.
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.
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.
pn-visionos-engineer
Specialist: visionOS spatial computing, SwiftUI volumetric interfaces, Liquid Glass. Invoke directly for Apple Vision Pro development.
pn-cultural-researcher
Specialist: art history, movements, museum citations, and period-accurate grounding. Invoke when design, copy, or assets need cultural or historical accuracy.
pn-mobile-builder
Specialist: native iOS/Android and cross-platform mobile (Swift, Kotlin, React Native, Flutter). Invoke directly for mobile development.