Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Khar-AG/t-800-agentnpx agentmods add commands/khar-ag/t-800-agent/t800-auditWrote 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/commands/khar-ag/t-800-agent/t800-audit)<a href="https://agentmods.dev/commands/khar-ag/t-800-agent/t800-audit"><img src="https://agentmods.dev/badge/commands/khar-ag/t-800-agent/t800-audit/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/commands/khar-ag/t-800-agent/t800-audit"><img src="https://agentmods.dev/badge/commands/khar-ag/t-800-agent/t800-audit.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 | $0.00000 | $0.00480 |
| Opus 5 | $0.00000 | $0.00240 |
| Sonnet 5 | $0.00000 | $0.00096 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
t800-audit 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 10d 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
/t800-audit — разбор системы Cursor
Зачем: понять, какие rules/skills/commands/agents реально нужны, а какие только едят контекст.
Запуск
Task(t-800-system-auditor)
Передай: workspace root, уровень (новичок / опытный), фокус (rules / всё).
Шаг 0 — машинный аудит
bash scripts/audit-cursor-setup.sh --workspace "."
bash scripts/audit-cursor-bloat.sh "."
Что получит человек
- Карта: global vs local (rules, skills, commands, agents, plugins)
- Оценка «жира»:
alwaysApply+ размер → high/medium/low - Диалог: по каждому рискованному правилу — «оставить / сузить / удалить / что это?»
- Итоговая таблица рекомендаций (без автоудаления)
После решений (keep / narrow / remove)
Если нужно сузить rules/skills (не удалять молча):
- Оформи
{memory_path}/fix-packs/<slug>.md(шаблонtemplates/fix-pack.md.template) с конкретнымиfiles[]. - Запусти
/t800-fix— PATCH через factory, не полный/t800-start.
Для карты одного плагина → /t800-plugin-audit → t800_audit_to_fixpack.py → /t800-fix.
Связанные команды
| Команда | Когда |
|---|---|
/t800-onboard |
Быстрый обзор «что установлено» без глубокого разбора |
/t800-fix |
Сузить/поправить артефакты по fix-pack |
/t800-doctor |
Scripts-only здоровье |
/t800-start |
Создать новый rule/skill после аудита |
/t800-update |
Обновить плагин T-800 до новой версии |
/t-800-operator |
Общие вопросы про Cursor |
Закон: не отвечай на полный audit из main chat без Task(t-800-system-auditor).
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.
- 10d ago First seen · 48 lines · 0 tokens per session scan A ef73f62c597d
t800-audit is a command published in the GitHub repository Khar-AG/t-800-agent (8 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 480 tokens. 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 commands, from other repositories
pn-audit-data
Design or review database schema — normalization, indexing strategy, migration plan, and data model decisions. Surgical command for database design. Use standalone or as part of pn-backend-audit.
pn-audit-performance
Identify and fix backend performance issues — N+1 queries, missing cache layers, blocking I/O, slow queries, and connection pool exhaustion. Surgical backend performance pass.
pn-delight
Add purposeful moments of joy, motion, and personality. Use when the design is correct and complete but feels flat and lifeless.
pn-audit-api
Surgical API design review — REST conventions, status codes, response shapes, validation, and schema leaks. Use standalone or as part of pn-backend-audit. Outputs a scored fix roadmap.
pn-audit-errors
Standardize error handling — consistent shapes, structured logging, correlation IDs, safe client responses. Surgical command for error handling. Use standalone or as part of pn-backend-audit.
pn-audit-security
OWASP-guided security review — auth posture, input validation, secrets, CORS, JWT, rate limiting. Surgical command for backend security. Use standalone or as part of pn-backend-audit.