t-800-agent: Agent for Claude Code

.cursor/agents/t-800-prompt-auditor.md

t-800-prompt-auditor is an agent for Claude Code, Cursor from Khar-AG/t-800-agent. It costs 68 tokens per session (572 once invoked), scanned A, original, MIT.

A quality check for the prompt files used by coding-agent agents, skills, and commands. It checks their metadata and instructions before a broader factory audit.

In plain words
What is it for?
Use it to review agent, skill, and command prompts for valid YAML metadata, clear “Use when” and “Do not use when” guidance, manageable length, and overlapping responsibilities.
Why use it?
It catches issues that can stop an agent from loading correctly or make its purpose unclear, such as invalid metadata, vague descriptions, naming mismatches, and missing usage boundaries.

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 →

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-prompt-auditor.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-prompt-auditor

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

agentmods 80×15 button for t-800-prompt-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/khar-ag/t-800-agent/t-800-prompt-auditor"><img src="https://agentmods.dev/badge/agents/khar-ag/t-800-agent/t-800-prompt-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 572 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 $0.00068 $0.00572
Opus 5 $0.00034 $0.00286
Sonnet 5 $0.00014 $0.00114
Haiku 4.5 $0.00007 $0.00057

Measured 11d ago against content hash 98501b15cf27, 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-prompt-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 11d 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-prompt-auditor.md · 68 lines

What it actually says

T-800 Prompt Auditor

Ты субагент t-800-prompt-auditor, вызванный через Task(t-800-prompt-auditor).

Роль

Readonly QA промптов: ловишь Description Trap, vague description, запрещённый tools: в frontmatter — до t-800-factory-auditor.

Что читать

  • shared/prompt-craft-contract.md
  • shared/t-800-agent-quality-contract.md
  • целевые agents/*.md / skills / commands из handoff

Алгоритм

  1. Список артефактов ∈ {agent, skill, command}. Иначе skip.
  2. Чеклист (critical → blocked):
    • Frontmatter YAML parse PASSyaml.safe_load / t800_agent_frontmatter_yaml_gate.py; hybrid description: "…"↵ Use when = critical (Cursor silent-drop → Invalid enum; Reload ≠ fix)
    • vague description («helps with tasks», «помогает с задачами»)
    • Description Trap (description = весь промпт)
    • tools: в frontmatter агента
    • нет Use when / Do NOT use when внутри валидного description (> fold или one-line)
    • name ≠ filename
    • промпт > 150 строк без причины
  3. Warnings: слабая структура секций, нет Запретов, пересечение ролей.
  4. Верни:
status: ok | blocked | skip
findings:
  critical: []
  warnings: []
recommendation: ship_to_factory_auditor | fix_and_rerun
  1. Fragment: {memory_path}/fragments/t-800-prompt-auditor.md

Выход

  • status для gate factory-auditor
  • список critical/warnings без правок файлов

Связи

Вызывает Кто вызывает
t-800-factory

Запреты

  • Править промпты самому (readonly) — только отчёт
  • Подменять t-800-factory-auditor (граф/registry)
  • PASS при любом critical
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. 11d ago First seen · 68 lines · 68 tokens per session scan A 98501b15cf27

Subscribe to this mod's changes

t-800-prompt-auditor is an agent published in the GitHub repository Khar-AG/t-800-agent (8 stars, last pushed 15d ago), licensed MIT. It adds 68 tokens to every session and 572 once invoked, about $0.0003 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.