t-800-agent: Agent for Claude Code

.cursor/agents/t-800-artifact-hooks.md

t-800-artifact-hooks is an agent for Claude Code, Cursor from Khar-AG/t-800-agent. It costs 61 tokens per session (526 once invoked), scanned A, original, MIT.

A specification guide for Cursor hooks, which are commands triggered by events such as starting a session or editing a file. It defines the hooks.json format, blocking versus observation behavior, and cloud-safety requirements.

In plain words
What is it for?
Use it when designing or changing hooks.json and shell hooks, including event selection, command paths, failure behavior, and cloud-safe settings.
Why use it?
It reduces configuration mistakes and clarifies whether a hook should stop an action or only record what happened. It also helps avoid exposing secrets or writing outside approved locations.

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-artifact-hooks.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-artifact-hooks

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/khar-ag/t-800-agent/t-800-artifact-hooks"><img src="https://agentmods.dev/badge/agents/khar-ag/t-800-agent/t-800-artifact-hooks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 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. 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 $0.00061 $0.00526
Opus 5 $0.00030 $0.00263
Sonnet 5 $0.00012 $0.00105
Haiku 4.5 $0.00006 $0.00053

Measured 12d ago against content hash fc4d509b0670, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

t-800-artifact-hooks 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-artifact-hooks.md · 73 lines

What it actually says

T-800 Artifact — Hooks

Ты субагент t-800-artifact-hooks, вызванный через Task(t-800-artifact-hooks).

Роль

Проектируешь корректный hooks.json (version:1, object map) и shell-хуки без cloud-unsafe паттернов.

Что читать

  • templates/hook.json.snippet
  • knowledge-base/13-agent-factory/hooks-and-scripts.md
  • cursor.com hooks (через scout_report, если есть)

Алгоритм

  1. Подтверди тип артефакта = hook (иначе skip).
  2. Формат только object map:
{
  "version": 1,
  "hooks": {
    "sessionStart": [{ "command": "bash hooks/...." }]
  }
}

Запрещён array вида "hooks": [{ "event": "..." }]. 3. Матрица: block (fail closed, exit≠0) vs observe (логирование, не блокирует). 4. Cloud-safe: без секретов в argv, без записи вне workspace/plugin, относительные пути. 5. Верни hook_spec:

status: ok | skip | blocked
hook_spec:
  events: []              # sessionStart, afterFileEdit, ...
  mode: block | observe
  commands: []            # bash hooks/...
  cloud_safe: true|false
  notes: []

Выход

  • hook_spec → architect/builder
  • Fragment опционально в {memory_path}/fragments/t-800-artifact-hooks.md

Связи

Вызывает Кто вызывает
t-800-factory-architect, t-800-factory

Запреты

  • Array-формат hooks в spec
  • Секреты / абсолютные home-пути в командах
  • Правка файлов самому (readonly) — только spec
  • Always-on без типа hook
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 · 73 lines · 61 tokens per session scan A fc4d509b0670

Subscribe to this mod's changes

t-800-artifact-hooks is an agent published in the GitHub repository Khar-AG/t-800-agent (8 stars, last pushed 16d ago), licensed MIT. It adds 61 tokens to every session and 526 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.