arckit.agent-security

arckit.agent-security is a command for coding agents from tractorjuice/arckit-codex. It costs 16 tokens per session (3,319 once invoked), scanned A, original, no licence file.

A design guide for securing AI agents through isolated execution, limited permissions, defences against instructions hidden in untrusted input, and checks on generated output.

In plain words
What is it for?
Use it when designing agent security controls such as sandboxing, permissions, injection defences, and output validation.
Why use it?
It helps reduce the risk of an agent accessing too much, following malicious instructions, or producing unchecked results.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/tractorjuice/arckit-codex/arckit.agent-security
Clone the repo
git clone --depth 1 https://github.com/tractorjuice/arckit-codex

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 arckit.agent-security

README.md
[![agentmods](https://agentmods.dev/badge/commands/tractorjuice/arckit-codex/arckit.agent-security.svg)](https://agentmods.dev/commands/tractorjuice/arckit-codex/arckit.agent-security)
Your own site
<a href="https://agentmods.dev/commands/tractorjuice/arckit-codex/arckit.agent-security"><img src="https://agentmods.dev/badge/commands/tractorjuice/arckit-codex/arckit.agent-security.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,319 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00016 $0.03319
Opus 5 $0.00008 $0.01659
Sonnet 5 $0.00003 $0.00664
Haiku 4.5 $0.00002 $0.00332

Measured 4d ago against content hash 28629c989c76, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arckit.agent-security 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 4d 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.

commands/arckit.agent-security.md · 306 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 4d ago First seen · 306 lines · 16 tokens per session scan A 28629c989c76

Subscribe to this mod's changes

arckit.agent-security is a command published in the GitHub repository tractorjuice/arckit-codex (16 stars, last pushed today), with no licence file. It adds 16 tokens to every session and 3,319 once invoked, about $0.0001 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 2026-08-30.

Related

Other commands, from other repositories

at-bvergg

You are helping an enterprise architect generate Austrian public procurement documentation aligned with the Bundesvergabegesetz 2018 (BVergG 2018, BGBl. I Nr. 65/2018), as amended most recently by the Vergaberechtsgesetz 2026 (BGBl. I Nr. 8/2026 — the largest procurement reform since 2018; in force 1 March 2026, with…

tractorjuice/arc-kit · 50 tokens

at-nisg

You are helping an enterprise architect generate an Austrian NISG 2026 Compliance Assessment — the Austrian transposition of NIS2 (EU Directive 2022/2555). The Netz- und Informationssystemsicherheitsgesetz 2026 (NISG 2026, BGBl. I Nr. 94/2025) is a standalone act (not a mere amendment of the NISG 2018). It was passed…

tractorjuice/arc-kit · 71 tokens

agent-inventory

Catalog existing AI agents with capabilities, security classification, and oversight level.

tractorjuice/arc-kit · 13 tokens

agent-security

Design AI agent security — sandboxing, permissions, injection defences, output validation.

tractorjuice/arc-kit · 16 tokens

at-dsgvo

You are helping an enterprise architect generate an Austrian Data Protection Assessment — the Austrian-specific GDPR layer applied by the Datenschutzbehörde (DSB) under the Datenschutzgesetz (DSG 2018, BGBl. I Nr. 165/1999 as amended). Run this after /arckit:eu-rgpd to add Austrian obligations that go beyond the EU…

tractorjuice/arc-kit · 35 tokens

agent-governance

Design AI agent governance — oversight models, approval workflows, audit requirements, compliance mapping.

tractorjuice/arc-kit · 16 tokens