agent-shielded

agent-shielded is a skill for Claude Code, Codex from Michae2xl/freedom-stack. It costs 123 tokens per session (2,127 once invoked), scanned B, original, no licence file.

A private infrastructure setup for AI agents that includes local models, workflow tools, data storage, network privacy tools, and monitoring services. It is designed to keep agent data within private infrastructure.

In plain words
What is it for?
Use it to deploy private AI-agent infrastructure with tools such as Ollama, n8n, Qdrant, sandboxing, Tor, dashboards, and monitoring.
Why use it?
It addresses the risk of sending agent data through services or networks you do not control.

Skill for Claude CodeCodex

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 skills/michae2xl/freedom-stack/agent-shielded
Any agent
npx skills add Michae2xl/freedom-stack --skill agent-shielded
Clone the repo
git clone --depth 1 https://github.com/Michae2xl/freedom-stack

Made for: Claude Code, 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 agent-shielded

README.md
[![agentmods](https://agentmods.dev/badge/skills/michae2xl/freedom-stack/agent-shielded.svg)](https://agentmods.dev/skills/michae2xl/freedom-stack/agent-shielded)
Your own site
<a href="https://agentmods.dev/skills/michae2xl/freedom-stack/agent-shielded"><img src="https://agentmods.dev/badge/skills/michae2xl/freedom-stack/agent-shielded.svg" alt="Measured on agentmods" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,127 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00123 $0.02127
Opus 5 $0.00062 $0.01064
Sonnet 5 $0.00025 $0.00425
Haiku 4.5 $0.00012 $0.00213

Measured 4d ago against content hash 1987e7223c41, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

agent-shielded scanned grade B with 2 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

analysis = requests.post("http://ollama:11434/api/generate", json={

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://raw.githubusercontent.com/Michae2xl/freedom-stack/main/scripts/install.sh -o install.sh
skills/agent-shielded/SKILL.md · 237 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 · 237 lines · 123 tokens per session scan B 1987e7223c41

Subscribe to this mod's changes

agent-shielded is a skill published in the GitHub repository Michae2xl/freedom-stack (10 stars, last pushed 5mo ago), with no licence file. It adds 123 tokens to every session and 2,127 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories