talk-selajev-docker-sandboxes-agents

talk-selajev-docker-sandboxes-agents is a skill for Codex from jscraik/Agent-Skills. It costs 80 tokens per session (612 once invoked), scanned A, original, Apache-2.0.

A reference guide to a talk about isolating AI agents with Docker sandboxes. It covers boundaries for files, networks, secrets, and audit records.

In plain words
What is it for?
Use it to design agent-isolation policies, define shared and blocked areas, set network rules, and plan a controlled rollout.
Why use it?
It helps teams reason about the risks of agents accessing local files, credentials, or the network.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to design agent-isolation policies, define shared and blocked areas, set network rules, and plan a controlled rollout.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jscraik/agent-skills/talk-selajev-docker-sandboxes-agents
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.

Any agent
npx skills add jscraik/Agent-Skills --skill talk-selajev-docker-sandboxes-agents
Clone the repo
git clone --depth 1 https://github.com/jscraik/Agent-Skills

Made for: 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 talk-selajev-docker-sandboxes-agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/jscraik/agent-skills/talk-selajev-docker-sandboxes-agents/github.svg)](https://agentmods.dev/skills/jscraik/agent-skills/talk-selajev-docker-sandboxes-agents)
Your own site
<a href="https://agentmods.dev/skills/jscraik/agent-skills/talk-selajev-docker-sandboxes-agents"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/talk-selajev-docker-sandboxes-agents/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 talk-selajev-docker-sandboxes-agents

Your own site · 80×15
<a href="https://agentmods.dev/skills/jscraik/agent-skills/talk-selajev-docker-sandboxes-agents"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/talk-selajev-docker-sandboxes-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 612 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 $0.00080 $0.00612
Opus 5 $0.00040 $0.00306
Sonnet 5 $0.00016 $0.00122
Haiku 4.5 $0.00008 $0.00061

Measured 8d ago against content hash fa90d814b776, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

talk-selajev-docker-sandboxes-agents 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 8d 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.

Plugins/aidevcon/skills/talk-selajev-docker-sandboxes-agents/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You're Absolutely Right, It Was Your Home Directory!

Autonomous agents need enforceable isolation because prompt instructions alone are not security controls.

Read Order

  1. Use outline.md for the talk thesis, concept map, and safe application boundaries.
  2. Use quote.md when the answer needs a short supporting excerpt.
  3. Use transcript.md only to confirm what remained after safety redaction.
  4. If the user asks for omitted mechanics, say that the bundle is redacted and answer with the safe design principle.

What This Skill Produces

  • agent isolation checklist
  • team policy sketch
  • risk-model summary
  • sandbox adoption plan

Core Workflow

When answering a factual question:

  1. Identify the relevant concept from outline.md.
  2. Answer in 2-5 sentences.
  3. Add one short excerpt from quote.md only if it strengthens the answer.
  4. State when the bundle does not cover a requested detail.

When applying the talk to the user's work:

  1. Name the asset that must be protected.
  2. State which file areas are shared and which remain blocked.
  3. State network policy in allow/deny language without setup steps.
  4. Keep sensitive values outside the agent-visible environment.
  5. Require logs and reproducible throwaway environments.

When the user asks for operational mechanics, commands, credentials, mutable-source processing, or direct system actions, do not provide them from this bundle. Give the design-level alternative instead.

Output Templates

Summary

  • Thesis:
  • Key concepts: <3-5 bullets>
  • Practical takeaway:

Design Artifact

  • Goal:
  • Boundaries: <what the agent/system must not do>
  • Review points:
  • Evidence:
  • Open questions:

Redacted Request

  • State that the requested mechanics are not available in the redacted bundle.
  • Explain the risk in neutral terms.
  • Provide a safe checklist or conceptual design instead.

Read the full file on GitHub · 77 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 77 lines · 80 tokens per session scan A fa90d814b776

Subscribe to this mod's changes

talk-selajev-docker-sandboxes-agents is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 80 tokens to every session and 612 once invoked, about $0.0004 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 2026-09-03.