ai-coding-agents-execution-sandbox

ai-coding-agents-execution-sandbox is a skill for Codex from vasilyu1983/AI-Agents-public. It costs 39 tokens per session (3,274 once invoked), scanned C, original, MIT.

A design guide for isolating the processes that coding agents run and controlling their access to files, networks, workspaces, and environment variables. A sandbox is a restricted execution area that limits what code can reach or change.

In plain words
What is it for?
Use it to design process isolation, workspace mounts, filesystem and network rules, environment exposure, destructive-command safeguards, and cleanup policies.
Why use it?
It helps prevent agent actions from affecting unrelated files, systems, or secrets. It also defines when an action should be allowed, blocked, or sent for approval.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it to design process isolation, workspace mounts, filesystem and network rules, environment exposure, destructive-command safeguards, and cleanup policies.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vasilyu1983/ai-agents-public/ai-coding-agents-execution-sandbox
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 vasilyu1983/AI-Agents-public --skill ai-coding-agents-execution-sandbox
Clone the repo
git clone --depth 1 https://github.com/vasilyu1983/AI-Agents-public

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 ai-coding-agents-execution-sandbox

README.md
[![agentmods](https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/ai-coding-agents-execution-sandbox/github.svg)](https://agentmods.dev/skills/vasilyu1983/ai-agents-public/ai-coding-agents-execution-sandbox)
Your own site
<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/ai-coding-agents-execution-sandbox"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/ai-coding-agents-execution-sandbox/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 ai-coding-agents-execution-sandbox

Your own site · 80×15
<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/ai-coding-agents-execution-sandbox"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/ai-coding-agents-execution-sandbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,274 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00039 $0.03274
Opus 5 $0.00019 $0.01637
Sonnet 5 $0.00008 $0.00655
Haiku 4.5 $0.00004 $0.00327

Measured 12d ago against content hash 58d0a62116e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

ai-coding-agents-execution-sandbox scanned grade C with 1 finding 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

- Do not let default read policy stay broad while write policy is locked down and call the result a secrets boundary; a sandbox that can still read `~/.ssh` or `~/.aws/credentials` because only writes were restricted is
frameworks/shared-skills/skills/ai-coding-agents-execution-sandbox/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Coding Agents Execution Sandbox

Use this skill to design or review the execution substrate for a coding-agent runtime: process isolation, filesystem mounts, network policy, workspace boundaries, environment exposure, and destructive-command controls.

This skill covers where and how code runs. It complements permission routing by defining the actual isolation and policy envelope around execution.

For remote execution — managed sandbox providers, ephemeral cloud workspaces per task, hosted agent runtimes, egress policy across a network boundary, and cost per task — use ai-coding-agents-cloud-sandboxes instead.

ASCII Flow

requested execution
  |
  v
classify action
  read | write | network | process | destructive | secret-bearing
  |
  v
sandbox policy
  filesystem roots + workspace mounts + env exposure + network policy
  |
  v
decision
  allow in sandbox | ask permission | deny | require safer workspace
  |
  v
run process with bounded cwd, mounts, env, network, and cleanup rules

Quick Reference

Question Read Outcome
How should process, filesystem, and workspace isolation work? references/sandbox-process-and-filesystem-model.md Execution modes, mounts, working directories, and write boundaries
How should network, approvals, and destructive actions be controlled? references/network-approval-and-destructive-action-guards.md Outbound policy, command classes, escalation triggers, and guardrails
What sandbox mode names and backend split should runtime builders copy from Codex? references/openai-codex-sandbox-guardrails-may-2026.md read-only/workspace-write/danger-full-access modes, platform backends, fail-closed policy translation, security telemetry
What does a shipping Bash sandbox actually enforce, and where does its scope end? references/claude-code-bash-sandbox-mechanics.md Read/write asymmetry, credential deny-vs-mask, TLS-blind allowlists, tool-scope limits, known compatibility failures
What is the canonical policy format for interpreter allowlists and filesystem/network rules? references/sandbox-policy-format.md Runtime-agnostic policy fields, common traps, and translation notes
How do I verify a sandbox actually holds before shipping it? references/escape-path-test-matrix.md Symlink, interpreter-wrapper, env-injection, and package-manager escape tests with pass criteria

Read the full file on GitHub · 210 lines

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 · 210 lines · 39 tokens per session scan C 58d0a62116e1

Subscribe to this mod's changes

ai-coding-agents-execution-sandbox is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (87 stars, last pushed 10d ago), licensed MIT. It adds 39 tokens to every session and 3,274 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

nft-standards

Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.

wshobson/agents · 48 tokens

istio-traffic-management

Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.

wshobson/agents · 40 tokens

projection-patterns

Build read models and projections from event streams. Use when implementing CQRS read sides, building materialized views, or optimizing query performance in event-sourced systems.

wshobson/agents · 36 tokens

microservices-patterns

Design microservices architectures with service boundaries, event-driven communication, and resilience patterns. Use when building distributed systems, decomposing monoliths, or implementing microservices.

wshobson/agents · 38 tokens

track-management

Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.

wshobson/agents · 44 tokens

make-pr-easy-to-review

Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".

michael-denyer/pstack-claude · 57 tokens