index

A directory of preconfigured Docker environments for popular AI coding agents, including Claude Code, OpenAI Codex, Gemini, GitHub Copilot, and others.

In plain words
What is it for?
Use it to choose an agent, install its plugin, create a sandbox, start the agent with the required API key, or connect an agent running locally to sandboxed code execution.
Why use it?
It provides a consistent way to run different coding agents and, in plugin mode, keep code execution inside a sandbox.

Agent

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 agents/thrashr888/agentkernel/index
Clone the repo
git clone --depth 1 https://github.com/thrashr888/agentkernel
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 635 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00635
Opus 5 $0.00000 $0.00318
Sonnet 5 $0.00000 $0.00127
Haiku 4.5 $0.00000 $0.00064

Measured yesterday against content hash 1719269bcaef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

index 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 yesterday.

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.

docs/agents/index.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agents

agentkernel provides pre-configured Docker images for popular AI coding agents. These images include all necessary dependencies and are optimized for sandbox execution.

Supported Agents

Agent CLI Command API Key Variable
Claude Code claude ANTHROPIC_API_KEY
OpenAI Codex codex OPENAI_API_KEY
Google Gemini gemini GEMINI_API_KEY
GitHub Copilot copilot GITHUB_TOKEN
Amp amp ANTHROPIC_API_KEY
Pi pi ANTHROPIC_API_KEY or OPENAI_API_KEY
OpenCode opencode Provider-specific
Hermes Agent hermes OPENROUTER_API_KEY or ANTHROPIC_API_KEY
Symphony symphony LINEAR_API_KEY + OPENAI_API_KEY

Quick Start

Plugin Mode (agent runs locally, code runs in sandbox)

# Install the plugin for your agent
agentkernel plugin install claude     # or: codex, gemini, copilot, amp, pi, opencode, mcp

Sandbox Mode (agent runs inside the sandbox)

# Create a sandbox with Claude Code
agentkernel sandbox create my-agent --config examples/agents/claude-code/agentkernel.toml

# Start and run with your API key
agentkernel sandbox start my-agent
agentkernel exec my-agent -e ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY -- claude -p "Hello"

Common Features

All agent images include:

  • Node.js 24 LTS - Runtime for agent CLIs
  • Git - Version control
  • Python 3 - For Python projects
  • ripgrep - Fast code search
  • fd - Fast file finder
  • jq - JSON processing
  • bash - Shell

Security

All agent images:

  • Run as non-root user developer
  • Have workspace isolated at /workspace
  • Respect agentkernel security profiles
  • Require explicit API key passthrough (not inherited from host)

Custom Agent Images

Create your own agent image by extending the base:

FROM agentkernel/claude-code

# Add your tools
RUN apk add --no-cache your-tools

# Add project-specific configuration
COPY .claude /home/developer/.claude/

Read the full file on GitHub · 81 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. yesterday First seen · 81 lines · 0 tokens per session scan A 1719269bcaef

Subscribe to this mod's changes

index is an agent published in the GitHub repository thrashr888/agentkernel (58 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 635 tokens. 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.