images

Commands for managing Docker images and building custom ones from Dockerfiles. A Docker image is a packaged environment containing the files and tools needed to run software.

In plain words
What is it for?
Use them to build, list, pull, synchronize, delete, and clean up images, then use a custom image in a sandbox.
Why use it?
They help keep sandbox environments consistent and avoid reinstalling the same tools every time a sandbox is created.

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/thrashr888/agentkernel/images
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 730 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 $0.00730
Opus 5 $0.00000 $0.00365
Sonnet 5 $0.00000 $0.00146
Haiku 4.5 $0.00000 $0.00073

Measured 2d ago against content hash ca08bf91a5b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

images 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 2d 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.

docs/commands/images.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agentkernel images & build

Manage Docker images and build custom images from Dockerfiles.

Subcommands

Command Description
build -t <name> <context> [--dockerfile PATH] Build a custom image from Dockerfile
images list [--all] List Docker images with sandbox usage
images local-list List locally built custom images
images local-delete <name> Delete a locally built image
images local-sync Sync metadata with actual Docker images
images prune [--agentkernel-only] Remove unused images
images pull <IMAGE> Pre-pull a Docker image

Examples

Build a custom image

Build custom images with your tools pre-installed:

# Build from Dockerfile in current directory
agentkernel build -t my-tools .

# Build with a specific Dockerfile
agentkernel build -t python-ml ./docker --dockerfile ./docker/Dockerfile.ml

Example Dockerfile:

FROM python:3.12-alpine
RUN pip install numpy pandas scikit-learn

Use custom images in sandboxes:

agentkernel sandbox create ml-sandbox --image my-tools
agentkernel sandbox start ml-sandbox
agentkernel exec ml-sandbox -- python3 -c "import numpy; print(numpy.__version__)"

List locally built images

$ agentkernel images local-list
NAME       SIZE      BUILT AT             DOCKER TAG
my-tools   145MB     2025-01-20 10:30:00  agentkernel-my-tools
python-ml  312MB     2025-01-20 11:00:00  agentkernel-python-ml

Delete a local image

agentkernel images local-delete my-tools

Sync local image metadata

If you manually delete Docker images, sync the metadata:

agentkernel images local-sync

List images

# Show agentkernel-related images only
$ agentkernel images list
No agentkernel images found. Use --all to show all images.

# Show all Docker images with usage info
$ agentkernel images list --all
REPOSITORY:TAG                           IMAGE ID        USED BY            SIZE
python:3.12-alpine                       82585c9f05cf    1 sandbox        79.7MB
alpine:3.24                              a4f4213abb84    2 sandboxes      13.7MB
node:22-alpine                           d7119ab9e005    unused            307MB

3 images, 3 sandbox references

Read the full file on GitHub · 112 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. 2d ago First seen · 112 lines · 0 tokens per session scan A ca08bf91a5b8

Subscribe to this mod's changes

images is a command published in the GitHub repository thrashr888/agentkernel (58 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 730 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.