volumes

Commands for managing persistent volumes, storage areas that keep their data after a sandbox restarts.

In plain words
What is it for?
Use them to create, list, inspect, delete, and mount volumes, including read-only mounts.
Why use it?
They separate data from a sandbox so that the data can survive the sandbox lifecycle.

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/volumes
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 701 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 $0.00701
Opus 5 $0.00000 $0.00351
Sonnet 5 $0.00000 $0.00140
Haiku 4.5 $0.00000 $0.00070

Measured 2d ago against content hash 345cfa8ea48a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

volumes 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/volumes.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agentkernel volume

Manage persistent volumes that survive sandbox restarts. Volumes are stored in ~/.agentkernel/volumes/.

Subcommands

Command Description
volume create <slug> [--size SIZE] Create a new volume
volume list List all volumes
volume info <slug> Show volume details
volume delete <slug> [--force] Delete a volume

Examples

Create a volume

# Create a volume with default settings
agentkernel volume create mydata

# Create with a size hint (for display only)
agentkernel volume create cache --size 2GB

Size accepts: B, KB, MB, GB suffixes (e.g., 512MB, 2GB).

List volumes

$ agentkernel volume list
SLUG       SIZE      CREATED              MOUNTS
mydata     1.2MB     2025-01-20 10:30:00  3
cache      0B        2025-01-20 11:00:00  0

Use a volume with a sandbox

Mount volumes when creating a sandbox with --volume or -v:

# Mount mydata volume at /data
agentkernel sandbox create dev --volume mydata:/data

# Mount read-only
agentkernel sandbox create dev --volume mydata:/data:ro

# Multiple volumes
agentkernel sandbox create dev \
  --volume mydata:/data \
  --volume cache:/cache

The volume must exist before mounting. Create it first:

agentkernel volume create mydata
agentkernel sandbox create dev --volume mydata:/data
agentkernel sandbox start dev
agentkernel exec dev -- ls /data

Volume info

$ agentkernel volume info mydata
Slug:       mydata
Size:       1.2MB
Created:    2025-01-20 10:30:00
Last Used:  2025-01-20 14:00:00
Mounts:     3
Path:       /Users/user/.agentkernel/volumes/mydata

Delete a volume

# Delete (will prompt if in use)
agentkernel volume delete mydata

# Force delete without prompt
agentkernel volume delete mydata --force

Volume Format

Volume mount specs follow the format: slug:/container/path[:ro]

  • slug - Volume identifier (alphanumeric, hyphens, underscores)
  • /container/path - Mount point inside the sandbox
  • :ro - Optional read-only flag

Read the full file on GitHub · 107 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 · 107 lines · 0 tokens per session scan A 345cfa8ea48a

Subscribe to this mod's changes

volumes 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 701 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.