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.
git clone --depth 1 https://github.com/thrashr888/agentkernelWrote 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.
[](https://agentmods.dev/commands/thrashr888/agentkernel/sandbox)<a href="https://agentmods.dev/commands/thrashr888/agentkernel/sandbox"><img src="https://agentmods.dev/badge/commands/thrashr888/agentkernel/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.
<a href="https://agentmods.dev/commands/thrashr888/agentkernel/sandbox"><img src="https://agentmods.dev/badge/commands/thrashr888/agentkernel/sandbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00009 | $0.00300 |
| Opus 5.5 | $0.00004 | $0.00120 |
| Sonnet 5.5 | $0.00002 | $0.00060 |
| Haiku 4.5 | $0.00001 | $0.00030 |
Grade A, and why
sandbox 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 2mo 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.
What it actually says
/sandbox Command
Run a command in an isolated agentkernel sandbox for security.
Usage
/sandbox <command>
/sandbox --profile restrictive <command>
/sandbox --no-network <command>
Examples
/sandbox python3 -c "print('Hello from sandbox!')"
/sandbox npm test
/sandbox cargo build
/sandbox --profile restrictive python3 untrusted_script.py
/sandbox --no-network python3 -c "import os; print(os.getcwd())"
Security Profiles
permissive- Network, mounts, environment passthrough enabledmoderate(default) - Network enabled, no mounts, no env passthroughrestrictive- No network, read-only filesystem, all capabilities dropped
Instructions
When the user invokes /sandbox <command>:
- Parse the command and any flags from the user's input
- Run it using agentkernel:
# Basic usage
agentkernel run <command>
# With security profile
agentkernel run --profile restrictive <command>
# Disable network
agentkernel run --no-network <command>
- Display the output to the user
- If the command fails, show the error message
The command will auto-detect the appropriate runtime based on what's being executed.
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.
- 2mo ago First seen · 57 lines · 9 tokens per session scan A 9d0d41db50ff
sandbox is a command published in the GitHub repository thrashr888/agentkernel (59 stars, last pushed today), licensed MIT. It adds 9 tokens to every session and 300 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-30.
Other commands, from other repositories
rust-test
Enforce TDD workflow for Rust. Write tests first, then implement. Verify 80%+ coverage with cargo-llvm-cov.
rust-build
Fix Rust build errors, borrow checker issues, and dependency problems incrementally. Invokes the rust-build-resolver agent for minimal, surgical fixes.
rust-review
Comprehensive Rust code review for ownership, lifetimes, error handling, unsafe usage, and idiomatic patterns. Invokes the rust-reviewer agent.
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
hep-local.body
A local workforce command that searches agents registered on this machine and prepares a selected group for a task.
rclone_config_dump
Dump the config file as JSON.