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.
npx agentmods add commands/thrashr888/agentkernel/sandboxgit clone --depth 1 https://github.com/thrashr888/agentkernelWhat 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 | $0.00009 | $0.00300 |
| Opus 5 | $0.00005 | $0.00150 |
| Sonnet 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 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.
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.
- 2d ago First seen · 57 lines · 9 tokens per session scan A 9d0d41db50ff
sandbox is a command published in the GitHub repository thrashr888/agentkernel (58 stars, last pushed 3d ago), licensed MIT. It adds 9 tokens to every session and 300 once invoked, about $0.0000 per session on Opus 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
MIGRATE_DESIGN
Design doc for the migration tool PR. Author: Sol ([email protected]). Co-authored-by: wakesync.
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
OpenSpec: Apply
Implement an approved OpenSpec change and keep tasks in sync.
diff
Compare two SKILL.md files section-by-section. Parses frontmatter and body sections independently, showing exactly what changed.
commit
智能生成 Git 提交信息并提交.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.