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.
/plugin marketplace add zekker6/devsandboxnpx agentmods add plugins/zekker6/devsandbox/marketplacegit clone --depth 1 https://github.com/zekker6/devsandboxGrade A, and why
devsandbox 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
{
"name": "devsandbox",
"description": "Plugins for devsandbox, the sandbox for AI coding assistants",
"owner": {
"name": "zekker6",
"url": "https://github.com/zekker6"
},
"plugins": [
{
"name": "devsandbox-config",
"source": "./.claude-plugin/devsandbox-config",
"description": "Answer devsandbox configuration questions from the published documentation instead of from memory"
},
{
"name": "devsandbox-triage",
"source": "./.claude-plugin/devsandbox-triage",
"description": "Recognize command failures caused by devsandbox's isolation and point at the setting or document that explains them"
}
]
}
What ships with it
7 files beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- devsandbox-config/.claude-plugin/plugin.json 440 B
- devsandbox-config/skills/devsandbox-config/SKILL.md 9.2 KB
- devsandbox-triage/.claude-plugin/plugin.json 444 B
- devsandbox-triage/hooks/hooks.json 539 B
- devsandbox-triage/README.md 3.0 KB
- devsandbox-triage/scripts/triage_test.sh 10 KB runs code
- devsandbox-triage/scripts/triage.sh 8.4 KB runs code
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 · 21 lines scan A 6326e2e29227
devsandbox is a plugin published in the GitHub repository zekker6/devsandbox (10 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
rove
Rove — terminal-native multiplexer for AI coding sessions. This marketplace ships the Claude Code integration plugin.
mavka
Skills from Mavka for writing and maintaining high-quality tests with AI coding agents.
ai-maestro-plugins
Plugin marketplace listing 1 plugin: ai-maestro.
rvdbreemen-adr-kit
Marketplace hosting the adr-kit plugin: a drop-in Architecture Decision Record toolkit for AI coding agents.
ensemble-ai
AI SDK skills for OpenAI, and other AI providers for Claude Code.
clipboard-mcp-server
Read, write, and inspect the system clipboard across macOS, Linux (X11/Wayland), and Windows via MCP. STDIO or Streamable HTTP.