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 skills/disler/agent-sandbox-skill/agent-sandboxesnpx skills add disler/agent-sandbox-skill --skill agent-sandboxesgit clone --depth 1 https://github.com/disler/agent-sandbox-skillWrote 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/skills/disler/agent-sandbox-skill/agent-sandboxes)<a href="https://agentmods.dev/skills/disler/agent-sandbox-skill/agent-sandboxes"><img src="https://agentmods.dev/badge/skills/disler/agent-sandbox-skill/agent-sandboxes.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.04849 |
| Opus 5 | $0.00000 | $0.02424 |
| Sonnet 5 | $0.00000 | $0.00970 |
| Haiku 4.5 | $0.00000 | $0.00485 |
Grade D, and why
Agent Sandboxes scanned grade D with 3 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 6d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
--root Run as root user Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
uv run sbx exec <sandbox_id> "curl -LsSf https://astral.sh/uv/install.sh | sh" --shell --timeout 120 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
uv run sbx exec <sandbox_id> "curl -LsSf https://astral.sh/uv/install.sh | sh" --shell --timeout 120 The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files beside SKILL.md 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.
- build_template.py 6.7 KB runs code
- cookbook/browser.md 5.6 KB
- examples/01_run_python_code.md 1.3 KB
- examples/02_test_package.md 1.5 KB
- examples/03_clone_and_test_repo.md 1.6 KB
- examples/04_process_binary_files.md 2.2 KB
- examples/05_host_frontend.md 7.3 KB
- prompts/browse.md 3.8 KB
- prompts/browser-testing.md 7.0 KB
- prompts/build.md 1.1 KB
- prompts/download.md 364 B
- prompts/host.md 2.2 KB
- prompts/plan-build-host-test.md 8.3 KB
- prompts/plan-full-stack.md 12 KB
- prompts/reboot.md 1.6 KB
- prompts/sandbox.md 772 B
- prompts/test.md 8.4 KB
- sandbox_cli/.gitignore 12 B
- sandbox_cli/.python-version 5 B
- sandbox_cli/pyproject.toml 527 B
- sandbox_cli/README.md 17 KB
- sandbox_cli/src/__init__.py 56 B runs code
- sandbox_cli/src/commands/__init__.py 146 B runs code
- sandbox_cli/src/commands/browser.py 20 KB runs code
- sandbox_cli/src/commands/exec.py 4.3 KB runs code
- sandbox_cli/src/commands/files.py 12 KB runs code
- sandbox_cli/src/commands/sandbox.py 13 KB runs code
- sandbox_cli/src/main.py 3.5 KB runs code
- sandbox_cli/src/modules/__init__.py 159 B runs code
- sandbox_cli/src/modules/browser.py 17 KB runs code
- sandbox_cli/src/modules/commands.py 2.5 KB runs code
- sandbox_cli/src/modules/files.py 11 KB runs code
- sandbox_cli/src/modules/sandbox.py 6.3 KB runs code
- sandbox_cli/temp/banana-pokemon-cards-iicr81igq2rw6a5qm2p65/index.html 14 KB
- sandbox_cli/temp/banana-pokemon-cards-iicr81igq2rw6a5qm2p65/README.md 1.7 KB
- sandbox_cli/temp/claude-code-sonnet-4-5--easy_notes_app/api.ts 918 B runs code
- sandbox_cli/temp/claude-code-sonnet-4-5--easy_notes_app/App.vue 3.3 KB
- sandbox_cli/temp/claude-code-sonnet-4-5--easy_notes_app/crud.py 1.2 KB runs code
- sandbox_cli/temp/claude-code-sonnet-4-5--easy_notes_app/database.py 918 B runs code
- sandbox_cli/temp/claude-code-sonnet-4-5--easy_notes_app/index.html 397 B
- sandbox_cli/temp/claude-code-sonnet-4-5--easy_notes_app/main.py 1.8 KB runs code
- sandbox_cli/temp/claude-code-sonnet-4-5--easy_notes_app/main.ts 186 B runs code
- sandbox_cli/temp/claude-code-sonnet-4-5--easy_notes_app/models.py 435 B runs code
- sandbox_cli/temp/claude-code-sonnet-4-5--easy_notes_app/NoteEditor.vue 2.7 KB
- sandbox_cli/temp/claude-code-sonnet-4-5--easy_notes_app/notes.ts 1.8 KB runs code
- sandbox_cli/temp/claude-code-sonnet-4-5--easy_notes_app/NotesList.vue 2.6 KB
- sandbox_cli/temp/claude-code-sonnet-4-5--easy_notes_app/specs/easy-notes-app.md 14 KB
- sandbox_cli/temp/claude-code-sonnet-4-5--easy_notes_app/validation-screenshot.png 97 KB
- sandbox_cli/temp/claude-code-sonnet-4-5--easy_notes_app/vite.config.ts 365 B runs code
- sandbox_cli/temp/codex-cli-codex-5-1--very_easy_url_shortener/specs/url-shortener-app.md 8.9 KB
- sandbox_cli/temp/codex-cli-codex-5-1-max-high--easy_notes_app/notes-ui.png 340 KB
- sandbox_cli/temp/codex-cli-codex-5-1-max-high--easy_notes_app/specs/easy-notes-app-plan.md 8.7 KB
- sandbox_cli/temp/gemini-cli-gemini-3--very_easy_todo_list/specs/todo-list-full-stack.md 15 KB
- sandbox_cli/temp/gemini-cli-gemini-3-pro--easy_notes_app/specs/easy-notes-app-plan.md 4.0 KB
- sandbox_cli/temp/multiport-test-1-counter/specs/simple-counter-full-stack.md 11 KB
- sandbox_cli/temp/multiport-test-2-calculator/specs/calculator-full-stack.md 11 KB
- sandbox_cli/temp/multiport-test-2-calculator/validation-screenshot.png 81 KB
- sandbox_cli/temp/multiport-test-3-timer/api.ts 1.3 KB runs code
- sandbox_cli/temp/multiport-test-3-timer/specs/simple-timer-app.md 10 KB
- sandbox_cli/temp/test-workflow-browser-validation/specs/easy-notes-app.md 14 KB
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.
- 6d ago First seen · 505 lines · 0 tokens per session scan D ddb2fed12b7f
Agent Sandboxes is a skill published in the GitHub repository disler/agent-sandbox-skill (382 stars, last pushed 9mo ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 4,849 tokens. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…