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 skills add s1366560/agi-demos --skill sandbox-mcp-servergit clone --depth 1 https://github.com/s1366560/agi-demosWrote 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/s1366560/agi-demos/sandbox-mcp-server)<a href="https://agentmods.dev/skills/s1366560/agi-demos/sandbox-mcp-server"><img src="https://agentmods.dev/badge/skills/s1366560/agi-demos/sandbox-mcp-server/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/skills/s1366560/agi-demos/sandbox-mcp-server"><img src="https://agentmods.dev/badge/skills/s1366560/agi-demos/sandbox-mcp-server.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 | $0.00076 | $0.04578 |
| Opus 5 | $0.00038 | $0.02289 |
| Sonnet 5 | $0.00015 | $0.00916 |
| Haiku 4.5 | $0.00008 | $0.00458 |
Grade C, and why
sandbox scanned grade C with 1 finding 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 9d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- 禁止危险命令 (`rm -rf /`, `mkfs`, fork bomb 等) 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.
- .dockerignore 174 B
- DEPLOYMENT.md 12 KB
- docker-compose.yml 1.2 KB
- docker/kasmvnc-configs/kasmvnc.yaml 1.3 KB
- docker/kasmvnc-configs/xstartup 1.3 KB
- docker/kde-configs/dolphinrc 733 B
- docker/kde-configs/katerc 784 B
- docker/kde-configs/kdeglobals 514 B
- docker/kde-configs/konsolerc 113 B
- docker/kde-configs/kwinrc 113 B
- docker/openbox-configs/menu.xml 706 B
- docker/openbox-configs/rc.xml 9.8 KB
- docker/seccomp-profile.json 7.3 KB
- docker/sudoers 1.4 KB
- docker/xfce-configs/autostart/xfce4-terminal.desktop 315 B
- docker/xfce-configs/whiskermenu-1.rc 550 B
- docker/xfce-configs/xfce4-desktop.xml 1.0 KB
- docker/xfce-configs/xfce4-panel.xml 2.1 KB
- docker/xfce-configs/xfce4-session.xml 1.8 KB
- docker/xfce-configs/xfwm4.xml 794 B
- docker/xfce-configs/xsettings.xml 1.4 KB
- Dockerfile 12 KB
- Dockerfile.e2e 950 B
- docs/phase1-completion.md 1.9 KB
- docs/phase2-completion.md 3.9 KB
- docs/phase3-changes.md 9.8 KB
- docs/phase3-completion.md 4.9 KB
- docs/phase3-tigervnc-report.md 18 KB
- docs/phase3-tigervnc-summary.md 7.2 KB
- docs/phase4-completion.md 4.4 KB
- docs/phase4-xfce-testing.md 16 KB
- docs/README.md 1.8 KB
- docs/remote-desktop-plan.md 8.9 KB
- docs/TIGERVNC_DOCKER_TEST_REPORT.md 9.2 KB
- docs/TIGERVNC_FINAL_SUMMARY.md 14 KB
- docs/TIGERVNC_IMPLEMENTATION_SUMMARY.md 8.8 KB
- docs/TIGERVNC_PHASE1_COMPLETE.md 10.0 KB
- docs/TIGERVNC_PHASES_3-5_COMPLETE.md 11 KB
- docs/TIGERVNC_TDD_PLAN.md 6.6 KB
- docs/xfce-docker-test-summary.md 5.7 KB
- docs/xfce-migration-final.md 13 KB
- docs/xfce-migration-phase1-progress.md 7.5 KB
- docs/xfce-migration-plan.md 12 KB
- docs/xfce-phase1-summary.md 7.4 KB
- docs/xfce-phase2-progress.md 5.4 KB
- docs/xfce-phase2-summary.md 12 KB
- docs/xfce-tdd-workflow.md 10 KB
- MIGRATION.md 8.0 KB
- PERFORMANCE.md 14 KB
- pyproject.toml 931 B
- README.md 16 KB
- scripts/build-xfce-4.20.sh 5.0 KB runs code
- scripts/entrypoint.sh 14 KB runs code
- src/__init__.py 101 B runs code
- src/mcp_manager/__init__.py 62 B runs code
- src/mcp_manager/installer.py 8.1 KB runs code
- src/mcp_manager/manager.py 72 KB runs code
- src/mcp_manager/process_tracker.py 8.9 KB runs code
- src/server/__init__.py 127 B runs code
- src/server/desktop_manager.py 11 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.
- 9d ago First seen · 736 lines · 76 tokens per session scan C 5525766effaf
sandbox is a skill published in the GitHub repository s1366560/agi-demos (5 stars, last pushed 4d ago), with no licence file. It adds 76 tokens to every session and 4,578 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
work
Deliver one maintainer-approved EmDash issue, choosing the bug-fix path for a defect and the direct implementation path for an enhancement or task.