OpenSpace is a skill-management layer for AI agents that stores, retrieves, evaluates, shares, and improves reusable workflows. It is intended for people using multiple coding agents who want skills to be reused and refined based on task outcomes. The catalogue provides 200 skills for use with OpenSpace and the agents it supports.
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 HKUDS/OpenSpace --skill sandbox-fallback-executiongit clone --depth 1 https://github.com/HKUDS/OpenSpaceWrote 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/hkuds/openspace/sandbox-fallback-execution)<a href="https://agentmods.dev/skills/hkuds/openspace/sandbox-fallback-execution"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/sandbox-fallback-execution.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00018 | $0.00669 |
| Opus 5 | $0.00009 | $0.00334 |
| Sonnet 5 | $0.00004 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
sandbox-fallback-execution 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sandbox Fallback Execution
When to Use This Skill
Use this pattern when execute_code_sandbox fails with unknown errors, timeouts, or persistent execution failures. This fallback bypasses sandbox restrictions by using run_shell with a Python heredoc script.
Pattern Overview
execute_code_sandbox fails → run_shell with pip install → Python heredoc execution
Step-by-Step Instructions
Step 1: Detect Sandbox Failure
Monitor for these failure indicators from execute_code_sandbox:
- Unknown or unexplained errors
- Repeated execution failures (>2 attempts)
- Timeout errors
- Environment/package availability issues
Step 2: Install Required Dependencies (If Needed)
Use run_shell to install any required Python packages:
pip install <package_name>
For multiple packages:
pip install package1 package2 package3
Step 3: Execute Python via Heredoc
Run Python code using a heredoc script with run_shell:
python3 << 'EOF'
# Your Python code here
import sys
print("Hello from fallback execution")
EOF
Key heredoc syntax notes:
- Use
<< 'EOF'(quoted) to prevent shell variable expansion - Use
<< EOF(unquoted) if you need shell variable interpolation - Close with
EOFon its own line
Step 4: Verify and Iterate
- Check stdout/stderr for success indicators
- If errors persist, inspect output and adjust the script
- Capture any generated artifacts (files, outputs) for verification
Complete Example
Scenario: Need to create a Word document but execute_code_sandbox keeps failing.
# Step 1: Install required package
pip install python-docx
# Step 2: Execute Python script via heredoc
python3 << 'EOF'
from docx import Document
doc = Document()
doc.add_heading('Proposal Document', 0)
doc.add_paragraph('This is the proposal content.')
doc.save('proposal.docx')
print("Document created successfully")
EOF
Best Practices
- Quote the heredoc delimiter (
'EOF') to avoid unintended shell expansion of Python code - Install packages first before running the script to ensure availability
- Print status messages in your script for easier debugging
- Save outputs to files when possible for verification
- Keep scripts focused - break complex tasks into multiple heredoc executions if needed
What ships with it
1 file 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.
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.
- 5d ago First seen · 105 lines · 18 tokens per session scan A bdd54b6b3d2d
sandbox-fallback-execution is a skill published in the GitHub repository HKUDS/OpenSpace (7,544 stars, last pushed 26d ago), licensed MIT. It adds 18 tokens to every session and 669 once invoked, about $0.0001 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 2026-09-03.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…