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-execution-fallbackgit 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-execution-fallback)<a href="https://agentmods.dev/skills/hkuds/openspace/sandbox-execution-fallback"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/sandbox-execution-fallback.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 | $0.00024 | $0.00684 |
| Opus 5 | $0.00012 | $0.00342 |
| Sonnet 5 | $0.00005 | $0.00137 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
sandbox-execution-fallback 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sandbox Execution Fallback
When to Use
Apply this pattern when execute_code_sandbox fails or times out, particularly for:
- Spreadsheet generation (pandas, openpyxl, xlsxwriter)
- Complex data processing with file I/O
- Tasks requiring external library imports
- Long-running computations that hit timeout limits
Recovery Procedure
Step 1: Capture the Python Code
Extract or reconstruct the Python code that failed in execute_code_sandbox.
Step 2: Write Code to File
Use write_file to save the script with a .py extension:
write_file(
path="script_name.py",
content="""
import pandas as pd
# Your implementation here
"""
)
Step 3: Execute via run_shell
Run the script using the system Python interpreter:
run_shell(command="python3 script_name.py")
Step 4: Verify Output
Confirm the results match expected outputs (files created, data processed correctly, etc.).
Complete Example
# Failed: execute_code_sandbox with pandas Excel generation
# Recovery - Step 1 & 2: Write script to file
write_file(
path="generate_pnl_report.py",
content="""
import pandas as pd
from openpyxl import Workbook
# Create sample data
data = {
'Category': ['Revenue', 'Expenses', 'Tax'],
'Amount': [10000, 3000, 500]
}
df = pd.DataFrame(data)
# Write to Excel
df.to_excel('pnl_report.xlsx', index=False)
print('Report generated: pnl_report.xlsx')
"""
)
# Step 3: Execute via shell
run_shell(command="python3 generate_pnl_report.py")
# Step 4: Verify file was created
run_shell(command="ls -la pnl_report.xlsx")
Why This Works
| Aspect | execute_code_sandbox | run_shell + write_file |
|---|---|---|
| Environment | Sandboxed, limited | Full system Python |
| File I/O | Restricted | Full access |
| Timeout | Strict limits | More flexible |
| Library Support | May be limited | System-installed packages |
| Result | Identical output | Identical output |
Best Practices
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 · 110 lines · 24 tokens per session scan A 2d58596b32f6
sandbox-execution-fallback is a skill published in the GitHub repository HKUDS/OpenSpace (7,544 stars, last pushed 26d ago), licensed MIT. It adds 24 tokens to every session and 684 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…