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-fallback-717e65git 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-717e65)<a href="https://agentmods.dev/skills/hkuds/openspace/sandbox-execution-fallback-717e65"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/sandbox-execution-fallback-717e65/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/hkuds/openspace/sandbox-execution-fallback-717e65"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/sandbox-execution-fallback-717e65.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00025 | $0.00881 |
| Opus 5 | $0.00013 | $0.00441 |
| Sonnet 5 | $0.00005 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
sandbox-execution-fallback-717e65 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 — 139 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 repeatedly or exhibits instability. Common triggers include:
- Sandbox returns errors after 2-3 retry attempts
- Error messages indicate provider/system issues rather than code bugs
- Execution times out or hangs inconsistently
- Complex multi-step code with file I/O is needed
- Better error visibility and debugging is required
Procedure
Step 1: Detect When to Switch
Recognize the failure pattern:
execute_code_sandboxproduces repeated errors despite code corrections- Error output suggests infrastructure issues (not syntax/logic errors)
- The sandbox environment appears unstable or limited
Step 2: Write Python Script to File
Use write_file to save your script:
write_file(
path="script.py",
content="#!/usr/bin/env python3
# Your Python code here
import sys
print('Executing via file-based approach')
# ... rest of your code
"
)
For multi-file projects, write each file separately:
write_file(path="utils.py", content="# Utility functions\ndef helper(): ...")
write_file(path="main.py", content="from utils import helper\nhelper()")
Step 3: Execute via Shell
Run the script using run_shell:
run_shell(command="python3 script.py")
For scripts in subdirectories:
run_shell(command="cd mydir && python3 script.py")
Step 4: Handle Output and Clean Up
- Parse stdout/stderr from
run_shelloutput - Inspect created files directly using
read_fileif needed - Remove temporary scripts after successful execution:
run_shell(command="rm script.py")
Advantages Over Sandbox Execution
| Benefit | Explanation |
|---|---|
| Bypasses provider limitations | No sandbox resource constraints |
| Better error visibility | Full stack traces and system errors |
| Environment control | Direct access to system Python and packages |
| Multi-file support | Easy imports and module structure |
| Persistence | Files remain for inspection and debugging |
| Reliability | More consistent execution behavior |
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 · 139 lines · 25 tokens per session scan A aec4ef85bb37
sandbox-execution-fallback-717e65 is a skill published in the GitHub repository HKUDS/OpenSpace (7,544 stars, last pushed 27d ago), licensed MIT. It adds 25 tokens to every session and 881 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…