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 research-fallback-enhancedgit 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/research-fallback-enhanced)<a href="https://agentmods.dev/skills/hkuds/openspace/research-fallback-enhanced"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/research-fallback-enhanced.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 | $0.00020 | $0.01154 |
| Opus 5 | $0.00010 | $0.00577 |
| Sonnet 5 | $0.00004 | $0.00231 |
| Haiku 4.5 | $0.00002 | $0.00115 |
Grade A, and why
research-fallback-robust 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- research-fallback — 88% identical, 48 lines differ
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Fallback Workflow
This skill provides a workflow for handling tasks that require external research when web search or webpage reading tools fail due to network issues or tool unavailability.
When to Use
- Task requires external research (legal analysis, market research, technical documentation, anatomical/medical information, etc.)
- Web search or webpage reading tools are failing or unavailable
- You have sufficient internal knowledge to proceed with reasonable accuracy
- Task completion is prioritized over perfect external sourcing
Workflow Steps
Step 1: Attempt External Research First
Begin by attempting to use available web research tools:
1. Use search_web for current information, statistics, or recent developments
2. Use read_webpage for detailed source material when URLs are provided
3. Document what you attempted to find
Step 2: Detect Tool Failure
Recognize when to pivot — including explicit error patterns:
- Web search returns errors, timeouts, or empty results
unknown errorfrom search_web — immediately recognize this as a tool failure trigger (do not retry excessively)- Page extraction fails repeatedly
- Network errors persist after 1-2 retry attempts
- Tool explicitly reports unavailability
Do not spend excessive time retrying failed tools. After 1-2 attempts with unknown error or similar failures, proceed to Step 3.
Step 3: Pivot to Internal Knowledge
When external tools fail:
- Acknowledge the limitation: Note that external research was attempted but tools were unavailable
- Assess internal knowledge: Determine what you know from training that covers the topic
- Identify gaps: Be transparent about what information may be dated or unavailable
- Proceed with available knowledge: Generate content using internal understanding
Step 4: Generate Content with Appropriate Disclaimers
When producing deliverables:
- Include a note that external verification is recommended for time-sensitive information
- Flag any claims that would benefit from current source verification
- Focus on established principles, frameworks, and well-documented facts
- Avoid making specific claims about very recent events or statistics
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.
- 4d ago First seen · 143 lines · 20 tokens per session scan A 0634d3885fea
research-fallback-robust is a skill published in the GitHub repository HKUDS/OpenSpace (7,534 stars, last pushed 26d ago), licensed MIT. It adds 20 tokens to every session and 1,154 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-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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…