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 working-directory-resolutiongit 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/working-directory-resolution)<a href="https://agentmods.dev/skills/hkuds/openspace/working-directory-resolution"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/working-directory-resolution.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 | $0.00681 |
| Opus 5 | $0.00009 | $0.00341 |
| Sonnet 5 | $0.00004 | $0.00136 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
working-directory-resolution 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working Directory Resolution Pattern
Many file operation failures occur because the tool's current working directory doesn't match where the target files are located. This skill provides a reliable pattern for resolving such issues.
Problem Symptoms
File operations fail with errors like:
- "File not found" or "No such file or directory"
- "Permission denied" (when path is actually relative)
- Tools returning empty results for files that should exist
These failures often occur even when files are present in the workspace—the working directory context is simply wrong.
Solution
Always explicitly set the working directory before file operations by prepending cd to your shell commands.
Implementation Pattern
Basic Syntax
cd /path/to/target/directory && your-command-here
With run_shell
run_shell(command="cd /workspace/project && cat config.json")
Multiple Operations in Same Directory
cd /workspace/project && ls -la && cat README.md && python script.py
Conditional Directory Change
cd /workspace/project 2>/dev/null && cat file.txt || echo "Directory not found"
When to Apply
Use this pattern when:
read_filefails to locate an existing fileexecute_code_sandboxcan't find referenced files- Shell commands report missing files that should exist
- File paths work in some contexts but not others
- You're unsure of the tool's current working directory
Best Practices
-
Use absolute paths when possible
cd /workspace/project/src && python main.py -
Combine related operations to avoid repeated
cdcallscd /workspace/project && ./build.sh && ./test.sh -
Verify directory exists before operations
[ -d /workspace/project ] && cd /workspace/project && ls -
For scripts, set working directory at the start
#!/bin/bash cd "$(dirname "$0")" || exit 1 # Rest of script runs from script's directory
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 · 99 lines · 18 tokens per session scan A 0900c301bd80
working-directory-resolution 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 681 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
material-ui-nextjs
Integrates Material UI with Next.js App and Pages routers using @mui/material-nextjs, Emotion cache providers, next/font, CSS layers with Tailwind/CSS Modules, Link component prop patterns, CSS theme variables SSR notes, and App Router useSearchParams + Suspense. Use when setting up or debugging MUI in a Next.js app.
RootCauseAnalysis
Structured incident investigation using Five Whys, Fishbone, blameless Postmortem, Fault Tree, Kepner-Tregoe, and FMEA — traces failures to systemic root causes rather than blaming humans. USE WHEN root cause, RCA, 5 whys, fishbone, postmortem, incident analysis, fault tree, why does this keep failing, blameless…
Vitals
Read-only macOS performance inspection: a deterministic CLI gathers the numbers, Interpretation.md turns them into a diagnosis instead of a data dump.
benchmark-workflow
Run, diagnose, or change Xberg extraction benchmarks, quality scoring, benchmark fixtures, artifact contracts, and independently sourced ground truth. Load for the Benchmarks workflow or benchmark-harness work, not ordinary unit tests.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error.
ai-development-guide
Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.