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 file-locate-verifygit 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/file-locate-verify)<a href="https://agentmods.dev/skills/hkuds/openspace/file-locate-verify"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/file-locate-verify.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00021 | $0.00757 |
| Opus 5 | $0.00010 | $0.00378 |
| Sonnet 5 | $0.00004 | $0.00151 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
file-locate-verify 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 7d 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.
File Locate and Verify Workflow
When encountering FileNotFoundError or uncertain file paths, follow this systematic pattern to safely locate and verify files before executing operations.
When to Use
- You receive a FileNotFoundError or similar path-related error
- You need to work with files whose exact location is unknown
- You want to verify file existence before executing operations that depend on those files
Step-by-Step Procedure
Step 1: Check Current Directory Contents
First, use list_dir to inspect what files exist in your current working directory:
# Use the list_dir tool to see current directory contents
list_dir(path=".")
This reveals files in the immediate context and helps determine if you need to search elsewhere.
Step 2: Search for the File Using Find
If the file is not in the current directory, use the find command to locate it by name:
# Search for a specific file by name (case-insensitive)
find . -iname "filename.pdf" 2>/dev/null
# Or search from root for system-wide files
find / -name "filename.pdf" 2>/dev/null
Tips:
- Use
-inamefor case-insensitive matching - Redirect stderr with
2>/dev/nullto suppress permission errors - Narrow the search scope when possible for better performance
Step 3: Verify the Discovered Path
Before executing any operations on the discovered file, verify it exists and check its properties:
# Verify file existence and permissions at the full path
ls -la /full/path/to/discovered/file.pdf
This confirms:
- The file actually exists at the located path
- File permissions (can you read/write it?)
- File size and modification time
Step 4: Execute Your Operation Safely
Only after verification, proceed with your intended operation:
# Now safe to work with the verified path
file_path = "/full/path/to/discovered/file.pdf"
# ... your extraction or processing code here
Complete Example
# Task: Process a file that may be in an unknown location
# Step 1: Check current directory
dir_contents = list_dir(path=".")
print(f"Current directory contains: {dir_contents}")
# Step 2: Find the file if not present
if "target_file.xlsx" not in dir_contents:
result = run_shell(command='find . -iname "target_file.xlsx" 2>/dev/null')
file_path = result.stdout.strip().split('\n')[0]
print(f"Found file at: {file_path}")
# Step 3: Verify before proceeding
verification = run_shell(command=f'ls -la {file_path}')
print(f"Verification: {verification.stdout}")
# Step 4: Proceed with operation
# ... your code to process the file
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.
- 7d ago First seen · 105 lines · 21 tokens per session scan A 9199ffb6805e
file-locate-verify is a skill published in the GitHub repository HKUDS/OpenSpace (7,510 stars, last pushed 25d ago), licensed MIT. It adds 21 tokens to every session and 757 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.