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 task-verification-checkpointsgit 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/task-verification-checkpoints)<a href="https://agentmods.dev/skills/hkuds/openspace/task-verification-checkpoints"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/task-verification-checkpoints/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/task-verification-checkpoints"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/task-verification-checkpoints.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 140 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.01084 |
| Opus 5 | $0.00009 | $0.00542 |
| Sonnet 5 | $0.00004 | $0.00217 |
| Haiku 4.5 | $0.00002 | $0.00108 |
Grade A, and why
task-verification-checkpoints 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 6d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Verification Checkpoints
Before declaring a task as <COMPLETE>, perform these verification checks to ensure the deliverable matches requirements and prevents wrong-task completion.
Overview
This skill prevents common failures where agents:
- Create outputs in wrong formats (PDF vs PPTX vs DOCX)
- Skip processing some reference files
- Drift from the actual task requirements
Three Critical Checkpoints
Checkpoint 1: Output Format Verification
Question: Does the output file format match task requirements?
Actions:
- Re-read the task prompt for explicit format requirements
- Check file extensions of all output files
- Verify the actual file type matches the extension
- Confirm against any format specifications (e.g., "revised PDF report")
Example validation:
def verify_output_format(task_prompt, output_files):
"""Check if output format matches task requirements."""
required_format = extract_format_requirement(task_prompt) # e.g., 'pdf', 'pptx'
for f in output_files:
actual_ext = f.split('.')[-1].lower()
if actual_ext != required_format:
return False, f"Expected .{required_format}, got .{actual_ext}"
return True, "Format verified"
Checkpoint 2: Reference File Coverage
Question: Were ALL reference/input files processed?
Actions:
- List all files mentioned in the task as inputs
- Confirm each was read/analyzed/used (check file access logs)
- Document which content from each file contributed to output
- Flag any unprocessed reference files
Example validation:
def verify_reference_coverage(task_files, accessed_files):
"""Ensure all reference files were actually processed."""
missing = set(task_files) - set(accessed_files)
if missing:
return False, f"Unprocessed files: {missing}"
return True, "All references processed"
Checkpoint 3: Task Alignment Verification
Question: Does the deliverable address the ACTUAL task prompt?
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.
- 6d ago First seen · 151 lines · 18 tokens per session scan A e860c84cb6d1
task-verification-checkpoints is a skill published in the GitHub repository HKUDS/OpenSpace (7,552 stars, last pushed 27d ago), licensed MIT. It adds 18 tokens to every session and 1,084 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
box
Box manages cloud files, sharing, search, and metadata.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.
recipe-bulk-download-folder
List and download all files from a Google Drive folder.
apple-notes
Manage Apple Notes via the memo CLI on macOS (create, view, search, edit).