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 delegated-file-edit-verificationgit 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/delegated-file-edit-verification)<a href="https://agentmods.dev/skills/hkuds/openspace/delegated-file-edit-verification"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/delegated-file-edit-verification.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, 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 250 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.
- medium Excessive Agency · line 252 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.
- medium Excessive Agency · line 264 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 | $0.00036 | $0.01878 |
| Opus 5 | $0.00018 | $0.00939 |
| Sonnet 5 | $0.00007 | $0.00376 |
| Haiku 4.5 | $0.00004 | $0.00188 |
Grade A, and why
delegated-file-edit-verification 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 8d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegated File Edit Verification
Use this workflow whenever another agent, subprocess, or delegated tool claims it successfully created or modified a file. The goal is to prevent false acceptance of incomplete, misplaced, or incorrect edits.
This skill is especially useful for structured files such as spreadsheets, CSVs, databases, and generated artifacts, but the same pattern applies to any delegated file-edit task.
Core principle
Never accept a delegated "done" message on summary alone.
Immediately verify the result yourself in the target workspace using direct commands that inspect:
- file existence
- exact path
- expected structure
- expected size or counts
- key headers, fields, or identifiers
If the delegate's summary and your verification disagree, treat the task as incomplete. Re-run the task using absolute paths and explicit acceptance checks.
When to use this
Use this workflow when:
- a sub-agent says it wrote or updated a file
- the task depends on a specific workspace or output location
- the output is structured and can be checked mechanically
- prior executions showed path confusion, stale files, or inconsistent summaries
- correctness matters more than trusting the delegate's narrative
Procedure
1. Record the intended output contract before delegating
Before handing off the task, write down the minimum facts that must be true if the task succeeds.
Include:
- absolute target path
- required file name
- required file type
- expected sheets, tabs, tables, or sections
- expected row counts or approximate size
- required headers or columns
- any sentinel values that should appear
Example contract:
- file exists at
/workspace/results/report.xlsx - workbook contains sheets
summaryanddata datasheet has more than 1,000 rows- headers include
id,created_at,status
Do not rely on vague goals like "updated spreadsheet correctly."
2. Delegate with explicit acceptance criteria
When delegating, include:
- the absolute input path
- the absolute output path
- the exact required structure
- a request to report what was changed
- a request to include paths actually used
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.
- 8d ago First seen · 275 lines · 36 tokens per session scan A f638ef8befdd
delegated-file-edit-verification is a skill published in the GitHub repository HKUDS/OpenSpace (7,544 stars, last pushed 26d ago), licensed MIT. It adds 36 tokens to every session and 1,878 once invoked, about $0.0002 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.