spreadsheet-proof-gate

spreadsheet-proof-gate is a skill for Claude Code, Codex from HKUDS/OpenSpace. It costs 41 tokens per session (3,851 once invoked), scanned A, original, MIT.

A verification-first workflow for Excel workbooks that audits the input, applies changes, and proves the saved file meets the requested criteria.

In plain words
What is it for?
Use it when editing or creating workbooks with exact requirements for files, sheets, columns, counts, or other workbook details.
Why use it?
It prevents completion claims based only on description by checking the actual workbook on disk. Any unmet requirement must be reported or resolved before finalization.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when editing or creating workbooks with exact requirements for files, sheets, columns, counts, or other workbook details.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hkuds/openspace/spreadsheet-audit-edit-validate-merged
About the project

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.

HKUDS/OpenSpace · 7,544 stars · on GitHub

Install

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.

Any agent
npx skills add HKUDS/OpenSpace --skill spreadsheet-audit-edit-validate-merged
Clone the repo
git clone --depth 1 https://github.com/HKUDS/OpenSpace

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for spreadsheet-proof-gate

README.md
[![agentmods](https://agentmods.dev/badge/skills/hkuds/openspace/spreadsheet-audit-edit-validate-merged.svg)](https://agentmods.dev/skills/hkuds/openspace/spreadsheet-audit-edit-validate-merged)
Your own site
<a href="https://agentmods.dev/skills/hkuds/openspace/spreadsheet-audit-edit-validate-merged"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/spreadsheet-audit-edit-validate-merged.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,851 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 574
    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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.03851
Opus 5 $0.00020 $0.01925
Sonnet 5 $0.00008 $0.00770
Haiku 4.5 $0.00004 $0.00385

Measured 5d ago against content hash f474e5c99b7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

spreadsheet-proof-gate 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.

benchmarks/gdpval/skills/spreadsheet-audit-edit-validate-merged/SKILL.md · 593 lines

How it starts

The opening of the file, as written. The whole thing — 593 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spreadsheet Proof Gate

Use this skill when you must modify, create, or validate an Excel workbook and the result must be proven against a user specification rather than merely described.

This skill combines:

  • workbook discovery and identity confirmation
  • pre-edit structure auditing
  • safe workbook editing
  • deterministic post-write verification from disk
  • a machine-checkable pass/fail checklist for every requested criterion
  • a hard finalization gate that rejects completion when any required criterion is unmet or unreconciled

This is a workflow skill. It does not require a specific editor, but it does require a direct Python verification pass with openpyxl before you report success.

When to use

Use this skill when any of the following are true:

  • the workbook path must be discovered
  • multiple similar Excel files may exist
  • the user requires exact sheet names, columns, counts, or samples
  • the task edits an existing workbook
  • a delegated agent may perform spreadsheet work
  • prior summaries are inconsistent or not trustworthy
  • exact post-edit workbook state matters
  • you must prove that mandatory criteria were satisfied

Core rule

Never finalize from narrative summary alone.

A workbook task is only complete when:

  1. the target workbook was identified from the anchored workspace path
  2. pre-edit structure matched the intended operation
  3. the edit was performed on the correct file
  4. the saved workbook was directly re-read from disk
  5. every requested criterion was checked in a deterministic verification report
  6. each criterion is marked as one of:
    • PASS
    • FAIL
    • UNAVAILABLE-IN-SOURCE
  7. any non-pass result is explicitly reconciled before finalizing

If any mandatory criterion is still FAIL, do not declare success.

If a criterion is UNAVAILABLE-IN-SOURCE, only finalize if:

  • the source workbook truly lacks the needed input,
  • you state that clearly,
  • and the user request did not require inventing unsupported data.

Workspace anchoring rule

Read the full file on GitHub · 593 lines

Files

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.

Changes

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.

  1. 5d ago First seen · 593 lines · 41 tokens per session scan A f474e5c99b7a

Subscribe to this mod's changes

spreadsheet-proof-gate is a skill published in the GitHub repository HKUDS/OpenSpace (7,544 stars, last pushed 27d ago), licensed MIT. It adds 41 tokens to every session and 3,851 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 2026-09-03.