An independent checking role that verifies Excel workbook changes and calculations without modifying the workbook.

Use it after workbook processing to inspect sheets, formulas, calculations, and test results, then report either PASS or FAIL with the cause and suggested correction.

It provides a separate review that can detect incorrect formulas, unexpected edits, missing columns, or failed tests.

How surajpanwar/advanced-calc-engine configures Claude Code and OpenCo

Reuse

Borrowing it

Nothing to install: this file belongs to surajpanwar/advanced-calc-engine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/surajpanwar/advanced-calc-engine/main/.opencode/agents/validator.md

Clone the repo

git clone --depth 1 https://github.com/surajpanwar/advanced-calc-engine

Made for: Claude Code, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/surajpanwar/advanced-calc-engine/validator/github.svg)](https://agentmods.dev/agents/surajpanwar/advanced-calc-engine/validator)

Your own site

<a href="https://agentmods.dev/agents/surajpanwar/advanced-calc-engine/validator"><img src="https://agentmods.dev/badge/agents/surajpanwar/advanced-calc-engine/validator/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/surajpanwar/advanced-calc-engine/validator"><img src="https://agentmods.dev/badge/agents/surajpanwar/advanced-calc-engine/validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 132 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00008	$0.00132
Opus 5.5	$0.00003	$0.00053
Sonnet 5.5	$0.00002	$0.00026
Haiku 4.5	$0.00001	$0.00013

Measured 2mo ago against content hash bdc9214da291, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

validator 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 2mo 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.

.opencode/agents/validator.md · 41 lines

What it actually says

Validation Agent

You independently verify the Engineer's work.

Responsibilities

Verify the output workbook.
Verify worksheets.
Verify expected columns.
Verify calculations.
Verify formulas.
Detect unexpected modifications.
Run pytest.
Report PASS or FAIL.

Rules

You must not modify the workbook.

If validation fails, report:

What failed
Expected result
Actual result
Likely cause
Recommended correction

Final result must be:

PASS

FAIL

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.

2mo ago First seen · 41 lines · 8 tokens per session scan A bdc9214da291

Subscribe to this mod's changes

validator is an agent published in the GitHub repository surajpanwar/advanced-calc-engine (0 stars, last pushed 2mo ago), licensed MIT. It adds 8 tokens to every session and 132 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-31.

Documents LangChain Spreadsheets agentic-ai ai-engineering data-engineering excel langgraph

validator next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
validatorsurajpanwar/advanced-calc-engine	Agent	0	2mo ago	MIT	A	8	Claude Code, OpenCode
Tenable Report Workshoptenable/cyberagents-exchange	Agent	23	yesterday	none	A	27	Claude Code
sheet-report-agentSpillwaveSolutions/automating-mac-apps-plugin	Agent	49	2mo ago	MIT	A	14	Claude Code
sheet-convert-agentSpillwaveSolutions/automating-mac-apps-plugin	Agent	49	2mo ago	MIT	A	12	Claude Code
csv-to-excel-agentSpillwaveSolutions/automating-mac-apps-plugin	Agent	49	2mo ago	MIT	A	13	Claude Code
csv-to-numbers-agentSpillwaveSolutions/automating-mac-apps-plugin	Agent	49	2mo ago	MIT	A	13	Claude Code
Sales Data Extraction Agentandywxy1/ceo-plugin	Agent	6	7mo ago	GPL-3.0	A	31	Claude Code

advanced-calc-engine: Agent for Claude Code