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 agentmods add instructions/surajpanwar/advanced-calc-engine/agents-mdgit clone --depth 1 https://github.com/surajpanwar/advanced-calc-engineWrote 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/instructions/surajpanwar/advanced-calc-engine/agents-md)<a href="https://agentmods.dev/instructions/surajpanwar/advanced-calc-engine/agents-md"><img src="https://agentmods.dev/badge/instructions/surajpanwar/advanced-calc-engine/agents-md.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 | $0.00410 | $0.00410 |
| Opus 5 | $0.00205 | $0.00205 |
| Sonnet 5 | $0.00082 | $0.00082 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
advanced-calc-engine AGENTS.md 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 3d 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.
What it actually says
AdvancedCalc Engine
Project Purpose
AdvancedCalc Engine is an agentic Excel analysis and calculation platform.
The system uses OpenCode agents, MCP tools and Python to:
- Understand Excel workbook structure.
- Analyze user requests.
- Create an execution plan.
- Execute calculations.
- Modify Excel workbooks safely.
- Validate results.
- Run automated tests.
- Maintain an audit trail.
Architecture
The system contains:
- Architect Agent
- Engineer Agent
- Validation Agent
- Security Auditor Agent
- Excel Metadata Tool
- Calculation Engine
- Formula Writer
- Workbook Validator
- MCP Server
- Pytest validation
- Audit logging
Core Rules
- Analyze before modifying.
- Never blindly modify a workbook.
- Never overwrite source data unless explicitly requested.
- Create backups before destructive operations.
- Validate workbook structure before calculations.
- Validate results after modification.
- Never silently ignore errors.
- Log important operations.
- Never expose secrets.
- Never execute unrestricted arbitrary Python code.
Agent Responsibilities
Architect:
- Analyze
- Plan
- Do not modify
Engineer:
- Execute
- Calculate
- Modify approved workbook areas
Validator:
- Independently verify results
- Do not modify the workbook
Security Auditor:
- Identify security risks
- Do not modify application code
Python Standards
Use:
- Type hints
- Pydantic models
- Clear function boundaries
- Exception handling
- Logging
- Pytest
- Small testable functions
Excel Safety
Before modifying Excel:
- Verify file exists.
- Verify worksheet exists.
- Verify expected columns exist.
- Verify target range.
- Create backup.
- Apply changes.
- Reopen workbook.
- Validate changes.
Security
Never:
- Execute arbitrary user Python.
- Read
.envsecrets through tools. - Expose API keys.
- Delete files without approval.
- Modify unrelated workbooks.
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.
- 3d ago First seen · 100 lines · 410 tokens per session scan A 8676422db1f7
advanced-calc-engine AGENTS.md is an instructions file published in the GitHub repository surajpanwar/advanced-calc-engine (0 stars, last pushed 20d ago), licensed MIT. It adds 410 tokens to every session, about $0.0020 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 2026-08-31.
Other instructions, from other repositories
open-sheet AGENTS.md
Instructions for lianghsun/open-sheet, covering open-sheet — repository guide, repo layout, commands, the one invariant and core pipeline.
excel-mcp-server AGENTS.md
Instructions for TangentDomain/excel-mcp-server, covering excelmcp, turn 起始流程, 项目事实(l0), 技术栈 and 目录结构.
excel-mcp-server CLAUDE.md
Instructions for TangentDomain/excel-mcp-server, covering excel mcp server, 技术栈, 目录结构, mcp 工具 → python api 映射 and sql 核心原则.
tablepack AGENTS.md
Instructions for kujiangmudao/tablepack, covering two user paths, multimodal requirement, environment, hard requirements (never skip) and qc checklist (every pdf).
open-sheet CLAUDE.md
Instructions for lianghsun/open-sheet, a project described as: The spreadsheet framework built for agents — write the model as React, export a live .xlsx. The third medium, after open-slide and open-doc.
exstruct CLAUDE.md
Instructions for harumiWeb/exstruct, a project described as: Conversion from Excel to structured JSON (tables, shapes, charts) for LLM/RAG pipelines, and autonomous Excel reading/writing by AI agents via CLI and MCP integration.