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/sbroenne/mcp-server-excel/critical-rulesgit clone --depth 1 https://github.com/sbroenne/mcp-server-excelWrote 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/sbroenne/mcp-server-excel/critical-rules)<a href="https://agentmods.dev/instructions/sbroenne/mcp-server-excel/critical-rules"><img src="https://agentmods.dev/badge/instructions/sbroenne/mcp-server-excel/critical-rules.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 | $0.00973 | $0.00973 |
| Opus 5 | $0.00487 | $0.00487 |
| Sonnet 5 | $0.00195 | $0.00195 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
mcp-server-excel critical-rules.instructions.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 4d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Non-negotiable repository rules
Change discipline
- Make the smallest complete change that fixes the root cause. Do not modify unrelated code or discard changes already present in the worktree.
- For behavioral changes, use a focused red-green cycle: reproduce the missing behavior in a test, observe the failure, implement, and rerun the same test. Do not manufacture tests for documentation-only or configuration-only edits.
- Search sibling commands and all generated/parallel surfaces for the same pattern before concluding a fix is complete.
- Do not leave placeholders, broad silent fallbacks, commented-out code, or unresolved TODO/FIXME/HACK markers in production code.
Validation
- Build with zero warnings and run the smallest existing tests that exercise the changed behavior. Use an explicit timeout for every Excel-dependent test run.
- Core integration tests require real Excel. Never replace COM-dependent coverage with mocks. Pure parsing, mapping, and generator logic may use fast non-COM tests when that is the behavior under test.
- Verify resulting workbook state, returned fields, and persistence where
applicable;
Success == truealone is not sufficient. - Do not call
batch.Save()unless the test specifically verifies persistence across close/reopen. - Session and batch infrastructure changes require targeted OnDemand tests.
Results and exceptions
Success == truerequires an empty or nullErrorMessage.- Core command operations run through
IExcelBatch.Execute. Do not add a broad catch that converts exceptions into a second result object. Let the batch and service layers preserve the failure context. - Catch only when handling a specific recoverable condition or adding required context at the owning boundary. Never swallow exceptions or return a success-shaped fallback.
- MCP tools return structured JSON for tool execution failures. Reserve thrown argument/protocol exceptions for invalid tool input or an unknown action.
- MCP stdio stdout is JSON-RPC only. Send diagnostics and logs to stderr.
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.
- 4d ago First seen · 95 lines · 973 tokens per session scan A ba44a6d39f26
mcp-server-excel critical-rules.instructions.md is an instructions file published in the GitHub repository sbroenne/mcp-server-excel (653 stars, last pushed yesterday), licensed MIT. It adds 973 tokens to every session, about $0.0049 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 instructions, from other repositories
mcp-server-powerpoint copilot-instructions.md
Copilot instructions for sbroenne/mcp-server-powerpoint, covering project instructions — powerpointmcp, critical files (read these first), sister projects, what is powerpointmcp? and session model (mcp server).
mcp-server-powerpoint architecture-patterns.instructions.md
Instructions for sbroenne/mcp-server-powerpoint, covering architecture patterns, .net class design (mandatory), layered architecture (critical), command pattern and structure (per domain).
mcp-server-powerpoint critical-rules.instructions.md
Instructions for sbroenne/mcp-server-powerpoint, covering critical rules - must follow, rule 1: success/errormessage invariant, rule 1b: no exception suppression in core, rule 30: real-com integration tests only, strict tdd and rule: 1-based indexing everywhere.
mcp-server-powerpoint mcp-server-guide.instructions.md
Instructions for sbroenne/mcp-server-powerpoint, covering mcp server development guide, llm-facing content rules, two kinds of tools: hand-written vs. generated, implementation pattern: single hand-written dispatch tool and error handling (mandatory).
mcp-server-powerpoint testing-strategy.instructions.md
Instructions for sbroenne/mcp-server-powerpoint, covering testing strategy, strict tdd (red → green), test project layout, serialization is mandatory and trait tagging (required for surgical filtering).
mcp-server-powerpoint code-review.instructions.md
Instructions for sbroenne/mcp-server-powerpoint, covering copilot code review, interop and resource safety, contract and path completeness and protocol, tests, and user-facing surfaces.