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/coverage-prevention-strategygit 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/coverage-prevention-strategy)<a href="https://agentmods.dev/instructions/sbroenne/mcp-server-excel/coverage-prevention-strategy"><img src="https://agentmods.dev/badge/instructions/sbroenne/mcp-server-excel/coverage-prevention-strategy.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 5.1 | $0.00396 | $0.00396 |
| Opus 5 | $0.00198 | $0.00198 |
| Sonnet 5 | $0.00079 | $0.00079 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
mcp-server-excel coverage-prevention-strategy.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 6d 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
Generated surface coverage
Core command interfaces annotated with [ServiceCategory] are the source
contracts for generated Service, CLI, and MCP routing. Do not follow old
hand-written "add a switch in every layer" patterns without first checking the
generator output.
Contract change workflow
- Add or change the method on the correct Core interface.
- Implement the method in the matching Core command class.
- Build Release so source generators refresh all generated surfaces.
- Inspect generated diagnostics and the hand-written MCP tool only where that tool owns special routing, metadata, cancellation, or atomic behavior.
- Verify CLI and MCP names, parameter defaults, validation, result shape, and timeout behavior remain identical.
- Update focused tests and shared guidance.
Required checks
dotnet build Sbroenne.ExcelMcp.sln -c Release
& .\scripts\audit-core-coverage.ps1 -CheckNaming -FailOnGaps
& .\scripts\check-mcp-core-implementations.ps1
& .\scripts\check-doc-counts.ps1
The audits are authoritative. Do not compare hand-maintained method or action counts in prose.
Common incomplete changes
- Core method added without a generated service route
- MCP action added without the matching Core implementation
- Parameter renamed on one entry point only
- Default or validation changed without regenerating CLI/MCP schemas
- Hand-written tool exception not updated after a generated contract change
- Generated file edited instead of its interface, generator, or template
- Docs or skills updated with literal counts that disagree with the audits
Treat a build success as necessary but not sufficient; the coverage and naming scripts catch contract gaps that compilation alone cannot.
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.
- 6d ago First seen · 48 lines · 396 tokens per session scan A e73cc336aaf2
mcp-server-excel coverage-prevention-strategy.instructions.md is an instructions file published in the GitHub repository sbroenne/mcp-server-excel (656 stars, last pushed yesterday), licensed MIT. It adds 396 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 2026-08-30.
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 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 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 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-amazon CLAUDE.md
Instructions for rigwild/mcp-server-amazon, covering claude.md, development commands, install dependencies (use -d flag for puppeteer), build typescript to javascript and clean mock html files.