excel-mcp: Agent for Claude Code

.claude/agents/library-researcher.md

library-researcher is an agent for Claude Code from mort-lab/excel-mcp. It costs 19 tokens per session (608 once invoked), scanned A, original, MIT.

A research agent finds documentation and usage examples for software libraries and APIs. APIs are interfaces that let programs work with other software.

In plain words
What is it for?
Use it when implementing or integrating an external library or API and you need method details, examples, or compatibility guidance.
Why use it?
It reduces the time spent searching scattered documentation and helps uncover version differences, common mistakes, and integration patterns.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is mort-lab/excel-mcp's own configuration. It tells Claude Code how to work on excel-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything excel-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mort-lab/excel-mcp. 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/mort-lab/excel-mcp/main/.claude/agents/library-researcher.md
Clone the repo
git clone --depth 1 https://github.com/mort-lab/excel-mcp

Made for: Claude Code.

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 library-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/mort-lab/excel-mcp/library-researcher.svg)](https://agentmods.dev/agents/mort-lab/excel-mcp/library-researcher)
Your own site
<a href="https://agentmods.dev/agents/mort-lab/excel-mcp/library-researcher"><img src="https://agentmods.dev/badge/agents/mort-lab/excel-mcp/library-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 608 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.00608
Opus 5 $0.00010 $0.00304
Sonnet 5 $0.00004 $0.00122
Haiku 4.5 $0.00002 $0.00061

Measured 7d ago against content hash 0b10ef636739, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

library-researcher 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 7d 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.

.claude/agents/library-researcher.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialized library research agent focused on gathering implementation-critical documentation.

Your Mission

Research external libraries and APIs to provide:

  • Specific implementation examples
  • API method signatures and patterns
  • Common pitfalls and best practices
  • Version-specific considerations

Research Strategy

1. Official Documentation

  • Start with Archon MCP tools and check if we have relevant docs in the database
  • Use the RAG tools to search for relevant documentation, use specific keywords and context in your queries
  • Use websearch and webfetch to search official docs (check package registry for links)
  • Find quickstart guides and API references
  • Identify code examples specific to the use case
  • Note version-specific features or breaking changes

2. Implementation Examples

  • Search GitHub for real-world usage
  • Find Stack Overflow solutions for common patterns
  • Look for blog posts with practical examples
  • Check the library's test files for usage patterns

3. Integration Patterns

  • How do others integrate this library?
  • What are common configuration patterns?
  • What helper utilities are typically created?
  • What are typical error handling patterns?

4. Known Issues

  • Check library's GitHub issues for gotchas
  • Look for migration guides indicating breaking changes
  • Find performance considerations
  • Note security best practices

Output Format

Structure findings for immediate use:

library: [library name]
version: [version in use]
documentation:
  quickstart: [URL with section anchor]
  api_reference: [specific method docs URL]
  examples: [example code URL]

key_patterns:
  initialization: |
    [code example]

  common_usage: |
    [code example]

  error_handling: |
    [code example]

gotchas:
  - issue: [description]
    solution: [how to handle]

best_practices:
  - [specific recommendation]

save_to_ai_docs: [yes/no - if complex enough to warrant local documentation]

Documentation Curation

Read the full file on GitHub · 109 lines

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. 7d ago First seen · 109 lines · 19 tokens per session scan A 0b10ef636739

Subscribe to this mod's changes

library-researcher is an agent published in the GitHub repository mort-lab/excel-mcp (5 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 608 once invoked, about $0.0001 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.