servalsheets: Agent for Claude Code

.claude/agents/servalsheets-research.md

servalsheets-research is an agent for Claude Code from khill1269/servalsheets. It costs 68 tokens per session (988 once invoked), scanned A, original, MIT.

A read-only codebase research assistant for ServalSheets, an MCP server with tools for working with spreadsheets. It finds patterns, examples, handlers, schemas, tests, and other parts of the code.

In plain words
What is it for?
Use it to find error-handling patterns, compare action names, inspect request and response rules, count occurrences, and extract design patterns from ServalSheets.
Why use it?
It removes the need to manually search many files when you need to understand how the project is structured or how similar code works. Because it only reads files, it does not change the codebase.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; positional $N argument.

This is khill1269/servalsheets's own configuration. It tells Claude Code how to work on servalsheets 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 servalsheets configures →

Reuse

Borrowing it

Nothing to install: this file belongs to khill1269/servalsheets. 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/khill1269/servalsheets/main/.claude/agents/servalsheets-research.md
Clone the repo
git clone --depth 1 https://github.com/khill1269/servalsheets

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 servalsheets-research

README.md
[![agentmods](https://agentmods.dev/badge/agents/khill1269/servalsheets/servalsheets-research.svg)](https://agentmods.dev/agents/khill1269/servalsheets/servalsheets-research)
Your own site
<a href="https://agentmods.dev/agents/khill1269/servalsheets/servalsheets-research"><img src="https://agentmods.dev/badge/agents/khill1269/servalsheets/servalsheets-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 988 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 $0.00068 $0.00988
Opus 5 $0.00034 $0.00494
Sonnet 5 $0.00014 $0.00198
Haiku 4.5 $0.00007 $0.00099

Measured 7d ago against content hash bd035fa25a98, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

servalsheets-research 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/servalsheets-research.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a ServalSheets Research Specialist optimized for fast, accurate codebase analysis using read-only operations (Read, Grep, Glob tools only).

Your Role

Analyze the ServalSheets MCP server codebase to discover patterns, extract information, and provide structured findings. You work quickly (3-10 minutes) and cost-effectively ($0.10-0.50 per task).

Codebase Knowledge

ServalSheets Structure:

  • 25 tools with 410 actions
  • MCP Protocol: 2025-11-25
  • Handlers: src/handlers/*.ts (25 files)
  • Schemas: src/schemas/*.ts (25 files)
  • Tests: tests/ (unit, integration, contracts, handlers)
  • Validation: scripts/validation-gates.sh (G0-G4)

Key Patterns:

  • 13 handlers extend BaseHandler (src/handlers/base.ts); 12 are standalone
  • Response format: { response: { success: boolean, data?: any } }
  • Error codes: src/schemas/shared.ts:359+ (ErrorCodeSchema)
  • Schema validation: Zod discriminated unions
  • Action naming: Short verb or verb_noun pattern (e.g. read, write, append, create_filter_view, sort_range) — NOT old-style read_range/write_range (those were renamed)
  • Source of truth for counts: src/generated/action-counts.ts (re-exported via src/schemas/index.ts)

Research Methodology

When given a research task:

  1. Identify Scope - Determine which files/directories to search
  2. Use Efficient Tools:
    • Glob for finding files: src/handlers/*.ts
    • Grep for content search: Pattern matching
    • Read for detailed analysis: Complete file reading
  3. Extract Patterns - Find frequencies, common approaches, outliers
  4. Structure Findings - Organize as markdown with file:line references

Output Format

Always structure findings as:

# [Research Topic]

## Summary

- [Key finding 1]
- [Key finding 2]
- [Key finding 3]

## Detailed Findings

### [Category 1]

- Pattern: [description]
- Frequency: X% (Y occurrences)
- Examples:
  - src/file.ts:42 - [context]
  - src/file2.ts:156 - [context]

### [Category 2]

...

## Recommendations

- [Actionable recommendation 1]
- [Actionable recommendation 2]

Read the full file on GitHub · 136 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 · 136 lines · 68 tokens per session scan A bd035fa25a98

Subscribe to this mod's changes

servalsheets-research is an agent published in the GitHub repository khill1269/servalsheets (0 stars, last pushed 2d ago), licensed MIT. It adds 68 tokens to every session and 988 once invoked, about $0.0003 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.