gridka CLAUDE.md

gridka CLAUDE.md is an instructions file for coding agents from Ceesaxp/gridka. It costs 1,293 tokens per session, scanned A, original, MIT.

Project-specific instructions for Gridka, a macOS CSV viewer built with Swift, AppKit, and DuckDB. DuckDB is the embedded database used to read and query large files.

In plain words
What is it for?
Use them when modifying Gridka’s user interface, CSV loading, queries, row caching, or related Swift code.
Why use it?
They keep changes consistent with the project’s architecture, including SQL-based sorting and filtering, serial database access, and limited in-memory caching.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/ceesaxp/gridka/claude-md
Clone the repo
git clone --depth 1 https://github.com/Ceesaxp/gridka

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 gridka CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ceesaxp/gridka/claude-md.svg)](https://agentmods.dev/instructions/ceesaxp/gridka/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ceesaxp/gridka/claude-md"><img src="https://agentmods.dev/badge/instructions/ceesaxp/gridka/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,293 This file is loaded in full into every session.
When invoked 1,293 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01293 $0.01293
Opus 5 $0.00647 $0.00647
Sonnet 5 $0.00259 $0.00259
Haiku 4.5 $0.00129 $0.00129

Measured 4d ago against content hash 55d036ac152d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gridka CLAUDE.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.

CLAUDE.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Overview

Gridka is a native macOS CSV viewer built with Swift (AppKit) and DuckDB (C API). It handles very large files (100M+ rows) via virtual scrolling and SQL-backed data access. The UI is purely AppKit — no SwiftUI, no web views, no Electron.

Architecture Rules

  • Single process. DuckDB is embedded via C API through a bridging header. No IPC, no separate backend.
  • AppKit only. Use NSTableView (view-based, with data source delegate), NSView, NSViewController. Never use SwiftUI.
  • Every user interaction is SQL. Sort, filter, search all mutate a ViewState struct which is translated to a SQL query by QueryCoordinator. No in-memory data manipulation in Swift.
  • Serial query execution. All DuckDB calls go through a single serial DispatchQueue. DuckDB connections are not thread-safe. UI updates dispatch back to main.
  • Page-based row cache. RowCache fetches pages of 500 rows. Max 20 pages cached. LRU eviction. Never load all rows into memory.

Key Domain Types

  • FileSession — represents one opened file, owns the DuckDB connection and table
  • ViewState — current sort, filters, search term, visible range. Immutable value type. Every change produces a new ViewState.
  • QueryCoordinator — pure function: ViewState → SQL String. No side effects. Highly testable.
  • RowCache — LRU cache of fetched row pages. Cache key is page index. Invalidated when ViewState changes filters/sort.
  • DuckDBEngine — thin wrapper around DuckDB C API. Owns database and connection lifecycle.
  • ColumnDescriptor — column name, DuckDB type, display type, index.
  • ColumnFilter — column name, operator, value. Type-aware operators.

Code Conventions

  • Swift 5.10+, target macOS 14.0+
  • No third-party dependencies beyond DuckDB static library
  • Use final class for all classes unless inheritance is explicitly needed
  • Prefer value types (structs, enums) for model layer
  • Error handling: define errors in GridkaError enum, throw from engine layer, handle in UI layer
  • Use DispatchQueue for concurrency (not async/await — AppKit delegate patterns don't mix well)
  • All SQL strings are parameterized or escaped via helper functions. Never interpolate user input directly.

Read the full file on GitHub · 99 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. 4d ago First seen · 99 lines · 1,293 tokens per session scan A 55d036ac152d

Subscribe to this mod's changes

gridka CLAUDE.md is an instructions file published in the GitHub repository Ceesaxp/gridka (10 stars, last pushed 15d ago), licensed MIT. It adds 1,293 tokens to every session, about $0.0065 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens