tablestakes: Instructions file for Claude Code

CLAUDE.md

tablestakes CLAUDE.md is an instructions file for Claude Code from oborchers/tablestakes. It costs 1,195 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Tablestakes, an MCP server that reads and edits tables in HTML and Markdown documents synced with GitBook. Markdown is a plain-text document format, while HTML is the markup used to structure web pages.

In plain words
What is it for?
Use it when developing, testing, or maintaining Tablestakes and its table parser, editor, tools, or checks.
Why use it?
It explains how the project preserves each file's original table format while showing AI agents a simpler table representation.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

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

Reuse

Borrowing it

Nothing to install: this file belongs to oborchers/tablestakes. 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/oborchers/tablestakes/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/oborchers/tablestakes

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 tablestakes CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/oborchers/tablestakes/claude-md/github.svg)](https://agentmods.dev/instructions/oborchers/tablestakes/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/oborchers/tablestakes/claude-md"><img src="https://agentmods.dev/badge/instructions/oborchers/tablestakes/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for tablestakes CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/oborchers/tablestakes/claude-md"><img src="https://agentmods.dev/badge/instructions/oborchers/tablestakes/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,195 This file is loaded in full into every session.
When invoked 1,195 The same file — it is already loaded in full.
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 $0.01195 $0.01195
Opus 5.5 $0.00478 $0.00478
Sonnet 5.5 $0.00239 $0.00239
Haiku 4.5 $0.00120 $0.00120

Measured 2mo ago against content hash 0448837e27d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tablestakes 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 2mo 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 · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Is

tablestakes is an MCP server that reads and edits HTML/Markdown tables in GitBook-synced documents. LLMs see clean pipe tables; files on disk stay in their original format (collapsed single-line HTML for GitBook, pipe tables for native Markdown). Published on PyPI (uvx tablestakes) and the MCP Registry (io.github.oborchers/tablestakes).

Commands

make init          # First-time setup: venv + deps + pre-commit hooks
make check         # Run all checks: format-check + lint + typecheck + test
make format        # Auto-format with ruff
make test          # Run tests
make test-cov      # Tests with coverage report
make typecheck     # mypy strict mode
make build         # Build wheel (runs clean first)

Single test: uv run pytest tests/test_parser.py::TestDetectTables::test_mixed_document_table_count -v

Dev server with hot-reload: uv run fastmcp dev

List registered tools: uv run fastmcp list

Architecture

Four Layers

  1. Parser (parser.py) — detect_tables(content) scans Markdown, returns list[RawTable] with byte offsets, classification, and cached BeautifulSoup Tags. Detection precedence: fenced code blocks (excluded) → HTML comments (excluded) → <table> blocks → GFM pipe tables.

  2. Converter (converter.py) — Bidirectional HTML↔pipe. Read path: html_to_rows() uses markdownify per-cell for inline tags (<strong>→**). Write path: rows_to_html() clones the original AST to preserve GitBook attributes (width=, data-*), falls back to fresh HTML build on structural changes.

  3. Hasher (hasher.py) — compute_hash() returns SHA-256 truncated to 12 hex chars. Used for optimistic concurrency version tokens.

  4. Tools (tools/read.py, tools/write.py, tools/column.py) — 9 MCP tools registered via @mcp.tool(output_schema=None) decorators.

The Shifted-Lines Safety Model

Read the full file on GitHub · 94 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. 2mo ago First seen · 94 lines · 1,195 tokens per session scan A 0448837e27d0

Subscribe to this mod's changes

tablestakes CLAUDE.md is an instructions file published in the GitHub repository oborchers/tablestakes (1 stars, last pushed 23d ago), licensed Apache-2.0. It adds 1,195 tokens to every session, about $0.0048 per session on Opus 5.5. 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

tablestakes CLAUDE.md compared with instructions from other repositories

tablestakes CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
tablestakes CLAUDE.mdoborchers/tablestakesInstructions file123d agoApache-2.0A1,195Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot
generative-ai-for-beginners AGENTS.mdmicrosoft/generative-ai-for-beginnersInstructions file124ktodayMITA2,981Codex, OpenCode