sabela: Instructions file for Claude Code

CLAUDE.md

sabela CLAUDE.md is an instructions file for Claude Code from DataHaskell/sabela. It costs 2,583 tokens per session, scanned A, original, MIT.

Repository guidance for Sabela, a web-based notebook where executable Haskell code is mixed with Markdown prose. It covers running, testing, linting, formatting, and frontend development.

In plain words
What is it for?
Use it when starting Sabela, running its HSpec tests, checking Haskell with HLint, formatting Haskell or frontend files, or working on the web interface.
Why use it?
It puts the project’s build and quality checks in one place, so contributors know how to run changes and verify them.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

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

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 sabela CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/datahaskell/sabela/claude-md/github.svg)](https://agentmods.dev/instructions/datahaskell/sabela/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/datahaskell/sabela/claude-md"><img src="https://agentmods.dev/badge/instructions/datahaskell/sabela/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 sabela CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/datahaskell/sabela/claude-md"><img src="https://agentmods.dev/badge/instructions/datahaskell/sabela/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,583 This file is loaded in full into every session.
When invoked 2,583 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 $0.02583 $0.02583
Opus 5.5 $0.01033 $0.01033
Sonnet 5.5 $0.00517 $0.00517
Haiku 4.5 $0.00258 $0.00258

Measured 6d ago against content hash 45bc919a97ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sabela 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 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.

CLAUDE.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 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.

Project Overview

Sabela is a reactive notebook environment for Haskell — a web-based IDE where users write executable Haskell code mixed with Markdown prose. Notebooks are stored as plain Markdown files. The name means "to respond" in Ndebele, reflecting its reactive execution model.

Commands

# Build and run
cabal run                                  # Starts server on localhost:3000
cabal run sabela -- 3000 .                  # sabela [--host H] <port> <work-dir> [global-file] [extra-pkgs...]
                                           # binds 127.0.0.1 by default (or SABELA_HOST); off loopback every
                                           # route needs SABELA_TOKEN (generated + printed if unset)

# Tests
cabal test                                 # Runs HSpec test suite

# Lint and format
./scripts/lint.sh                          # HLint on src/, app/, test/
./scripts/lint.sh --fix                    # Auto-fix lint issues on edited files
./scripts/format.sh                        # fourmolu (Haskell) + prettier (frontend)
./scripts/format.sh --haskell-only         # Skip the prettier pass
./scripts/format.sh --frontend-only        # Only static/*.{html,js,mjs,css}
./scripts/format.sh --check                # Dry-run; non-zero exit on drift

Frontend (modular sources → bundled embeds)

The three served pages — static/index.html (the editor), static/dashboard.html, and static/slideshow.html — are generated build artifacts. The binary embeds them verbatim via Template Haskell (embedFile in Sabela.Server.Static), so the single executable still ships fully self-contained with no runtime asset fetches. Do not hand-edit those files; edit the sources and rebuild.

Layout

The editable sources live under static/src/<page>/:

static/src/index/
  index.html          # shell: <head>/<body> markup + ordered <link>/<script>/include refs
  css/*.css           # style partials, inlined in order (cascade preserved)
  js/*.js             # script partials, inlined in order (one shared global scope)
  html/icons.svg      # inline SVG icon sprite (an asset; inlined, not fetched)
  html/modals.html    # body markup fragment

Read the full file on GitHub · 196 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. 6d ago Changed · +2 lines · +46 tokens per session 45bc919a97ee
  2. 17d ago Changed · +13 lines · +171 tokens per session 10f11c449265
  3. 2mo ago First seen · 181 lines · 2,366 tokens per session scan A 142ad30e1d8f

Subscribe to this mod's changes

sabela CLAUDE.md is an instructions file published in the GitHub repository DataHaskell/sabela (117 stars, last pushed 6d ago), licensed MIT. It adds 2,583 tokens to every session, about $0.0103 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 2026-08-30.

Related

sabela CLAUDE.md compared with instructions from other repositories

sabela CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sabela CLAUDE.mdDataHaskell/sabelaInstructions file1176d agoMITA2,583Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode