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.
npx agentmods add instructions/datahaskell/sabela/claude-mdgit clone --depth 1 https://github.com/DataHaskell/sabelaWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02366 | $0.02366 |
| Opus 5 | $0.01183 | $0.01183 |
| Sonnet 5 | $0.00473 | $0.00473 |
| Haiku 4.5 | $0.00237 | $0.00237 |
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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 181 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 <port> <work-dir> [global-file] [extra-pkgs...]
# 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
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.
- 3d ago First seen · 181 lines · 2,366 tokens per session scan A 142ad30e1d8f
sabela CLAUDE.md is an instructions file published in the GitHub repository DataHaskell/sabela (114 stars, last pushed 10d ago), licensed MIT. It adds 2,366 tokens to every session, about $0.0118 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 2026-08-30.
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).
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.
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.
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.
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).
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.