ihp CLAUDE.md

ihp CLAUDE.md is an instructions file for coding agents from digitallyinduced/ihp. It costs 3,452 tokens per session, scanned A, original, MIT.

Repository instructions for developing IHP, a Haskell web framework that includes tools for routing, HTML templates, and PostgreSQL database work. It covers environment setup and test commands.

In plain words
What is it for?
For setting up IHP with Nix or devenv, using GHCi for quick checks, and running the project's IDE tests.
Why use it?
It gives developers the project's expected setup and faster ways to check Haskell code before running slower full builds.

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/digitallyinduced/ihp/claude-md
Clone the repo
git clone --depth 1 https://github.com/digitallyinduced/ihp

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 ihp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/digitallyinduced/ihp/claude-md.svg)](https://agentmods.dev/instructions/digitallyinduced/ihp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/digitallyinduced/ihp/claude-md"><img src="https://agentmods.dev/badge/instructions/digitallyinduced/ihp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,452 This file is loaded in full into every session.
When invoked 3,452 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 $0.03452 $0.03452
Opus 5 $0.01726 $0.01726
Sonnet 5 $0.00690 $0.00690
Haiku 4.5 $0.00345 $0.00345

Measured 4d ago against content hash 87016b7260d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ihp 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 · 393 lines

How it starts

The opening of the file, as written. The whole thing — 393 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.

Overview

IHP (Integrated Haskell Platform) is a batteries-included Haskell web framework built on Haskell and Nix. It follows an MVC architecture with type-safe routing, HSX templating (JSX-like syntax for HTML), and PostgreSQL as the database.

Development Environment Setup

IHP uses devenv.sh (a wrapper around nix develop and direnv) for development:

cd /path/to/ihp
direnv allow

Alternatively, use nix develop directly to enter a dev shell. You can also use direnv exec . to get a cached nix develop environment.

Running Tests

Prefer ghci for quick type checking and iteration — full nix builds (nix flake check) are slow. Use ghci interactively or via echo ... | ghci one-liners for fast feedback.

When using ghci, keep in mind that it expects input on stdin. If you don't provide any, ghci will never return. The echo ... | ghci pattern handles this correctly by piping input.

IHP IDE Tests (from the repo root):

# Interactive (allows :r to reload after changes):
ghci
:l ihp-ide/Test/Main.hs
main
:r
main

# One-liner:
echo -e ':l ihp-ide/Test/Main.hs\nmain' | ghci

All tests via Nix (slower but comprehensive):

nix flake check --impure

Verify a single module compiles:

echo ':l ihp-ide/IHP/IDE/CodeGen/MigrationGenerator.hs' | ghci

When adding new tests, add them to Test/Main.hs in the appropriate package.

Running the Dev Server (for local IHP development)

From the IHP directory with a host project:

export DEBUG=1  # Optional: enable debug logging
ghci
:l ihp-ide/exe/IHP/IDE/DevServer.hs
mainInParentDirectory

Project Structure

This is a monorepo with multiple Haskell packages:

Package Purpose
ihp/ Core web framework (routing, controllers, views, models, validation)
ihp-ide/ Development server, code generators, schema designer
ihp-hsx/ HSX templating system (JSX-like HTML in Haskell)
ihp-migrate/ Database migration tool
ihp-datasync/ Real-time data synchronization via WebSockets
ihp-graphql/ GraphQL API support
ihp-hspec/ Testing utilities
ihp-openai/ OpenAI integration
ihp-ssc/ Server-side components

Read the full file on GitHub · 393 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 · 393 lines · 3,452 tokens per session scan A 87016b7260d9

Subscribe to this mod's changes

ihp CLAUDE.md is an instructions file published in the GitHub repository digitallyinduced/ihp (5,351 stars, last pushed 2d ago), licensed MIT. It adds 3,452 tokens to every session, about $0.0173 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.