heritagegraph: Instructions file for Claude Code

CLAUDE.md

heritagegraph CLAUDE.md is an instructions file for Claude Code from CAIRNepal/heritagegraph. It costs 2,656 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for the heritagegraph project. It covers coding style, the project’s purpose, and its Django REST Framework backend, Python setup, and settings pattern.

In plain words
What is it for?
Use it when developing or maintaining heritagegraph’s Python and Django backend.
Why use it?
It gives the coding agent the project context and conventions needed to work consistently in the codebase.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

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

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 heritagegraph CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cairnepal/heritagegraph/claude-md"><img src="https://agentmods.dev/badge/instructions/cairnepal/heritagegraph/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,656 This file is loaded in full into every session.
When invoked 2,656 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 $0.02656 $0.02656
Opus 5.5 $0.01062 $0.01062
Sonnet 5.5 $0.00531 $0.00531
Haiku 4.5 $0.00266 $0.00266

Measured 15d ago against content hash c9f7d23ab599, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

heritagegraph 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 15d 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 · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Coding Conventions & AI Agent Style Guide

Purpose: This file tells AI coding agents exactly how to write code in this project — what patterns to follow, what to avoid, and how to stay consistent with the existing codebase.


🎯 Project Identity

  • Project: HeritageGraph — Cultural Heritage Linked Open Data platform
  • Organization: CAIR-Nepal
  • Stack: Django REST Framework + Next.js 15 + NextAuth v4 + Google OAuth + Traefik + PostgreSQL
  • Branch strategy: Work from v1 branch

🐍 Backend (Django REST Framework)

Python Version & Tooling

  • Python: 3.12 (matches Dockerfile.backend and pyproject.toml)
  • Formatter: ruff (configured in pyproject.toml) — replaces black/isort
  • Linting: ruff — run ruff check . and ruff format .
  • Package manager: pip with requirements.txt (no Poetry/PDM)
  • WSGI server: gunicorn in production, runserver in dev

Django Settings Pattern

# Settings are split across files:
# settings/__init__.py reads DJANGO_ENV and dispatches
# Always import shared config:
from .base import *  # noqa: F403
  • Never modify base.py for environment-specific config. Use development.py or production.py.
  • All secrets must come from os.environ.get() in production. Use django-environ for .env loading.

Model Conventions

# Use UUID primary keys for new models
import uuid
from django.db import models

class MyModel(models.Model):
    id = models.UUIDField(primary_key=True, default=uuid.uuid4, editable=False)
    created_at = models.DateTimeField(auto_now_add=True)
    updated_at = models.DateTimeField(auto_now=True)

    class Meta:
        ordering = ["-created_at"]
        db_table = "my_model"  # explicit table name, snake_case
  • New models should follow the CulturalEntity / Revision / Activity pattern (not the legacy Submission flat-field pattern).
  • Use JSONField for flexible/extensible data — not 80+ CharFields.
  • Always set db_table explicitly in Meta.
  • Always add created_at and updated_at timestamps.

Read the full file on GitHub · 297 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. 15d ago Changed · +7 lines · +179 tokens per session c9f7d23ab599
  2. 2mo ago First seen · 290 lines · 2,477 tokens per session scan A c17c3de24078

Subscribe to this mod's changes

heritagegraph CLAUDE.md is an instructions file published in the GitHub repository CAIRNepal/heritagegraph (4 stars, last pushed 11d ago), licensed MIT. It adds 2,656 tokens to every session, about $0.0106 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

heritagegraph CLAUDE.md compared with instructions from other repositories

heritagegraph CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
heritagegraph CLAUDE.mdCAIRNepal/heritagegraphInstructions file411d agoMITA2,656Claude Code
graftcode graftcode-python.instructions.mdgrft-dev/graftcodeInstructions file9671mo agononeA4,639GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, 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