heritagegraph: Instructions file for Codex

AGENTS.md

heritagegraph AGENTS.md is an instructions file for Codex, OpenCode from CAIRNepal/heritagegraph. It costs 7,870 tokens per session, scanned A, original, MIT.

Project-specific instructions for coding agents working on the heritagegraph repository.

In plain words
What is it for?
Use them when modifying heritagegraph so the agent understands the repository and follows its required coding practices.
Why use it?
They give agents the project's background, file layout, critical rules, and a reminder not to hardcode secrets before coding.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is CAIRNepal/heritagegraph's own configuration. It tells Codex and OpenCode 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/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/CAIRNepal/heritagegraph

Made for: Codex, OpenCode.

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 AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cairnepal/heritagegraph/agents-md"><img src="https://agentmods.dev/badge/instructions/cairnepal/heritagegraph/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,870 This file is loaded in full into every session.
When invoked 7,870 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 $0.07870 $0.07870
Opus 5.5 $0.03148 $0.03148
Sonnet 5.5 $0.01574 $0.01574
Haiku 4.5 $0.00787 $0.00787

Measured 11d ago against content hash 3019707ee003, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

heritagegraph AGENTS.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 11d 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.

AGENTS.md · 415 lines

How it starts

The opening of the file, as written. The whole thing — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — AI Agent Instructions for HeritageGraph

Purpose: This file gives AI coding agents (GPT, Claude, Copilot, Cursor, Cody, etc.) the full context they need to work effectively in this codebase. Read this file first before making any changes.


🧠 What Is This Project?

HeritageGraph is a full-stack platform by CAIR-Nepal for digitally preserving and publishing cultural heritage data as linked open data. It has:

  • A Django REST Framework backend (API, auth, data models)
  • A Next.js 15 main app (heritage_graph_ui) — dashboard, contribution forms, graph visualization
  • A Next.js 15 marketing landing (heritage_graph_landing) — public site; same brand colors as the dashboard
  • NextAuth v4 + Google OAuth for authentication
  • Traefik as reverse proxy (routes traffic, handles TLS)
  • PostgreSQL as database (Django backend)

📁 Repository Structure

heritagegraph/
│
├── heritage_graph/              # Django backend (DRF)
│   ├── apps/
│   │   ├── heritage_data/       # Main app: submissions, moderation, profiles
│   │   ├── cidoc_data/          # CIDOC-CRM ontology, identity layer, RDF projection
│   │   ├── graph/               # KG engine (Oxigraph), museum enrichment, KG APIs
│   │   ├── document_processing/ # Document upload (OCR pipeline suspended)
│   │   ├── assistant/           # Grounded in-app chat (OpenRouter)
│   │   └── health_check.py      # /health/ endpoints for Docker/Traefik
│   ├── celery_app.py            # **NEW** Celery app initialization (imported from `heritage_graph/__init__.py`)
│   ├── settings/
│   │   ├── __init__.py          # Env-based dispatch (DJANGO_ENV → dev or prod)
│   │   ├── base.py              # Shared settings (apps, middleware, DRF config, Celery)
│   │   ├── development.py       # Dev: SQLite, DEBUG=True, Celery eager mode
│   │   └── production.py        # Prod: PostgreSQL, env-based secrets
│   ├── urls.py                  # Root URL configuration
│   ├── entrypoint.sh            # Docker entrypoint (migrate, superuser, start)
│   ├── manage.py                # Django management
│   └── requirements.txt         # Python dependencies
│
├── heritage_graph_ui/           # Next.js 15 main app (authenticated product UI)
│   ├── src/
│   │   ├── app/                 # App Router pages
│   │   │   ├── layout.tsx       # Root layout (SessionProvider, ThemeProvider)
│   │   │   ├── (dashboard)/     # Dashboard route group (sidebar layout)
│   │   │   │   ├── page.tsx     # Dashboard home (/)
│   │   │   │   ├── knowledge/   # Knowledge base CRUD (entity, person, etc.)
│   │   │   │   ├── contribute/  # Contribution forms
│   │   │   │   ├── curation/    # Moderation & activity logs
│   │   │   │   │   ├── contributions/  # Contribution queue
│   │   │   │   │   ├── activity/       # Activity log
│   │   │   │   │   ├── review/         # Triaged review queue
│   │   │   │   │   │   └── [id]/       # Three-panel review workspace
│   │   │   │   │   ├── identity/       # Identity resolution queue + workspace
│   │   │   │   │   ├── conflicts/      # Conflict resolution
│   │   │   │   │   └── dashboard/      # Reviewer dashboard
│   │   │   │   ├── community/   # Contributors & organizations
│   │   │   │   └── graphview/   # Graph visualization (Cytoscape)
│   │   │   └── api/auth/        # NextAuth API route
│   │   ├── components/          # Shared components (shadcn/ui, data tables, chat)
│   │   ├── providers/           # Context providers (ChatContext)
│   │   ├── hooks/               # Custom hooks (use-mobile)
│   │   └── lib/                 # Utilities (auth.ts, utils.ts, chat/)
│   ├── types/                   # TypeScript type augmentations
│   └── public/                  # Static assets
│
├── heritage_graph_landing/      # Next.js 15 marketing site (port 3001 locally)
│   ├── src/app/                 # Public landing + chat widget (calls same assistant API)
│   └── README.md                # Env: NEXT_PUBLIC_APP_URL → main app origin
│
├── infra/                       # Infrastructure configs
│   ├── traefik/                 # Traefik reverse proxy config
│   ├── postgres/                # Database init scripts
│   └── docker/                  # Legacy docker-compose files (reference only)
│
├── docker-compose.yml           # Main compose: all services (dev)
├── docker-compose-coolify.yml   # Coolify (platform proxy; no in-repo Traefik)
├── docker-compose-dokploy.yml   # Dokploy (same + MIGRATION_AUTO_REPAIR, landing build args)
├── documentation/deployment/    # DEPLOYMENT.md, DOKPLOY.md, Coolify runbooks
├── docker-compose.prod.yml      # Production override (HTTPS, Let's Encrypt)
├── Dockerfile.backend           # Backend multi-stage build
├── Dockerfile.frontend          # Same as heritage_graph_ui/Dockerfile (repo-root `-f` alias)
├── Makefile                     # Convenience commands
├── .env.example                 # Environment variable template
├── tests/                       # E2E runners (see documentation/testing/TESTING.md)
└── documentation/               # Topic guides (see DOCS.md)

Read the full file on GitHub · 415 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. 11d ago Changed · -55 tokens per session 3019707ee003
  2. 15d ago Changed · +190 lines · +5,095 tokens per session 6e37cc06c0f6
  3. 2mo ago First seen · 225 lines · 2,830 tokens per session scan A 9763904600da

Subscribe to this mod's changes

heritagegraph AGENTS.md is an instructions file published in the GitHub repository CAIRNepal/heritagegraph (4 stars, last pushed 11d ago), licensed MIT. It adds 7,870 tokens to every session, about $0.0315 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 AGENTS.md compared with instructions from other repositories

heritagegraph AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
heritagegraph AGENTS.mdCAIRNepal/heritagegraphInstructions file411d agoMITA7,870Codex, OpenCode
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
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode