oppertunity-party AGENTS.md

Repository instructions for a data pipeline that collects content from the New Zealand Opportunity Party website and converts it into organized Markdown files. A data pipeline is a sequence that gathers, cleans, and prepares information for use.

In plain words
What is it for?
Working on Dagster-managed ingestion and transformation jobs for policies, blog posts, news, profiles, events, and governance documents.
Why use it?
They define where raw and cleaned data belongs and explain how the project keeps ingestion separate from later users of the data.

Instructions file for CodexOpenCode

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/mcwalrus/oppertunity-party/agents-md
Clone the repo
git clone --depth 1 https://github.com/mcwalrus/oppertunity-party

Made for: Codex, OpenCode.

Per session 1,746 This file is loaded in full into every session.
When invoked 1,746 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01746 $0.01746
Opus 5 $0.00873 $0.00873
Sonnet 5 $0.00349 $0.00349
Haiku 4.5 $0.00175 $0.00175

Measured 2d ago against content hash dd5cc5319062, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

oppertunity-party AGENTS.md scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

just validate-docs # hyperlink on docs/**/*.md (internal) + curl HEAD on external URLs
AGENTS.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Project Overview

Scrapes the New Zealand Opportunity Party website and converts content into local markdown files. Sources include policies (with linked PDFs), blog posts, news, team profiles, events, and party governance documents.

Key Paths

Path Description Git
data/sources/opportunity-website/ Raw scraper output — written by ingestors, never read by consumers Ignored
data/clean/ Normalized content — canonical source for all consumers Tracked
data/clean/_index.json Cross-type search index (regenerated each transform run) Tracked
pipeline/ Dagster code location — wraps ingestion + transforms as assets
docs/data-architecture.md Pipeline design, layer invariants, how to add source/consumer Tracked
docs/dependencies.md Why each dependency exists (grouped by purpose) Tracked
docs/reference/ Reference materials used while building (Dagster course, …) Tracked
tasks/ PRDs and planning notes (prd-*.md, campaign-website-issues/) Tracked

TODO: add docs/data-schema.md

Data Pipeline

https://dagster.io/ is the library we use to manage ETL (Extract, Transform, Load) processes. This will include web-scraping, data cleansing, transformations, site build, sitemap resolution, and deployment. We expect agents to apply the appropriate Asset management.

Operations go through Dagster

Most operations should be expressed as Dagster assets — not as standalone scripts or justfile recipes. The justfile is reserved for:

Read the full file on GitHub · 132 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. 2d ago First seen · 132 lines · 1,746 tokens per session scan A dd5cc5319062

Subscribe to this mod's changes

oppertunity-party AGENTS.md is an instructions file published in the GitHub repository mcwalrus/oppertunity-party (0 stars, last pushed 10d ago), licensed MIT. It adds 1,746 tokens to every session, about $0.0087 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories