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/microsoft/hve-core/docusaurus-editsgit clone --depth 1 https://github.com/microsoft/hve-coreWhat 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 | $0.01695 | $0.01695 |
| Opus 5 | $0.00847 | $0.00847 |
| Sonnet 5 | $0.00339 | $0.00339 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
hve-core docusaurus-edits.instructions.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 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.
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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docusaurus Content Instructions
These instructions apply automatically when editing any file under docs/. Follow them to maintain consistency across the documentation site.
Frontmatter
Every documentation page requires these frontmatter fields. npm run lint:frontmatter fails when any of them is missing or empty, and the check runs in PR validation:
title: Page title displayed in the browser tab and sidebardescription: One-sentence summary for SEO and social sharingauthor: Author or team responsible for the contentms.date: Last review or update date inYYYY-MM-DDformatms.topic: One ofoverview,concept,tutorial,reference,how-to,troubleshooting,architecturekeywords: Non-empty list of content categorization terms
Optional fields:
sidebar_position: Integer controlling page order within its category (1, 2, 3...)sidebar_label: Override the sidebar display text when it should differ fromtitletags: Array of tags for content categorizationestimated_reading_time: Positive integer in minutes
---
title: The RPI Workflow
description: How the Research-Plan-Implement-Review loop structures AI-assisted development
author: Microsoft
ms.date: 2026-08-04
ms.topic: concept
keywords:
- rpi
- research
- plan
- implement
- review
sidebar_position: 2
sidebar_label: RPI Workflow
tags: [build-the-work, rpi, workflow]
---
Update ms.date to the current date whenever you review or change a page.
Two subtrees follow different rules:
- Architecture Decision Records under
docs/planning/adrs/are governed byadr-frontmatter.schema.json. They usetagsfor categorization and must not declarekeywords. - Pages under
docs/reference/are generated bynpm run docs:generate, which emits the required fields automatically. Do not hand-edit their frontmatter.
Admonitions
Both Docusaurus admonitions (:::note, :::tip, :::warning) and GitHub-style alerts (> [!NOTE], > [!TIP], > [!WARNING]) are supported. GitHub-style alerts render correctly in Docusaurus via remark-github-blockquote-alert and on GitHub natively. Prefer GitHub-style alerts for content that must render on both platforms.
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.
- 2d ago First seen · 223 lines · 1,695 tokens per session scan A 5d005b162297
hve-core docusaurus-edits.instructions.md is an instructions file published in the GitHub repository microsoft/hve-core (1,405 stars, last pushed 2d ago), licensed MIT. It adds 1,695 tokens to every session, about $0.0085 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
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.
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).
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.
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).
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.
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.