HVE Core is a collection of agents, prompts, coding instructions, and skills for building repeatable software-development workflows with GitHub Copilot. It is intended for individuals and teams that want structured AI-assisted research, planning, implementation, and review, while the catalogue entries provide many of its reusable workflow components.
Borrowing it
Nothing to install: this file belongs to microsoft/hve-core. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/hve-core/main/.github/instructions/workflows.instructions.mdgit clone --depth 1 https://github.com/microsoft/hve-coreWrote 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.
[](https://agentmods.dev/instructions/microsoft/hve-core/workflows)<a href="https://agentmods.dev/instructions/microsoft/hve-core/workflows"><img src="https://agentmods.dev/badge/instructions/microsoft/hve-core/workflows/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.
<a href="https://agentmods.dev/instructions/microsoft/hve-core/workflows"><img src="https://agentmods.dev/badge/instructions/microsoft/hve-core/workflows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.04482 | $0.04482 |
| Opus 5.5 | $0.01793 | $0.01793 |
| Sonnet 5.5 | $0.00896 | $0.00896 |
| Haiku 4.5 | $0.00448 | $0.00448 |
Grade A, and why
hve-core workflows.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 5d 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 — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Actions Workflow Instructions
These instructions define required conventions and security requirements for GitHub Actions workflows in the hve-core repository. All workflows MUST comply with these rules to pass CI validation.
Dependency Pinning
All third-party GitHub Actions MUST be pinned to a full commit SHA. Version tags MUST NOT be used as the reference. Each pin MUST carry a trailing comment naming the exact release tag that points at the pinned commit (for example # v4.2.2, not a moving # v4). The commit MUST be a commit, not an annotated tag object, and MUST be on an upstream tag or in the upstream default branch history. A reusable workflow pinned to an untagged commit on the default branch may use a free-text comment that records its origin.
Required pattern:
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
Forbidden patterns:
uses: actions/checkout@v4
uses: actions/[email protected]
Same-repository actions and reusable workflows use the self-repository syntax, uses: $/.github/actions/<name> or uses: $/.github/workflows/<name>.yml. It resolves to the running commit, needs no checkout, and can't load code a job cloned at runtime, so these references are excluded from SHA pinning requirements. Don't use the workspace-relative ./ form; it loads whatever is checked out in the workspace.
Enforcement: Violations are detected by scripts/security/Test-DependencyPinning.ps1 and scripts/security/Test-SHAStaleness.ps1. scripts/security/Test-ActionPinProvenance.ps1 resolves each comment and commit against the upstream repository with git ls-remote and the compare API, and fails on a mislabeled comment, a tag-object pin, or a commit that is on no tag and not in the default branch history (a possible impostor commit). CI will fail on SHA pinning violations.
Permissions
Workflows MUST declare explicit permissions following the principle of least privilege. The workflow-level block MUST be contents: read or permissions: {} and MUST NOT grant any other scope, including read scopes such as security-events: read. Additional permissions MUST be granted at the job level and only when required for a specific capability. The read-all and write-all values MUST NOT be used at any level; read-all includes reads of security events and vulnerability alerts.
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.
- 5d ago Changed · +43 lines · +1,226 tokens per session 736cbabed01b
- 12d ago Changed · +3 lines · +52 tokens per session a858fc0844cf
- 17d ago Changed · +14 lines · +279 tokens per session 7bad2b252333
- 1mo ago Changed · +3 lines · +119 tokens per session 622703bde45e
- 1mo ago First seen · 358 lines · 2,806 tokens per session scan A 116ac6bee7ba
hve-core workflows.instructions.md is an instructions file published in the GitHub repository microsoft/hve-core (1,580 stars, last pushed yesterday), licensed MIT. It adds 4,482 tokens to every session, about $0.0179 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 2026-08-30.
Other instructions, from other repositories
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
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, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.