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/workflowsgit 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 | $0.02806 | $0.02806 |
| Opus 5 | $0.01403 | $0.01403 |
| Sonnet 5 | $0.00561 | $0.00561 |
| Haiku 4.5 | $0.00281 | $0.00281 |
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 yesterday.
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 — 358 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. A semantic version MAY be included as a trailing comment for readability.
Required pattern:
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
Forbidden patterns:
uses: actions/checkout@v4
uses: actions/[email protected]
Local reusable workflows referenced via relative paths are excluded from SHA pinning requirements.
Enforcement: Violations are detected by scripts/security/Test-DependencyPinning.ps1 and scripts/security/Test-SHAStaleness.ps1. CI will fail on SHA pinning violations.
Permissions
Workflows MUST declare explicit permissions following the principle of least privilege. The default permission set is contents: read. Additional permissions MUST be granted at the job level and only when required for a specific capability.
Every job MUST declare its own permissions: block whenever the workflow-level block grants any scope. A job with no block silently inherits the workflow grant, which is neither explicit nor auditable. The one exception is a workflow-level permissions: {}, which grants nothing, so a job beneath it that declares no block inherits an empty set and holds no scope.
An empty workflow-level block is a default, not a ceiling. A job that does declare its own block still receives what it declares, because job-level permissions replace the workflow-level set rather than being capped by it.
Required pattern:
permissions:
contents: read
pull-requests: write
Job-level permissions example:
jobs:
validate:
name: Validate Code
runs-on: ubuntu-latest
permissions:
contents: read
steps:
- name: Checkout
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Run validation
run: |
echo "Running validation steps"
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.
- yesterday 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 (1,405 stars, last pushed 2d ago), licensed MIT. It adds 2,806 tokens to every session, about $0.0140 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.
buildNext
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
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
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.