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/dependency-feedsgit 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 | $0.00905 | $0.00905 |
| Opus 5 | $0.00452 | $0.00452 |
| Sonnet 5 | $0.00181 | $0.00181 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
hve-core dependency-feeds.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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Public Dependency Feed Policy
Outcome
Every committed dependency manifest and lockfile resolves from a canonical public package registry so external contributors and CI can restore the repository without private network or feed access.
Required Practice
- Commit an
.npmrcbeside everypackage.jsonthat npm installs from, and repeat the canonical registry settings in each one. npm reads project configuration only from the root it runs in, so a nested project ignores the repository-root.npmrcand resolves from whatever registry the machine supplies. Apply this to install roots only; a workspace member, a generated manifest, or a template that npm never installs separately does not need its own file. - Generate npm lockfiles from
https://registry.npmjs.org/and retain its canonical tarball URLs and integrity metadata. - Keep every npm lockfile
integrityvalue onsha512. Internal mirrors often omitdist.integrityand publish onlydist.shasum, which makes npm record asha1value and silently weakens verification to a collision-vulnerable hash. Rewriting aresolvedURL back to the public registry does not repair a downgradedintegrityvalue. - Use public ecosystem sources for other package managers, such as PyPI, the public PyTorch index, GitHub releases, NuGet Gallery, PowerShell Gallery, crates.io, and the Go module proxy.
- Run
npm run lint:public-dependency-feedsafter changing dependency metadata. - When machine or enterprise configuration redirects a package manager through an internal mirror, override it with the canonical public registry while generating committed lockfiles.
- Treat a package version available only from an internal mirror as unpublished for this OSS repository. Wait for a public release or select a publicly available version rather than committing an internal feed URL.
Prohibited Sources
Do not commit dependency source URLs pointing at private or organization-scoped artifact feeds, corporate or machine-level package proxies, authenticated URLs, or URLs carrying registry credentials. Do not commit lockfile entries whose integrity value uses an algorithm weaker than sha512.
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 · 44 lines · 905 tokens per session scan A 33cb52968e97
hve-core dependency-feeds.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 905 tokens to every session, about $0.0045 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.