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.
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 skills add microsoft/hve-core --skill vexgit 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/skills/microsoft/hve-core/vex)<a href="https://agentmods.dev/skills/microsoft/hve-core/vex"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/vex.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.01385 |
| Opus 5 | $0.00015 | $0.00692 |
| Sonnet 5 | $0.00006 | $0.00277 |
| Haiku 4.5 | $0.00003 | $0.00138 |
Grade A, and why
vex 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 3d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VEX skill
This skill is the entrypoint for VEX operations in hve-core. It combines the OpenVEX v0.2.0 specification reference with reusable management playbooks for implementing, reviewing, and validating VEX documents. The normative reference material below remains the authoritative source for schema, status logic, and public-source guidance.
VEX management playbooks
Detection, drafting, and attestation are workflow-owned automation. This skill supplies the
reusable procedures, mutation rules, and review criteria. The CVE Analyzer subagent performs the per-CVE exploitability analysis that feeds those workflows.
Implement VEX in a target project
Use this playbook when standing up VEX in a target project. Scaffold the VEX document under
security/vex, wire the vex-detect and vex-draft workflows, reference the PR-body scaffold in
assets/pr-body-scaffold.yml, connect the dedicated reusable VEX
attestation workflow for provenance and OpenVEX-over-SBOM attestation, and set CODEOWNERS on the VEX document.
Use references/vex-status-logic.md and the
vex-standards.instructions.md instructions for the detailed rules.
Review and validate VEX
Use this playbook when reviewing drafted VEX statements. Assess the status determination against the evidence and confidence bands, honor the document mutation and forbidden-transition contract, and validate the release attestation output. Attestation generation is owned by the dedicated reusable VEX attestation workflow, not by the reviewer. The forthcoming tested gate module and tests will live in this skill so the workflow and interactive entry points can share the same rules.
VEX statuses
| Status | Meaning |
|---|---|
not_affected |
The vulnerability is not exploitable in this product. Requires a justification or impact_statement. |
affected |
The vulnerability is exploitable. Requires an action_statement describing remediation. |
fixed |
The vulnerability was present but has been remediated in this product version. |
under_investigation |
The author is evaluating whether the vulnerability affects this product. Safe default for uncertain cases. |
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/pr-body-scaffold.yml 1.8 KB
- pyproject.toml 653 B
- references/cve-data-sources.md 9.9 KB
- references/openvex-schema.md 11 KB
- references/vex-status-logic.md 7.0 KB
- scripts/vex_gate.py 4.7 KB runs code
- SECURITY.md 19 KB
- tests/corpus/0_empty 0 B
- tests/corpus/1_finding_table 146 B
- tests/corpus/2_terminal_statement 40 B
- tests/corpus/3_evaluate_mixed 71 B
- tests/corpus/4_json_like_payload 182 B
- tests/fuzz_harness.py 2.7 KB runs code
- tests/test_vex_gate.py 8.1 KB runs code
- uv.lock 52 KB
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.
- 3d ago First seen · 113 lines · 31 tokens per session scan A e4590ad74ba3
vex is a skill published in the GitHub repository microsoft/hve-core (1,436 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 1,385 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…