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 agentmods add skills/microsoft/hve-core/outcome-hypothesisnpx skills add microsoft/hve-core --skill outcome-hypothesisgit 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/outcome-hypothesis)<a href="https://agentmods.dev/skills/microsoft/hve-core/outcome-hypothesis"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/outcome-hypothesis.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 | $0.00103 | $0.04221 |
| Opus 5 | $0.00051 | $0.02110 |
| Sonnet 5 | $0.00021 | $0.00844 |
| Haiku 4.5 | $0.00010 | $0.00422 |
Grade A, and why
outcome-hypothesis 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outcome Hypothesis
Goal
Produce an evidence-grounded prediction of what business result will change, for whom, within a specific timeframe, and how leading and lagging indicators will prove or disprove it.
Treat "outcome hypothesis", "business outcome hypothesis", "value hypothesis", and "outcome statement" as equivalent requests.
When to Use
Use this skill to:
- Frame or sharpen an outcome for a project, initiative, or engagement.
- Convert a technical idea or deliverable-led proposal into a measurable beneficiary result.
- Assess whether an existing hypothesis is falsifiable, quantified, baselined, and traceable.
- Prepare an evidence-based starting point for an outcome conversation.
Do not use it to create a full project plan, write a decision record, produce a status update, or run evidence-free ideation.
Use requirements-author when the outcome is understood and the task is to create or govern a BRD or PRD. Use performance-slo-planner for production SLOs, capacity, latency budgets, and load-test planning.
When an AI or ML intervention materially affects people's access, eligibility, treatment, allocation, or opportunities, continue outcome framing here and initiate the RAI Planner as a separate assessment. AI or ML involvement alone does not trigger this route.
Modes
Resolve the mode before scoring:
create: Author a new or revised hypothesis from the available evidence.assess: Evaluate a supplied hypothesis without changing its facts, structure, or prose.
If the request is ambiguous, ask whether the user wants to create a hypothesis or assess an existing one. Assess mode requires the existing hypothesis or outcome document. A revised draft is a separate create or revision request after assessment.
Flow
Use the Outcome-Hypothesis CAUTION in the Outcome-Hypothesis section of ../../../instructions/shared/disclaimer-language.instructions.md as the only disclaimer source. That file and section are required before create or assess delivery. Load the CAUTION verbatim when rendering a create-mode document or delivering either mode's result; never store a second literal in this skill or its template. If the required file or section is missing, unreadable, or unavailable, state that the canonical CAUTION is unavailable. Do not fabricate, invent, or paraphrase a substitute. Stop before delivering a draft or assessment, persistence, or handoff, and name rerunning after the required file and section are accessible as the condition to resume.
What ships with it
2 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.
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 First seen · 208 lines · 103 tokens per session scan A 14238389c886
outcome-hypothesis is a skill published in the GitHub repository microsoft/hve-core (1,431 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 4,221 once invoked, about $0.0005 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 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…