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 rpi-implementgit 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/rpi-implement)<a href="https://agentmods.dev/skills/microsoft/hve-core/rpi-implement"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/rpi-implement.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 | $0.00032 | $0.01617 |
| Opus 5 | $0.00016 | $0.00809 |
| Sonnet 5 | $0.00006 | $0.00323 |
| Haiku 4.5 | $0.00003 | $0.00162 |
Grade A, and why
rpi-implement 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RPI Implement
Goal
Deliver the approved outcome using the current plan and phase details as evidence. Keep task completion, implementation evidence, plan maintenance, and validation trustworthy for the caller.
Flow
- Resolve the exact plan at
.copilot-tracking/plans/{{YYYY-MM-DD}}/{{task_slug}}-plan.md, related plan details, and declared invocation scope: the full plan, onePxxphase, or onePxx-Txxtask. The declared scope limits completion claims and active implementation. - Create or continue
.copilot-tracking/changes/{{YYYY-MM-DD}}/{{task_slug}}-changes.mdusing templates/changes-log.md. Record material evidence under descriptive headings tied to plan areas or markers, not per-entry formal IDs. - Before substantive source edits or implementation, update the plan checklist, changes log, and any related state tracking artifacts.
- Send the implementation opening defined in references/implementation.md.
- Start with the first unchecked dependency-ready plan item in declared scope, then execute eligible items in plan order.
- Delegate only a whole
Pxxphase when it is in declared scope, dependency-ready, independent, parallelizable, and write-disjoint. Its scope, dependencies, disjoint write boundary, and expected evidence return must be clear. The primary implementation agent executes individualPxx-Txxtasks, consumes phase returns, and retains plan order, plan and changes-record reconciliation, implementation-time plan updates, and completion markers. - When stated task completion evidence exists, immediately check the completed
Pxx-Txxmarker in scope. Check aPxxphase immediately only when that phase is in scope and completion evidence exists for every task in the phase. Do not check markers outside declared scope.
- Delegate only a whole
- When declared scope finishes, ensure its changes, blockers, completion markers, remaining work, and validation state are current. Report active plan markers outside the scope as remaining work. Report full-plan completion only when the full plan was declared and all of its markers have completion evidence.
- Classify new implementation information using references/implementation.md: retain ordinary local judgment, apply immediately relevant current-state updates that preserve approved intent, record unrelated work as follow-up-only, and treat a discovery as material only when it requires a new user decision or planning reconsideration.
- Ask for the smallest decision-critical user input only when available evidence cannot support a responsible user-owned decision. Persist the result in current planning state and the changes record. If the accepted plan must change, pause only affected dependent work and return the current evidence to planning. The confirmed user decision remains authoritative; do not run another critique.
- Run validation expected by the plan or changed behavior after the approved source or correction batch is complete. Record checks, results, and explicit skip reasons without treating validation alone as permission to resume paused dependent work.
- Before handing a full-plan or review-ready scope to Review, reconcile plan markers, phase details, completed-work evidence, handoff prose, blockers, remaining work, follow-up items, and validation state.
- Return the current implementation result to the caller using the return contract below.
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.
- 3d ago First seen · 77 lines · 32 tokens per session scan A f66cd3d89ba5
rpi-implement is a skill published in the GitHub repository microsoft/hve-core (1,436 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,617 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.