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 vscode-playwrightgit 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/vscode-playwright)<a href="https://agentmods.dev/skills/microsoft/hve-core/vscode-playwright"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/vscode-playwright/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/microsoft/hve-core/vscode-playwright"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/vscode-playwright.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 177 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00034 | $0.03885 |
| Opus 5.5 | $0.00014 | $0.01554 |
| Sonnet 5.5 | $0.00007 | $0.00777 |
| Haiku 4.5 | $0.00003 | $0.00388 |
Grade C, and why
vscode-playwright scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$VSCODE_SERVE_DIR" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
compatibility: 'VS Code screenshots require its CLI. Scripted capture requires uv, Python 3.11+, and Chromium; animation encoding also requires FFmpeg. Interactive capture requires Playwright MCP tools and curl' How it starts
The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VS Code and Browser Capture Skill
Captures VS Code editor views, code walkthroughs, and Copilot Chat examples, and records self-contained browser animation scenes as silent WebM clips.
Overview
This skill provides a complete workflow for capturing high-quality VS Code screenshots suitable for embedding in slide decks, documentation, and other visual media. It handles server lifecycle management, viewport configuration, UI cleanup, and screenshot validation.
Two paths share the same constraints. Prefer the scripted path for any repeatable or unattended capture, including CI. Use the interactive Playwright MCP path for exploratory or one-off captures.
Scripted Capture
scripts/capture_vscode.py runs a YAML capture plan headless: it starts serve-web, applies capture settings, opens each file in Monaco, measures the rendered font, and writes one screenshot per capture. It drives Playwright directly, so it needs no MCP server and runs on a CI runner.
uv sync
uv run playwright install --with-deps chromium
uv run python scripts/capture_vscode.py --plan capture-plan.yml --workspace /path/to/repo
A plan names each capture's id, a workspace-relative file, and an output path relative to the plan directory, or to --output-root when given. An id is one filename-safe token of letters, digits, ., _, or -. An output is a relative .png path with / separators and no .., and the script refuses to write outside the output root or through a symlink:
resolution: 1920x1080
min_font_pt: 18
font_size: 26
theme: Default Dark Modern
captures:
- id: marketplace-catalog
file: .github/plugin/marketplace.json
output: frames/marketplace-catalog.png
The script exits 0 only when every capture was written and met min_font_pt, and prints one JSON result on its last stdout line with each capture's measured rendered_font_size_pt, zoom, and source_resolution. A failed capture also writes debug-<id>.png. It rejects markdown targets at plan validation and fails when the dark theme does not apply, so a clashing light capture cannot pass. When piping its output in CI, run the step under shell: bash so pipefail preserves the exit code.
What ships with it
10 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.
- pyproject.toml 522 B
- scripts/capture_vscode.py 20 KB runs code
- scripts/record_browser_video.py 7.6 KB runs code
- tests/corpus/not-a-mapping.yml 16 B
- tests/corpus/traversal-plan.yml 102 B
- tests/corpus/valid-plan.yml 200 B
- tests/fuzz_harness.py 2.3 KB runs code
- tests/test_capture_vscode.py 6.0 KB runs code
- tests/test_record_browser_video.py 12 KB runs code
- uv.lock 104 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.
- yesterday Changed ce43b4f86cc8
- 29d ago Changed · +31 lines · +4 tokens per session d951bbc7aa97
- 1mo ago Changed · +27 lines · +9 tokens per session 09ba6652f211
- 2mo ago First seen · 192 lines · 21 tokens per session scan C ca0f37753379
vscode-playwright is a skill published in the GitHub repository microsoft/hve-core (1,606 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 3,885 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
vscode-playwright compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vscode-playwrightmicrosoft/hve-core | Skill | 1.6k | today | MIT | C | 34 | Claude Code, Codex |
| interactive-loginyc-software/qm | Skill | 16k | today | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 11d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | 2d ago | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | today | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.9k | today | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 911 | 2d ago | MIT | A | 40 | Claude Code |