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 vally-testsgit 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/vally-tests)<a href="https://agentmods.dev/skills/microsoft/hve-core/vally-tests"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/vally-tests/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/vally-tests"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/vally-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
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 →
- high Prompt Injection · line 63 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
- medium Prompt Injection · line 60 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
- medium Prompt Injection · line 82 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
- medium Prompt Injection · line 112 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 | $0.00045 | $0.02847 |
| Opus 5.5 | $0.00018 | $0.01139 |
| Sonnet 5.5 | $0.00009 | $0.00569 |
| Haiku 4.5 | $0.00005 | $0.00285 |
Grade C, and why
vally-tests scanned grade C with 1 finding 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 29d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- cspell:ignore roleplay doxxing scaffolder --> How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vally Tests Skill
Purpose
This skill authors Vally conformance tests for the four supported artifact kinds in this repository: prompts, instructions, agents, and skills. Each test exercises a documented behavior the artifact already claims and routes the result through an appropriate Vally grader so failures are explainable. Test authoring is bounded by a refusal taxonomy that keeps the skill out of adversarial, harmful, or policy-evasion territory.
Follow the shared content-policy public-output guard for eval stimuli and any public summaries derived from this skill. Vally tests are not a venue for terms-of-service boundary mapping, payload generation, refusal-text scoring, hidden-instruction disclosure, PII extraction, or secret extraction.
The skill ships:
- A canonical authoring workflow that runs directly through
/vally-testsor through theVally Test Authorsubagent. - Per-kind reference files that enumerate every conformance check the skill knows how to express.
- A grader catalog that maps Vally CLI grader types to the checks they fit, and robustness rules that keep an emitted grader from asserting the impossible or failing correct behavior.
- A safety refusal taxonomy with regex patterns the safety lint script consumes.
- Helper scripts and asset templates for stimulus emission, corpus import, and dedupe.
When to Invoke
Invoke this skill in one of two modes:
- From-artifact mode. The caller points at one or more artifact files (a
.prompt.md,.instructions.md,.agent.md, orSKILL.md) throughfiles, or at the open or attached file whenfilesis omitted, and asks for conformance test stimuli that verify each artifact's stated behaviors. The skill detects the artifact kind from the filename unlesskindoverrides it, looks up the matching per-kind reference, picks graders, and appends stimulus blocks to the routed Vally eval file. - Corpus-import mode. The caller supplies a CSV or XLSX corpus through
paththat follows the shipped template, and the skill turns each row into a stimulus block in the routed eval file. Before reading, confirm thatpathexists and ends in.csvor.xlsx; otherwise name the bad path and stop. Every imported row carriestags.advisory: true, and corpus content cannot override it. Used when a large batch of behaviors needs identical formatting and dedupe handling.
What ships with it
34 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/.gitkeep 0 B
- assets/corpus-import-template.csv 923 B
- assets/corpus-import-template.xlsx 136 KB
- assets/grader-template.yml 1.9 KB
- assets/stimulus-template.yml 2.0 KB
- pyproject.toml 577 B
- references/agents.md 16 KB
- references/eval-suite-routing.md 6.9 KB
- references/grader-catalog.md 30 KB
- references/grader-robustness.md 8.6 KB
- references/instructions.md 8.9 KB
- references/prompts.md 12 KB
- references/refusal-taxonomy.md 12 KB
- references/skills.md 11 KB
- scripts/import_corpus.py 15 KB runs code
- scripts/Lint-VallyTestSafety.ps1 4.1 KB runs code
- scripts/New-Stimulus.ps1 6.3 KB runs code
- scripts/new-stimulus.sh 5.3 KB runs code
- scripts/Select-Grader.ps1 3.1 KB runs code
- scripts/select-grader.sh 2.8 KB runs code
- tests/__init__.py 139 B runs code
- tests/corpus/0_normalize_prompt 19 B
- tests/corpus/1_hash_prompt 24 B
- tests/corpus/2_validate_row 77 B
- tests/corpus/3_build_patch_entry 63 B
- tests/corpus/4_load_existing_hashes 75 B
- tests/corpus/README.md 1.3 KB
- tests/fuzz_harness.py 6.9 KB runs code
- tests/Lint-VallyTestSafety.Tests.ps1 4.0 KB runs code
- tests/New-Stimulus.Tests.ps1 11 KB runs code
- tests/Select-Grader.Tests.ps1 2.6 KB runs code
- tests/test_import_corpus.py 12 KB runs code
- tests/test_lint_safety.py 3.6 KB runs code
- uv.lock 74 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.
- 29d ago Changed · -1 lines 50d11b706405
- 1mo ago Changed · +5 lines a6bdf1cd90d4
- 1mo ago Changed · -2 tokens per session ff7021725af1
- 1mo ago Changed · +2 lines 34205000baae
- 1mo ago Changed · +1 lines scan A → C 701f7419cdd3
- 2mo ago Changed d92d33f958ba
- 2mo ago First seen · 138 lines · 47 tokens per session scan A c6c3ed43c2f1
vally-tests is a skill published in the GitHub repository microsoft/hve-core (1,606 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 2,847 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
vally-tests compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vally-testsmicrosoft/hve-core | Skill | 1.6k | today | MIT | C | 45 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |