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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/microsoft/hve-corenpx agentmods add skills/microsoft/hve-core/accessibilityWrote 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/accessibility)<a href="https://agentmods.dev/skills/microsoft/hve-core/accessibility"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/accessibility/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/accessibility"><img src="https://agentmods.dev/badge/skills/microsoft/hve-core/accessibility.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, 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 Excessive Agency · line 426 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- 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 62 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 248 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 253 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 | $0.00047 | $0.09002 |
| Opus 5.5 | $0.00019 | $0.03601 |
| Sonnet 5.5 | $0.00009 | $0.01800 |
| Haiku 4.5 | $0.00005 | $0.00900 |
Grade A, and why
accessibility 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 9d 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 — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility — Skill Entry
This skill is the canonical accessibility reference contract for HVE Core. Agents and instructions invoke this skill by name and rely on it to own framework reference resolution, phase guidance resolution, and the scanner CLI entrypoint.
Framework references
- WCAG 2.2
- ARIA Authoring Practices Guide
- Cognitive Accessibility Guidance
- Section 508
- EN 301 549
- Graphics ARIA and SVG-AAM
Assessment reference (cross-cutting, not a conformance framework):
- Assistive-technology announcement model — read this when deciding the announcement-class criteria (WCAG 1.3.1, 4.1.2, 4.1.3): what a screen-reader user should hear, and how to decide it with an accessibility-tree assertion or a manual AT pass.
Accessibility Planner workflow
The Accessibility Planner runs six phases, each keyed to a state id:
- Phase 1 — Discovery (
discovery) - Phase 2 — Framework Selection (
framework-selection) - Phase 3 — Standards Mapping (
standards-mapping) - Phase 4 — Plan Risk Assessment (
plan-risk-assessment) - Phase 5 — Impact and Evidence (
impact-evidence) - Phase 6 — Backlog Handoff (
backlog-handoff)
Phase reference index
- Phase 1 — Discovery: capture-coaching.md — read this when running exploration-first capture questioning.
- Phase 2 — Framework Selection: framework-selection.md — read this when choosing which frameworks and conformance level apply.
- Phase 3 — Standards Mapping: walk the framework references roll-up tables to emit
controlMappings; consumed by Phase 5. No dedicated file — mapping is driven by the framework roll-ups. - Phase 4 — Plan Risk Assessment: capture-coaching.md governs the questioning posture when escalation triggers reopen scoping; tier criteria are applied per the Accessibility Planner identity instructions and recorded as
riskClassification.tier. No dedicated file — the accessibility risk surface is narrow enough to stay inline. - Phase 5 — Impact and Evidence: impact-assessment.md — read this when building the evidence register, tradeoff log, and seed work-items.
- Phase 6 — Backlog Handoff: backlog-handoff.md — read this when rendering work items and validating handoff gates.
What ships with it
60 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 891 B
- references/ci/accessibility-coverage.workflow-template.yml 23 KB
- references/ci/act-rule-format.md 5.4 KB
- references/ci/probe-spec-parity.md 15 KB
- references/design-intent/record-contract.md 9.6 KB
- references/evidence-composition-adoption.md 8.6 KB
- references/examples/evidence/asset-journeys.json 364 B
- references/examples/evidence/evidence-scope.json 396 B
- references/examples/evidence/requirement-methods.json 683 B
- references/examples/evidence/run-context.json 994 B
- references/examples/evidence/state-proofs.json 367 B
- references/frameworks/aria-apg.md 89 KB
- references/frameworks/at-announcement-model.md 12 KB
- references/frameworks/coga.md 81 KB
- references/frameworks/en-301-549.md 154 KB
- references/frameworks/graphics-aria-svg-aam.md 6.9 KB
- references/frameworks/section-508.md 37 KB
- references/frameworks/wcag-22.md 66 KB
- references/phases/backlog-handoff.md 26 KB
- references/phases/capture-coaching.md 11 KB
- references/phases/framework-selection.md 8.3 KB
- references/phases/impact-assessment.md 19 KB
- scripts/runtime_a11y/__init__.py 154 B runs code
- scripts/runtime_a11y/__main__.py 89 KB runs code
- scripts/runtime_a11y/_config.py 8.1 KB runs code
- scripts/runtime_a11y/_errors.py 1.3 KB runs code
- scripts/runtime_a11y/_intent.py 33 KB runs code
- scripts/runtime_a11y/_projection.py 6.9 KB runs code
- scripts/runtime_a11y/.npmrc 923 B
- scripts/runtime_a11y/aria-at-catalog.json 21 KB
- scripts/runtime_a11y/aria-at-catalog.schema.json 5.7 KB
- scripts/runtime_a11y/composition-summary.schema.json 655 B
- scripts/runtime_a11y/config-schema.json 12 KB
- scripts/runtime_a11y/criteria-catalog.aria-apg.json 1.6 KB
- scripts/runtime_a11y/criteria-catalog.defect-scan.json 2.0 KB
- scripts/runtime_a11y/criteria-catalog.schema.json 5.1 KB
- scripts/runtime_a11y/criteria-catalog.wcag-22.json 9.6 KB
- scripts/runtime_a11y/design-intent.schema.json 10 KB
- scripts/runtime_a11y/evidence_bundle/__init__.py 494 B runs code
- scripts/runtime_a11y/evidence_bundle/_adapters.py 15 KB runs code
- scripts/runtime_a11y/evidence_bundle/_canonical.py 1.3 KB runs code
- scripts/runtime_a11y/evidence_bundle/_compose.py 32 KB runs code
- scripts/runtime_a11y/evidence_bundle/_validate.py 5.8 KB runs code
- scripts/runtime_a11y/evidence-bundle.schema.json 11 KB
- scripts/runtime_a11y/evidence-scope.schema.json 2.2 KB
- scripts/runtime_a11y/evidence-source.schema.json 3.7 KB
- scripts/runtime_a11y/matrix/__init__.py 643 B runs code
- scripts/runtime_a11y/matrix/_aria_at.py 11 KB runs code
- scripts/runtime_a11y/matrix/_artifacts.py 6.6 KB runs code
- scripts/runtime_a11y/matrix/_build.py 1.6 KB runs code
- scripts/runtime_a11y/matrix/_catalog.py 7.3 KB runs code
- scripts/runtime_a11y/matrix/_coverage.py 3.0 KB runs code
- scripts/runtime_a11y/matrix/_ingest_assessor.py 4.4 KB runs code
- scripts/runtime_a11y/matrix/_ingest_planner.py 5.6 KB runs code
- scripts/runtime_a11y/matrix/_ingest_probe.py 2.7 KB runs code
- scripts/runtime_a11y/matrix/_ingest_reports.py 3.5 KB runs code
- scripts/runtime_a11y/matrix/_merge.py 3.0 KB runs code
- scripts/runtime_a11y/matrix/_model.py 5.8 KB runs code
- scripts/runtime_a11y/matrix/_provenance.py 4.6 KB runs code
- scripts/runtime_a11y/matrix/_render_earl.py 7.3 KB runs code
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.
- 9d ago Changed c9a3fbc06f2c
- 25d ago Changed 83283a35a15b
- 28d ago Changed · +50 lines 614c2f26e792
- 1mo ago Changed · +17 lines 76c873cdd05e
- 1mo ago First seen · 418 lines · 47 tokens per session scan A 213b5a4833bc
accessibility is a skill published in the GitHub repository microsoft/hve-core (1,529 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 9,002 once invoked, about $0.0002 per session on Opus 5.5. 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
build-ui-components-and-systems
A guide for building reusable UI components and design systems: shared visual rules, component interfaces, behavior, accessibility requirements, documentation, packaging, and version management. A design system is a maintained set of parts and rules that multiple screens or products can share.