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 instructions/pplancq/copilot-instructions/a11ygit clone --depth 1 https://github.com/pplancq/copilot-instructionsWrote 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/instructions/pplancq/copilot-instructions/a11y)<a href="https://agentmods.dev/instructions/pplancq/copilot-instructions/a11y"><img src="https://agentmods.dev/badge/instructions/pplancq/copilot-instructions/a11y.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 | $0.05184 | $0.05184 |
| Opus 5 | $0.02592 | $0.02592 |
| Sonnet 5 | $0.01037 | $0.01037 |
| Haiku 4.5 | $0.00518 | $0.00518 |
Grade A, and why
copilot-instructions a11y.instructions.md 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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions for accessibility
- In addition to WCAG 2.2, you must also comply with the French RGAA (Référentiel Général d’Amélioration de l’Accessibilité) version 4. Always fetch and review the latest RGAA 4 criteria and tests available at https://accessibilite.numerique.gouv.fr before answering or validating accessibility requirements. This ensures alignment with the most up-to-date French accessibility standards.
- Code must conform to WCAG 2.2 Level AA.
- Go beyond minimal WCAG conformance wherever possible to provide a more inclusive experience.
- Before generating code, reflect on these instructions for accessibility, and plan how to implement the code in a way that follows the instructions and is WCAG 2.2 compliant.
- After generating code, review it against WCAG 2.2 and these instructions. Iterate on the code until it is accessible.
- Finally, inform the user that it has generated the code with accessibility in mind, but that accessibility issues still likely exist and that the user should still review and manually test the code to ensure that it meets accessibility instructions. Suggest running the code against tools like Accessibility Insights. Do not explain the accessibility features unless asked. Keep verbosity to a minimum.
Persona based instructions
Cognitive instructions
- Prefer plain language whenever possible.
- Use consistent page structure (landmarks) across the application.
- Ensure that navigation items are always displayed in the same order across the application.
- Keep the interface clean and simple - reduce unnecessary distractions.
Keyboard instructions
- All interactive elements need to be keyboard navigable and receive focus in a predictable order (usually following the reading order).
- Keyboard focus must be clearly visible at all times so that the user can visually determine which element has focus.
- All interactive elements need to be keyboard operable. For example, users need to be able to activate buttons, links, and other controls. Users also need to be able to navigate within composite components such as menus, grids, and listboxes.
- Static (non-interactive) elements, should not be in the tab order. These elements should not have a
tabindexattribute.- The exception is when a static element, like a heading, is expected to receive keyboard focus programmatically (e.g., via
element.focus()), in which case it should have atabindex="-1"attribute.
- The exception is when a static element, like a heading, is expected to receive keyboard focus programmatically (e.g., via
- Hidden elements must not be keyboard focusable.
- Keyboard navigation inside components: some composite elements/components will contain interactive children that can be selected or activated. Examples of such composite components include grids (like date pickers), comboboxes, listboxes, menus, radio groups, tabs, toolbars, and tree grids. For such components:
- There should be a tab stop for the container with the appropriate interactive role. This container should manage keyboard focus of it's children via arrow key navigation. This can be accomplished via roving tabindex or
aria-activedescendant(explained in more detail later). - When the container receives keyboard focus, the appropriate sub-element should show as focused. This behavior depends on context. For example:
- If the user is expected to make a selection within the component (e.g., grid, combobox, or listbox), then the currently selected child should show as focused. Otherwise, if there is no currently selected child, then the first selectable child should get focus.
- Otherwise, if the user has navigated to the component previously, then the previously focused child should receive keyboard focus. Otherwise, the first interactive child should receive focus.
- There should be a tab stop for the container with the appropriate interactive role. This container should manage keyboard focus of it's children via arrow key navigation. This can be accomplished via roving tabindex or
- Users should be provided with a mechanism to skip repeated blocks of content (such as the site header/navigation).
- Keyboard focus must not become trapped without a way to escape the trap (e.g., by pressing the escape key to close a dialog).
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 · 348 lines · 5,184 tokens per session scan A d513cc679d92
copilot-instructions a11y.instructions.md is an instructions file published in the GitHub repository pplancq/copilot-instructions (4 stars, last pushed 7mo ago), licensed MIT. It adds 5,184 tokens to every session, about $0.0259 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.