tokensagents .COM
Install

Installed in about ten minutes.

Install is a folder copy. The skills are plain Markdown on the open Agent Skills standard, so once they are in place Claude fires them on matching work without being asked. In any other agent you point its rules or context at the same folder. Here is each path.

Install the skills

Claude Code, for repo work

  1. Unzip the two skill files.

    Each skill ships as a .skill file, which is a zip of the skill folder. You get ada-visual.skill and ada-aria.skill with your license.

  2. Put each skill folder in your skills directory.

    Personal skills live in ~/.claude/skills/ and load in every project. Project skills live in .claude/skills/ and ship with one repo. Either works. 

    mkdir -p ~/.claude/skills
unzip ada-visual.skill -d ~/.claude/skills/
unzip ada-aria.skill  -d ~/.claude/skills/

    You should end up with ~/.claude/skills/ada-visual/SKILL.md and ~/.claude/skills/ada-aria/SKILL.md. If your unzip left the files loose, move each into a folder named for the skill. The folder name is the skill name.

  3. Confirm they loaded.

    Both skills now show up in autocomplete, and you can invoke them directly with /ada-visual and /ada-aria. Claude Code picks up new skills during a session. If ~/.claude/skills/ did not exist before, restart Claude Code once so it watches the new directory.

  4. Point one at your code.

    Name a file or a pull request, or just ask for a review. The skill fires on matching work on its own, and you can always call it by name. 

    Run ada-aria on src/components/Dialog.tsx
Do a full accessibility review of this component at AA
Regulatory check only on this page

claude.ai and Cowork, for design review

Add the same two .skill files to your Claude account. Manage account skills from the skills settings on claude.ai, or from Customize in the Claude Desktop sidebar. Once they are enabled for your account, they are available in claude.ai and Cowork sessions and fire on matching work, the same as in Claude Code.

Any other agent

The skills are plain Markdown on the open Agent Skills standard, so they are not Claude-only. Point your tool's rules or context mechanism at the skill folder, a Cursor rules file, a Copilot instructions file, or an AGENTS.md reference, and the model reads the same rules. One difference: firing on their own is a Claude feature. In other agents you include the rules with the work rather than having them trigger automatically.

On the roadmap: an optional MCP server, run locally in your own environment, that serves the rules to any MCP-capable agent so non-Claude tools can query them like an API instead of loading the files by hand. It stays local. Nothing about the security story above changes.

What IT will ask

  • The files are static and plain text. Markdown skill files. Your team can read every rule before installing it.
  • They run inside your own environment. The pack has no server and makes no network calls of its own.
  • No telemetry, no vendor access. Nothing leaves your repo. We never see your code.
  • License enforcement lives with the merchant of record. Polar handles keys and renewal. The files do not phone home to check a license.

For a managed Claude Code fleet, the pack can be pinned and allowlisted so only an approved version runs. Enterprise licenses include the exact configuration snippet for your admin.

Requirements

  • An AI coding agent. Claude is the first-class path: it installs the skills and fires them on its own.
  • For repo fixes, that agent on the developer machine, Claude Code or your editor's agent.
  • Platforms the pack reviews: web, iOS, Android, desktop, and enterprise internal tools. Any stack, any framework. If it renders a UI, the rules apply.

Ready when your repo is.

Get the pack