v3.0.0

Accessibility Agents v3.0.0

This release captures all changes from v2.5 to v3.0.0.

Compare: v2.5...v3.0.0

Release Scope (v2.5 -> v3.0.0)

• 375 files changed
• 17,825 insertions, 283 deletions
• Major delivery areas: lifecycle hooks, VS Code 1.110 integration, citation authority, browser verification, plugin packaging, and release management docs

Highlights

1) Cross-Platform Lifecycle Hooks (Phase 4)

• Added Python hook scripts in .github/hooks/scripts/ for SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, and SessionEnd
• Added consolidated hook configs for both Copilot and Claude flows:
  • .github/hooks/hooks-consolidated.jsonn - .claude/hooks/hooks-consolidated.jsonn- Implemented edit-gate enforcement for web UI files until accessibility review is completed
• Added setup and troubleshooting docs:
  • docs/guides/hooks-guide.mdn - docs/guides/hooks-troubleshooting.mdn - docs/HOOKS-CROSS-PLATFORM-STRATEGY.md`n

2) VS Code 1.110 Integration (Phases 5 and 6)

• Added Agent Debug Panel guidance and troubleshooting:
  • docs/guides/agent-debug-panel.mdn - updates in README.md, docs/hooks-guide.md, and docs/getting-started.mdn- Added session forking (/fork) guidance to orchestrator workflows
• Added getDiagnostics integration to specialist agents for lint-aware accessibility audits
• Added docs for:
  • OS notifications during long audits
  • AI co-author attribution (git.addAICoAuthor)
  • inline chat continuity
  • collapsible terminal tool output
  • custom thinking phrases
• Added built-in VS Code accessibility skill comparison:
  • docs/guides/vscode-builtin-skill-comparison.md`n

3) Citation Authority and Source Currency (Phase 1B)

• Added authoritative source citations across the agent ecosystem
• Added source registry and automated verification workflow:
  • .github/agents/SOURCE_REGISTRY.jsonn - .github/workflows/verify-sources.ymln

4) Agentic Browser Verification (Phase 3)

• Added browser-assisted validation design and testing guides:
  • docs/AGENTIC-BROWSER-TOOLS.mdn - docs/BROWSER-TOOLS-TESTING.mdn- Expanded remediation workflows in web-accessibility-wizard and web-issue-fixer`n

5) Marketplace and Prompt Ecosystem Expansion

• Added marketplace packaging metadata and submission support
• Added large prompt coverage expansion under .github/prompts/ for agent-aligned workflows

Notable Documentation Updates

• CHANGELOG.md now includes complete phased v3.0 history
• prd.md updated with completed phase status and release management tracking
• README.md expanded with current system requirements and troubleshooting
• CONTRIBUTING.md updated with version-currency testing requirements

Migration Notes from v2.5

• If you are on v2.5, update to latest toolchain versions first, then pull v3.0.0
• Hook-based enforcement is now part of normal web UI workflows
• Use the Agent Debug Panel in VS Code 1.110+ for visibility into hooks, tools, and agent loading

Full Commit Range

Recent high-impact commits in this range include:

• de47245 v3.0.0 release integration
• 77a92e8 consolidation into prd.md and migration audit
• ce4179a marketplace packaging and submission prep
• 4dfbdd9 autonomous browser verification implementation
• �511e08 context compaction and custom-skills guidance
• ac9d49 authoritative source citations rollout

Thanks to all contributors helping make accessibility workflows more reliable and easier to adopt.

v2.5: The Community Milestone Release

Every feature in v2.5 was requested, debated, or built by the community. This is the moment Accessibility Agents became something the community owns.

Highlights

• NVDA Addon Development Specialist -- The most-requested agent of the year. Build, debug, package, and publish NVDA addons with AI grounded in the official NVDA source code.
• Text Quality Reviewer -- Catches invisible-to-sighted text quality issues that break the screen reader experience: template variables in alt text, code syntax as labels, empty accessible names.
• Source Citation Policy -- No source, no claim. Every agent now cites WCAG specs, ARIA APG, vendor docs, or explicitly flags advice as experience-based. A weekly automation checks freshness.
• wxPython Screen Reader Key Event Pitfalls -- Documented cross-platform issue where screen readers intercept keyboard events before they reach the application.

By the Numbers

• 57 agents (up from 55)
• 17 skills (up from 16)
• 54 prompts
• 5 platforms
• Source citations now enforced across all agents
• Automated freshness checks via GitHub Actions

Install or Update

macOS / Linux:

curl -fsSL https://raw.githubusercontent.com/Community-Access/accessibility-agents/main/update.sh | bash

Windows (PowerShell):

irm https://raw.githubusercontent.com/Community-Access/accessibility-agents/main/update.ps1 | iex

Full changelog: v2.1.1...v2.5

Accessibility Agents v2.1.1

Accessibility Agents v2.1.1

Builds on v2.1 — Claude Code plugin with three-hook enforcement gate.

This patch release adds the Claude Code plugin packaging system and a three-hook enforcement gate that automatically delegates to the accessibility-lead agent before any UI code can be written or edited.

---

What Is New Since v2.1

Claude Code Plugin System

The agents are now packaged as a first-class Claude Code plugin (accessibility-agents@community-access), registered in the plugin cache and discoverable by Claude Code automatically.

• Plugin registration -- Installs to ~/.claude/plugins/cache/community-access/accessibility-agents/ with plugin.json manifest, CLAUDE.md instructions, and all 55 agent files.
• One-command install -- curl -fsSL ... | bash registers the plugin, copies agents, and sets up hooks in a single step.
• Clean uninstall -- Removes plugin registration, cache, hooks, and settings entries without touching user configuration.

Three-Hook Enforcement Gate

A proactive accessibility enforcement system that activates automatically in any web project:

1. UserPromptSubmit (a11y-team-eval.sh) -- Detects web projects and injects the delegation instruction into every prompt. No manual activation needed.
2. PreToolUse (a11y-enforce-edit.sh) -- Blocks Edit/Write to UI files (.html, .jsx, .tsx, .vue, .svelte, .css, .leaf, .ejs, .erb, .hbs) until accessibility-lead has been consulted. Returns permissionDecision: "deny".
3. PostToolUse (a11y-mark-reviewed.sh) -- Unlocks the edit gate after accessibility-lead completes its review via session markers.

Windows PowerShell Support

Full three-hook enforcement added to the PowerShell installer (install.ps1) and uninstaller (uninstall.ps1) for Windows users.

Installer Fixes

• Bash 3 compatibility -- Fixed declare -A (associative array) usage that crashed on macOS default bash 3.2. Replaced with string-based dedup.
• Plugin key matching -- Uninstaller now matches both a11y-agent-team@* and accessibility-agents@* key formats for backward compatibility.
• Manifest guard -- Fixed add_manifest_entry: command not found when using the plugin install path.
• Agent sync -- All 55 agents (including 6 new developer team agents) now included in the plugin package.

Repository

• CODEOWNERS -- Added org maintainer ownership rules.

---

By the Numbers

Metric	v2.1	v2.1.1
Agents	55	55
Enforcement hooks	0	3
Plugin support	No	Yes
Platforms	5	5

Installation

macOS / Linux:

curl -fsSL https://raw.githubusercontent.com/Community-Access/accessibility-agents/main/install.sh | bash

Windows (PowerShell):

irm https://raw.githubusercontent.com/Community-Access/accessibility-agents/main/install.ps1 | iex

---

Free. MIT licensed. Built by and for the blind and low vision community.

Accessibility Agents v2.1

Accessibility Agents v2.1

55 agents. 17 skills. 54 prompts. 5 platforms. The Developer and Desktop Accessibility team has arrived.

This release expands the agent ecosystem with a complete Developer Tools team -- 6 new specialized agents for Python, wxPython, desktop accessibility, desktop testing, and accessibility tool building. It also adds the Scanner Bridge and Lighthouse Bridge agents for CI/CD integration, brings 3 new knowledge skills, and extends platform support to Codex CLI and Gemini CLI.

---

What Is New Since v2.0.0

Developer Tools Team (6 New Agents)

The biggest addition in v2.1 is a full developer tools team led by Developer Hub, an intelligent routing agent that connects you to the right specialist:

• Developer Hub -- Start here for any Python, wxPython, desktop app, or accessibility tool task. Routes to specialists automatically.
• Python Specialist -- Debugging, packaging (PyInstaller/Nuitka/cx_Freeze), testing (pytest/unittest), type checking, async patterns, and optimization.
• wxPython Specialist -- Sizer layouts, event handling, AUI framework, custom controls, threading, dialog design, and desktop accessibility.
• Desktop Accessibility Specialist -- Platform APIs (UI Automation, MSAA/IAccessible2, ATK/AT-SPI, NSAccessibility), screen reader Name/Role/Value/State, focus management, and high contrast support.
• Desktop A11y Testing Coach -- Testing with NVDA, JAWS, Narrator, VoiceOver, and Orca. Accessibility Insights for Windows, automated UIA testing, and keyboard-only testing flows.
• Accessibility Tool Builder -- Building scanning tools, rule engines, document parsers, report generators, severity scoring, and CI/CD integration for accessibility tooling.

CI/CD Scanner Integration (2 New Agents)

• Scanner Bridge -- Bridges GitHub Accessibility Scanner CI data into the agent ecosystem. Parses scanner-created issues, correlates with local scans, and tracks Copilot fix status.
• Lighthouse Bridge -- Bridges Lighthouse CI accessibility audit data. Score interpretation, weight-to-severity mapping, and score regression tracking.

Structured Accessibility Audit Modes

Three new rule sets provide structured audit frameworks with numbered checklists:

• WX-A11Y-001 through WX-A11Y-012 -- wxPython accessibility audit covering screen reader support, keyboard navigation, high contrast, focus management, custom controls, and platform-specific patterns.
• DTK-A11Y-001 through DTK-A11Y-012 -- Desktop accessibility audit covering platform API implementation, accessible control patterns, screen reader compatibility, and assistive technology integration.
• TST-A11Y-001 through TST-A11Y-010 -- Accessibility testing audit covering screen reader testing procedures, keyboard testing flows, automated testing setup, and test plan creation.

New Knowledge Skills (3 New)

• Python Development -- Python and wxPython development patterns, packaging, testing, wxPython sizers/events/threading, and cross-platform paths.
• GitHub A11y Scanner -- GitHub Accessibility Scanner detection, issue parsing, severity mapping, axe-core correlation, and Copilot fix tracking.
• Lighthouse Scanner -- Lighthouse CI accessibility audit detection, score interpretation, weight-to-severity mapping, and score regression tracking.

Platform Expansion (3 to 5)

• Codex CLI -- Full agent support via .codex/AGENTS.md for the OpenAI Codex CLI environment.
• Gemini CLI -- 63 accessibility skills exposed via Gemini extension files for geminicli.com discoverability.
• Existing platforms (Claude Code, GitHub Copilot, Claude Desktop MCP) continue with full feature parity.

Additional Improvements

• VS Code Chat Participant -- Scaffolded @a11y VS Code extension for Tier 2 integration (in preview).
• ARIA and Web Agent Hardening -- Strengthened all web agent rules against authoritative WCAG source documents.
• Landmark Rule Improvements -- Fixed landmark antipatterns discovered during site audit.
• Agent Naming Convention -- All agents renamed to Title Case with argument-hint and infer support.
• Security Hardening -- Hardened MCP server path validation and locked dependency versions.
• Installer Overhaul -- Comprehensive install/uninstall rewrite with manifest fallback support.
• CI/CD Workflow -- Updated manifest workflow to use PR-based approach for branch protection compatibility.
• Office Document Rules -- Fixed decorative image handling in alt text checks.
• Documentation -- Research sources attribution document, platform count updates, Codex CLI invocation syntax.

---

By the Numbers

Metric	v2.0.0	v2.1
Agents	47	55
Platforms	3	5
Knowledge skills	14	17
Prompts	52	54
Audit rule sets	--	3 (34 rules)
Agent teams	4	5

Installation

macOS / Linux:

curl -fsSL https://raw.githubusercontent.com/Community-Access/accessibility-agents/main/install.sh | bash

Windows (PowerShell):

irm https://raw.githubusercontent.com/Community-Access/accessibility-agents/main/install.ps1 | iex

Update existing installation:

# macOS / Linux
curl -fsSL https://raw.githubusercontent.com/Community-Access/accessibility-agents/main/update.sh | bash

# Windows
irm https://raw.githubusercontent.com/Community-Access/accessibility-agents/main/update.ps1 | iex

Links

• Website: https://community-access.github.io/
• Documentation: https://community-access.github.io/docs.html
• Getting Started: https://github.com/Community-Access/accessibility-agents/blob/main/docs/getting-started.md
• Contributing: https://github.com/Community-Access/accessibility-agents/blob/main/CONTRIBUTING.md

---

Free. MIT licensed. Built by and for the blind and low vision community.

Accessibility Agents v2.0.0

Accessibility Agents v2.0.0

47 agents. 3 platforms. 1 command to install. Built over a weekend by people who need it.

This release represents a complete rebuild of the project. What started as 6 accessibility agents for Claude Code on Friday, February 21 became 47 specialized agents across 4 teams and 3 platforms by Monday, February 24. The project moved from a personal repository to the Community Access GitHub organization and gained 9 contributors, 30 merged pull requests, and 360 changed files.

---

What Is New Since v1.0.0

Agents (6 to 47)

Web Accessibility (16 agents): accessibility-lead, aria-specialist, modal-specialist, contrast-master, keyboard-navigator, live-region-controller, forms-specialist, alt-text-headings, tables-data-specialist, link-checker, cognitive-accessibility, mobile-accessibility, design-system-auditor, web-accessibility-wizard, testing-coach, wcag-guide

Document Scanning (9 agents): word-accessibility, excel-accessibility, powerpoint-accessibility, pdf-accessibility, epub-accessibility, office-scan-config, pdf-scan-config, epub-scan-config, document-accessibility-wizard

Markdown Documentation (3 agents): markdown-a11y-assistant, markdown-scanner, markdown-fixer

GitHub Workflows (11 agents): github-hub, nexus, daily-briefing, pr-review, issue-tracker, analytics, insiders-a11y-tracker, repo-admin, team-manager, contributions-hub, template-builder, repo-manager

Sub-agents (10): cross-document-analyzer, cross-page-analyzer, document-inventory, document-csv-reporter, web-csv-reporter, markdown-csv-reporter, web-issue-fixer, office-scan-config, pdf-scan-config, epub-scan-config

Platform Support (1 to 3)

• Claude Code — markdown-based agents in .claude/agents/
• GitHub Copilot — agents and workspace instructions in .github/agents/
• Claude Desktop — MCP extension with 11 tools and 6 prompts

14 Shared Knowledge Modules

Accessibility rules, framework patterns (React, Vue, Angular, Svelte, Tailwind), cognitive accessibility, mobile accessibility, document scanning, report generation, VPAT formatting, severity scoring, help URL references, GitHub workflow standards, design system auditing, and markdown accessibility.

52 Pre-Built Prompts

• 6 web audit prompts
• 10 document audit prompts
• 31 GitHub workflow prompts
• 5 markdown audit prompts

Document Scanning

• Microsoft Word, Excel, and PowerPoint scanning with 46 built-in rules
• PDF scanning per PDF/UA and Matterhorn Protocol with 56 built-in rules
• EPUB accessibility scanning
• VPAT 2.5 compliance report generation
• CSV export with help documentation links
• Scan configuration profiles (strict, moderate, minimal)

Multi-Agent Reliability Engineering

• Hooks removed entirely
• Structured output contracts added to all orchestrator and sub-agent files
• Handoff transparency sections added to all custom prompts
• Multi-agent reliability instructions shared across both platforms

Security Hardening

• 34 security findings resolved
• Path traversal prevention in MCP tools
• Python source injection prevention
• ZIP bomb protection (200MB limit)
• ZIP64 archive detection
• Case-insensitive bypass prevention
• Input validation at all call sites

Installer Improvements

• One-command install on macOS, Linux, and Windows
• Non-destructive — never overwrites existing files
• Manifest-based tracking of installed files
• Daily auto-update system
• One-command uninstall
• Safe update that only touches manifest-tracked files

Organization Move

• Repository moved from taylorarndt/a11y-agent-team to Community-Access/accessibility-agents
• All internal references updated
• Dedicated website at https://community-access.github.io/

---

By the Numbers

Metric	v1.0.0	v2.0.0
Agents	6	47
Platforms	1	3
Knowledge modules	0	14
Prompts	0	52
Document scanning rules	0	102
Contributors	1	9
Merged PRs	0	30
Files changed	—	360
Lines added	—	73,988

Installation

macOS / Linux:

curl -fsSL https://raw.githubusercontent.com/Community-Access/accessibility-agents/main/install.sh | bash

Windows (PowerShell):

irm https://raw.githubusercontent.com/Community-Access/accessibility-agents/main/install.ps1 | iex

Contributors

Taylor Arndt, Michael Babcock, Jeff Bishop, Clint Covington, Michael Doise, Doug Geoffray, Maria Lamardo, Roberto Perez, and Megan Rogge.

Links

• Website: https://community-access.github.io/
• Getting Started: https://github.com/Community-Access/accessibility-agents/blob/main/docs/getting-started.md
• Contributing: https://github.com/Community-Access/accessibility-agents/blob/main/CONTRIBUTING.md

---

Free. MIT licensed. Built by and for the blind and low vision community.

v1.0.0 -- A11y Agent Team

A11y Agent Team v1.0.0

Accessibility review tools for Claude Code and Claude Desktop. Built by a screen reader user who got tired of AI tools forgetting accessibility.

Claude Code (agents + hooks)

Clone the repo and run the install script. See the README for full setup instructions.

Claude Desktop (.mcpb extension)

Download a11y-agent-team.mcpb below and double-click it to install in Claude Desktop.

Tools included:

• check_contrast -- Calculate WCAG contrast ratios between two hex colors
• get_accessibility_guidelines -- Get WCAG AA guidelines for modals, tabs, accordions, comboboxes, carousels, forms, live regions, navigation, and general best practices

Prompts included:

• Full Accessibility Audit -- Comprehensive WCAG 2.1 AA review
• ARIA Review -- ARIA roles, states, and properties
• Modal/Dialog Review -- Focus trapping, return, escape behavior
• Color Contrast Review -- Visual accessibility and Tailwind checks
• Keyboard Navigation Review -- Tab order and focus management
• Live Region Review -- Screen reader announcements for dynamic content

Updating

Claude Code: If you installed with auto-updates enabled, updates happen automatically. Otherwise run bash update.sh or powershell -File update.ps1.

Claude Desktop: Download the latest .mcpb from this Releases page and double-click to update. Watch this repo for release notifications. We have submitted to the Anthropic Connectors Directory for automatic updates.

MIT License