Accessibility Agents 4.5.0

Accessibility Agents 4.5.0

Released: March 27, 2026 | 232 files changed | 96 agents updated across 3 platforms

---

What's New

4.5.0 is our biggest quality-of-life release yet. The installer now guides you through MCP server setup automatically. Document audit reports speak in plain language instead of XML schemas. The entire agent suite is aligned to VS Code 1.113. And the installation, update, and uninstall tooling has been comprehensively rebuilt for reliability.

---

Guided MCP Server Installation

Before 4.5.0: You installed the agents, then had to manually navigate to the MCP server directory, figure out which npm packages you needed, configure VS Code settings.json by hand, and hope it all worked.

Now: The installer walks you through everything.

Interactive Capability Planner

When the installer detects Node.js, it presents a guided setup menu:

1. Baseline scanning - Core accessibility scanning tools
2. Browser testing - Adds Playwright and axe-core for live page testing
3. PDF-heavy workflow - Adds pdf-lib for form conversion
4. Everything - All of the above plus deep PDF validation prerequisites
5. Custom - Pick exactly what you need

Automatic Dependency Management

• Node.js detection and installation - If Node.js 18+ is not found, the installer offers to install it via winget (Windows) or brew (macOS)
• npm dependencies - Core MCP server packages installed automatically (npm install --omit=dev)
• Playwright and Chromium - When browser testing is selected, Playwright is installed and Chromium is downloaded (npx playwright install chromium)
• pdf-lib - Installed when PDF form capabilities are selected
• Java and veraPDF - For deep PDF/UA validation, the installer offers to set up Java 21 JRE and veraPDF through platform package managers

VS Code Settings Auto-Configuration

The installer automatically merges the MCP server entry into your VS Code settings.json - for both Stable and Insiders editions if you have them. No manual JSON editing required.

Health Check and Readiness Dashboard

At the end of installation, you see a readiness report:

MCP Capability Readiness
  [x] Node.js 18+
  [x] npm
  [x] MCP core dependencies
  [x] Baseline PDF scan
  [!] Deep PDF validation (Java found, veraPDF missing)
  [x] Local health smoke test - READY
  [x] Playwright
  [x] Chromium
  [x] pdf-lib

The installer actually starts the MCP server on a test port and hits /health to confirm everything works before declaring success.

---

Completely Rebuilt Installation Tooling

The install, update, and uninstall scripts for both PowerShell and Bash have been rewritten from the ground up with a shared library architecture.

New Command-Line Flags

Every script now supports these flags (both install.ps1/install.sh, update.ps1/update.sh, and uninstall.ps1/uninstall.sh):

The following table lists flags available across all installer operations.

Flag	What it does
--dry-run	Simulates the operation, writes a JSON plan file, changes nothing
--check	Validates your environment and exits - useful for CI pre-flight
--yes	Auto-approves all prompts for non-interactive and CI use
--vscode-stable	Target only VS Code Stable
--vscode-insiders	Target only VS Code Insiders
--vscode-both	Target both editions
--summary=path	Override where the JSON summary file is written

The installer adds additional selection flags:

The following table lists installer-specific selection flags.

Flag	What it does
--copilot	Pre-select Copilot agent installation
--cli	Pre-select Copilot CLI installation
--codex	Pre-select Codex installation
--gemini	Pre-select Gemini CLI installation
--no-auto-update	Skip auto-update scheduling
--mcp-profile-stable / --mcp-profile-insiders / --mcp-profile-both	Control which VS Code editions get MCP settings

Machine-Readable Output

Every operation now writes a structured JSON summary file (.a11y-agent-team-install-summary.json, -update-summary.json, or -uninstall-summary.json) containing the full record of what was installed, where, which VS Code profiles were targeted, and what the MCP configuration state is. CI pipelines can parse these for automated validation.

Shared Installer Libraries

Two new shared modules (scripts/Installer.Common.ps1 and scripts/installer-common.sh) provide consistent cross-platform behavior for VS Code profile detection, JSON summary writing, directory operations, and backup metadata. This eliminated duplicated logic and the class of bugs where PowerShell and Bash installers behaved differently.

Clean Uninstallation

The uninstaller now removes the MCP server entry from VS Code settings.json automatically - including cleanup of empty mcp.servers objects. Previously you had to edit settings.json by hand after uninstalling.

---

Document Audit Reports Now Speak Plain Language

This is a fundamental change in how document accessibility findings are presented.

Native-Tool-First Remediation

Every finding across all document agents - Word, Excel, PowerPoint, PDF, and the CSV export - now follows a new three-part structure:

Start Here - tells the user exactly what to do in the native application (Word ribbon path, Excel menu, PowerPoint selection pane, Acrobat Pro tool panel). This is the first thing readers see.

Why It Matters - explains the accessibility impact in plain language.

Advanced / Technical Follow-Up - XML structures, scripting approaches, and programmatic fixes for power users who need them.

What Changed

• document-accessibility-wizard - New Remediation Writing Standard, new Start Here and Native App Action Plan sections in the report template
• word-accessibility - All findings restructured with Start Here leading to Word ribbon paths
• excel-accessibility - All findings restructured with Start Here leading to Excel menu paths
• powerpoint-accessibility - All findings restructured with Start Here leading to Selection Pane and slide layout paths
• pdf-accessibility - All findings restructured with Start Here leading to Acrobat Pro tool paths, with specific note about Acrobat triage before source rebuilds
• document-csv-reporter - CSV fix_suggestion column now leads with native-app action in the first sentence

Why This Matters

Most people who receive a document accessibility audit report are content authors, not developers. They know how to use Word and PowerPoint. They should not have to parse XML schemas to fix a missing alt text description. Now they do not have to.

---

96 Agent Definitions Updated Across 3 Platforms

Every agent change was synchronized across GitHub Copilot (.github/agents/), Claude Code (.claude/agents/), and the Claude Code plugin (claude-code-plugin/agents/).

Coordinator Safety

All coordinator agents (accessibility-lead, web-accessibility-wizard, document-accessibility-wizard, and others) now declare an explicit agents: list in their YAML frontmatter specifying exactly which specialist agents they are allowed to invoke. The validator enforces this at commit time.

This prevents the "wrong agent called" problem and makes the orchestration architecture visible and auditable in code review.

Platform Focus: Windows and macOS

4.5.0 removes Linux desktop accessibility references across the agent suite. This affects:

• Desktop accessibility specialist - ATK/AT-SPI API section removed
• Desktop a11y testing coach - Orca screen reader section removed
• Testing coach - Orca references removed
• Screen reader lab - Orca simulation mode removed
• Python specialist - Linux column removed from cross-platform reference tables
• wxPython specialist - Linux-specific guidance removed
• All installer scripts - Linux cron scheduling removed; shell auto-update now macOS-only
• All documentation - "macOS/Linux" changed to "macOS" throughout

The agents, installers, and documentation now explicitly target Windows and macOS. Linux users can still install and use the agents for web and document accessibility, but desktop accessibility testing coverage (screen reader APIs, platform automation) is Windows and macOS only.

Markdown Rendering Quality

Approximately 40 agent files received systematic formatting fixes:

• Blank lines added before bulleted lists for correct markdown spec rendering
• Code fences changed from bare triple-backtick to language-tagged blocks (text, yaml, json) so output is not randomly syntax-highlighted
• Trailing newlines normalized

These changes improve rendering quality in GitHub, VS Code preview, and documentation site builds.

---

MCP Server Documentation Overhaul

New: PDF Quick Start Guide

New standalone guide (PDF-QUICKSTART.md) for users who only need PDF scanning. Six steps from zero to working PDF accessibility scan, without touching the full agent suite.

Expanded MCP README

The MCP server README was substantially rewritten:

• "What Works Out of the Box" matrix - shows which agents need which MCP capabilities
• Prerequisite matrix - 9-row table showing what is required vs. optional
• Local vs. shared server comparison - helps teams decide deployment topology
• Actionable veraPDF setup - platform-specific install commands for Windows (winget/choco), macOS (brew), and manual download
• Verification examples - how to confirm each prerequisite is working

---

VS Code 1.113 Alignment

MCP Across Agent Types

MCP servers registered in VS ...

v4.10.0: Enhanced Validator, Pre-commit Hook & Agent Fixes

v4.10.0 — Enhanced Validator, Pre-commit Hook & Agent Fixes

This release brings a comprehensive overhaul of the agent validation system, a pre-commit hook to catch issues before they land, and fixes for 38 issues found across the agent fleet.

Highlights

Enhanced Validator

The validate-agents.js script is now a full schema validator built from three official sources:

• Official tool alias table from the GitHub custom-agents configuration reference
• VS Code qualified tools from the Copilot features reference
• MCP namespace patterns for <server>/* and <server>/<tool> validation

New checks include:

• Frontmatter property validation against the official schema
• Deprecated infer: detection with migration guidance
• Prompt body size enforcement (30K GitHub.com limit)
• Duplicate tool detection
• Claude Code tool validation (MCP(...) syntax)
• --strict, --quiet, --files CLI flags

Pre-commit Hook

New scripts/pre-commit hook validates only staged agent/skill files before every commit. Runs in --strict mode to block commits with validation warnings.

�ash node scripts/install-hooks.js # one-time setup

38 Agent Fixes

Fix	Files	Impact
user-invokable typo fixed to user-invocable	16 agents	Property was silently ignored by Copilot
Removed deprecated infer: true	16 agents	Defaults are equivalent; no behavioral change
Removed duplicate search tool	repo-manager	Cleaner config
Added target: vscode	5 agents	Prevents false positive on 30K char limit

Other Changes

• MCP server dependency auto-install in install.ps1 / install.sh
• MCP setup guide added to docs/getting-started.md
• CI workflow runs --strict and triggers on claude-code-plugin/agents/**
• Broken link repairs from v4.0.0 follow-up

Upgrade

�ash git pull node scripts/install-hooks.js # install pre-commit hook

Or use the installer:

`powershell

PowerShell

./update.ps1
`

`�ash

Bash

./update.sh
`

Full changelog: v4.0.0...v4.10.0

v4.0.0 - 80 Agents, 25 Skills, 134 Prompts, 24 MCP Tools

Accessibility Agents v4.0.0

80 agents. 5 platforms. 25 skills. 134 prompts. 24 MCP tools. One mission: accessible software for everyone.

What's New

21 New Specialist Agents

Agent	What It Does
CI Accessibility	CI/CD accessibility pipeline setup - GitHub Actions, Azure DevOps, GitLab CI, CircleCI, Jenkins
Screen Reader Lab	Interactive screen reader simulation for education
WCAG 3.0 Preview	Educational agent for WCAG 3.0 Working Draft
WCAG AAA	Dedicated AAA-level conformance checking - 28 criteria beyond AA
i18n Accessibility	Internationalization auditing - lang, RTL, BCP 47
PDF Remediator	Programmatic PDF fixes - 8 auto-fixable + 6 manual-fix
Email Accessibility	HTML email accessibility under client constraints
Media Accessibility	Video/audio - captions, descriptions, transcripts
Web Component Specialist	Shadow DOM, ElementInternals, cross-shadow ARIA
Compliance Mapping	Legal framework mapping - Section 508, EN 301 549
Data Visualization	Chart/graph/dashboard accessibility
Performance Accessibility	Performance + accessibility intersection
Accessibility Statement	W3C/EU model statement generation
Regression Detector	Score trends across commits/branches
Office Remediator	Office doc remediation via python-docx/openpyxl
Projects Manager	GitHub Projects v2 boards, views, custom fields
Actions Manager	GitHub Actions runs, logs, re-runs, CI debugging
Security Dashboard	Dependabot, code scanning, secret scanning triage
Release Manager	Release lifecycle, tags, assets, notes
Notifications Manager	GitHub notification inbox management
Wiki Manager	Wiki pages with accessible markdown enforcement

7 New Knowledge Skills (25 total)

• CI Integration - axe-core CLI reference, baseline schema, CI/CD templates
• Testing Strategy - Automated vs manual testing coverage matrix
• Legal Compliance Mapping - Section 508, ADA, EN 301 549, EAA, AODA
• Email Accessibility - Email client rendering constraints
• Media Accessibility - Caption formats, audio description, WCAG 1.2.x
• Data Visualization - Chart patterns, SVG ARIA, color-safe palettes
• Office Remediation - OOXML patterns, python-docx/openpyxl/python-pptx

3 New Always-On Instructions (9 total)

• CSS Accessibility - Focus visibility, motion safety, high contrast
• Testing Accessibility - Accessibility assertions in test files
• Document Generation - Enforces accessibility metadata in doc libraries

4 New MCP Tools (24 total)

• fix_document_metadata - Fix title, language, author in Office documents
• fix_document_headings - Report heading structure issues in .docx files
• check_audit_cache - Check for changed files since last scan
• update_audit_cache - Save scan results for incremental scanning

23 New Prompts (134 total)

Including: component library audit, training scenarios, native app audit, web CI/CD setup, PR accessibility check, team onboarding, email template audit, media content audit, accessibility dashboard, statement generator, and more.

Comprehensive User Guide

New instructor-style User Guide covering all 80 agents, 25 skills, 134 prompts, 9 instructions, and 24 MCP tools.

Cross-Platform Sync

All 80 agents available on every supported platform:

• GitHub Copilot (VS Code + CLI) - 80 agents, 25 skills, 134 prompts, 9 instructions
• Claude Code - 80 agents with 3-hook enforcement system
• Claude Code Plugin - 80 agents
• Gemini CLI - 98 skills (80 agent + 18 knowledge)
• Codex CLI - 11 roles

Infrastructure

• HTTP-based MCP Server with Streamable HTTP + stdio
• Enterprise configuration schema
• Accessibility PR Gate CI workflow
• 52-test MCP server test suite
• Anthropic directory manifest for Claude Desktop

Bug Fixes

• Fixed fix_document_headings reading .docx ZIP as raw UTF-8
• 52/52 MCP server tests passing
• Full markdownlint compliance
• Fixed installer manifest initialization order
• Fixed wxPython SetName() screen reader issues
• Fixed USER_GUIDE coverage gaps

Upgrade

cd accessibility-agents
git pull origin main
bash update.sh   # or: powershell -File update.ps1

---

Full changelog: https://github.com/Community-Access/accessibility-agents/blob/main/CHANGELOG.md

v3.2.0

Accessibility Agents v3.2.0

Compare: v3.0.0...v3.2.0

Release Scope (v3.0.0 -> v3.2.0)

• 238 files changed
• 7,968 insertions, 1,473 deletions

---

Highlights

1) Playwright Integration

• Added 5 Playwright MCP tools for behavioral accessibility scanning (keyboard traversal, dynamic state, viewport, contrast, a11y tree)
• New playwright-scanner agent for runtime accessibility verification
• New playwright-verifier agent for post-fix confirmation scans
• New playwright-testing skill with reusable scanning patterns
• New generate-a11y-tests prompt with CI template for automated test generation
• Integrated Playwright workflows into web-accessibility-wizard and web-issue-fixer

2) veraPDF PDF/UA Validator

• Added veraPDF integration for PDF/UA-1 and PDF/UA-2 validation
• New MCP tools for PDF standards compliance checking
• Integrated into document-accessibility-wizard scanning pipeline

3) PDF Form-to-HTML Converter

• Added PDF form extraction and accessible HTML conversion tool
• Preserves form field labels, grouping, and ARIA attributes in output

4) askQuestions Integration

• Added askQuestions tool integration across all 59 agents
• Enables agents to request clarification from users during complex audits
• Consistent integration pattern across the entire agent ecosystem

5) Plugin Distribution Fixes

• Fixed plugin symlink drift for docs, templates, and example directories (#57)
• Added .gitattributes for consistent line endings and symlink handling
• Updated CONTRIBUTING.md with Windows symlink documentation

6) NVDA Addon Specialist Updates

• Updated NVDA 2026.1 architecture transition documentation (#62)
• Corrected minimum addon version guidance across all 4 platform files
• Fixed 12 files with inaccurate version references

7) Codex Multi-Agent Support

• Added experimental multi-agent role support for Codex CLI (#59)

8) Additional Improvements

• Automated agent manifest generation workflow (#70)
• Gemini CLI hooks support with five lifecycle hook scripts
• Improved Copilot agent configuration with missing agents and updated WCAG references
• Fixed broken URLs and migrated Deque help links to Accessibility Insights
• Repository-wide accuracy and authority documentation refresh

---

Version Updates

File	Old Version	New Version
plugin.yaml	3.0.0	3.2.0
vscode-extension/package.json	3.0.0	3.2.0
desktop-extension/package.json	3.0.0	3.2.0
desktop-extension/manifest.json	3.0.0	3.2.0
claude-code-plugin/plugin.json	3.1.0	3.2.0
.claude-plugin/marketplace.json	1.1.0	3.2.0

Asset Counts

• 59 specialist agents
• 106 custom prompts
• 18 reusable skills
• 6 workspace instructions
• 338 manifest entries

---

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

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