chore: Update CHANGELOG.md

docs: add examples/settings

CHANGELOG.md

@@ -1,5 +1,72 @@
 # Changelog
 
+## 2.1.32
+
+- Claude Opus 4.6 is now available!
+- Added research preview agent teams feature for multi-agent collaboration (token-intensive feature, requires setting CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1)
+- Claude now automatically records and recalls memories as it works
+- Added "Summarize from here" to the message selector, allowing partial conversation summarization.
+- Skills defined in `.claude/skills/` within additional directories (`--add-dir`) are now loaded automatically.
+- Fixed `@` file completion showing incorrect relative paths when running from a subdirectory
+- Updated --resume to re-use --agent value specified in previous conversation by default.
+- Fixed: Bash tool no longer throws "Bad substitution" errors when heredocs contain JavaScript template literals like `${index + 1}`, which previously interrupted tool execution
+- Skill character budget now scales with context window (2% of context), so users with larger context windows can see more skill descriptions without truncation
+- Fixed Thai/Lao spacing vowels (สระ า, ำ) not rendering correctly in the input field
+- VSCode: Fixed slash commands incorrectly being executed when pressing Enter with preceding text in the input field
+- VSCode: Added spinner when loading past conversations list
+
+## 2.1.31
+
+- Added session resume hint on exit, showing how to continue your conversation later
+- Added support for full-width (zenkaku) space input from Japanese IME in checkbox selection
+- Fixed PDF too large errors permanently locking up sessions, requiring users to start a new conversation
+- Fixed bash commands incorrectly reporting failure with "Read-only file system" errors when sandbox mode was enabled
+- Fixed a crash that made sessions unusable after entering plan mode when project config in `~/.claude.json` was missing default fields
+- Fixed `temperatureOverride` being silently ignored in the streaming API path, causing all streaming requests to use the default temperature (1) regardless of the configured override
+- Fixed LSP shutdown/exit compatibility with strict language servers that reject null params
+- Improved system prompts to more clearly guide the model toward using dedicated tools (Read, Edit, Glob, Grep) instead of bash equivalents (`cat`, `sed`, `grep`, `find`), reducing unnecessary bash command usage
+- Improved PDF and request size error messages to show actual limits (100 pages, 20MB)
+- Reduced layout jitter in the terminal when the spinner appears and disappears during streaming
+- Removed misleading Anthropic API pricing from model selector for third-party provider (Bedrock, Vertex, Foundry) users
+
+## 2.1.30
+
+- Added `pages` parameter to the Read tool for PDFs, allowing specific page ranges to be read (e.g., `pages: "1-5"`). Large PDFs (>10 pages) now return a lightweight reference when `@` mentioned instead of being inlined into context.
+- Added pre-configured OAuth client credentials for MCP servers that don't support Dynamic Client Registration (e.g., Slack). Use `--client-id` and `--client-secret` with `claude mcp add`.
+- Added `/debug` for Claude to help troubleshoot the current session
+- Added support for additional `git log` and `git show` flags in read-only mode (e.g., `--topo-order`, `--cherry-pick`, `--format`, `--raw`)
+- Added token count, tool uses, and duration metrics to Task tool results
+- Added reduced motion mode to the config
+- Fixed phantom "(no content)" text blocks appearing in API conversation history, reducing token waste and potential model confusion
+- Fixed prompt cache not correctly invalidating when tool descriptions or input schemas changed, only when tool names changed
+- Fixed 400 errors that could occur after running `/login` when the conversation contained thinking blocks
+- Fixed a hang when resuming sessions with corrupted transcript files containing `parentUuid` cycles
+- Fixed rate limit message showing incorrect "/upgrade" suggestion for Max 20x users when extra-usage is unavailable
+- Fixed permission dialogs stealing focus while actively typing
+- Fixed subagents not being able to access SDK-provided MCP tools because they were not synced to the shared application state
+- Fixed a regression where Windows users with a `.bashrc` file could not run bash commands
+- Improved memory usage for `--resume` (68% reduction for users with many sessions) by replacing the session index with lightweight stat-based loading and progressive enrichment
+- Improved `TaskStop` tool to display the stopped command/task description in the result line instead of a generic "Task stopped" message
+- Changed `/model` to execute immediately instead of being queued
+- [VSCode] Added multiline input support to the "Other" text input in question dialogs (use Shift+Enter for new lines)
+- [VSCode] Fixed duplicate sessions appearing in the session list when starting a new conversation
+
+## 2.1.29
+
+- Fixed startup performance issues when resuming sessions that have `saved_hook_context`
+
+## 2.1.27
+
+- Added tool call failures and denials to debug logs
+- Fixed context management validation error for gateway users, ensuring `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1` avoids the error
+- Added `--from-pr` flag to resume sessions linked to a specific GitHub PR number or URL
+- Sessions are now automatically linked to PRs when created via `gh pr create`
+- Fixed /context command not displaying colored output
+- Fixed status bar duplicating background task indicator when PR status was shown
+- Windows: Fixed bash command execution failing for users with `.bashrc` files
+- Windows: Fixed console windows flashing when spawning child processes
+- VSCode: Fixed OAuth token expiration causing 401 errors after extended sessions
+
 ## 2.1.25
 
 - Fixed beta header validation error for gateway users on Bedrock and Vertex, ensuring `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1` avoids the error

examples/settings/README.md

@@ -0,0 +1,31 @@
+# Settings Examples
+
+Example Claude Code settings files, primarily intended for organization-wide deployments. Use these are starting points — adjust them to fit your needs.
+
+These may be applied at any level of the [settings hierarchy](https://code.claude.com/docs/en/settings#settings-files), though certain properties only take effect if specified in enterprise settings (e.g. `strictKnownMarketplaces`, `allowManagedHooksOnly`, `allowManagedPermissionRulesOnly`).
+
+
+## Configuration Examples
+
+> [!WARNING]
+> These examples are community-maintained snippets which may be unsupported or incorrect. You are responsible for the correctness of your own settings configuration.
+
+| Setting | [`settings-lax.json`](./settings-lax.json) | [`settings-strict.json`](./settings-strict.json) | [`settings-bash-sandbox.json`](./settings-bash-sandbox.json) |
+|---------|:---:|:---:|:---:|
+| Disable `--dangerously-skip-permissions` | ✅ | ✅ | |
+| Block plugin marketplaces | ✅ | ✅ | |
+| Block user and project-defined permission `allow` / `ask` / `deny` | | ✅ | ✅ |
+| Block user and project-defined hooks | | ✅ | |
+| Deny web fetch and search tools | | ✅ | |
+| Bash tool requires approval | | ✅ | |
+| Bash tool must run inside of sandbox | | | ✅ |
+
+## Tips
+- Consider merging snippets of the above examples to reach your desired configuration
+- Settings files must be valid JSON
+- Before deploying configuration files to your organization, test them locally by applying to `managed-settings.json`, `settings.json` or `settings.local.json`
+- The `sandbox` property only applies to the `Bash` tool; it does not apply to other tools (like Read, Write, WebSearch, WebFetch, MCPs), hooks, or internal commands
+
+## Full Documentation
+
+See https://code.claude.com/docs/en/settings for complete documentation on all available managed settings.

examples/settings/settings-bash-sandbox.json

@@ -0,0 +1,18 @@
+{
+  "allowManagedPermissionRulesOnly": true,
+  "sandbox": {
+    "enabled": true,
+    "autoAllowBashIfSandboxed": false,
+    "allowUnsandboxedCommands": false,
+    "excludedCommands": [],
+    "network": {
+      "allowUnixSockets": [],
+      "allowAllUnixSockets": false,
+      "allowLocalBinding": false,
+      "allowedDomains": [],
+      "httpProxyPort": null,
+      "socksProxyPort": null
+    },
+    "enableWeakerNestedSandbox": false
+  }
+}

examples/settings/settings-lax.json

@@ -0,0 +1,6 @@
+{
+  "permissions": {
+    "disableBypassPermissionsMode": "disable"
+  },
+  "strictKnownMarketplaces": []
+}

examples/settings/settings-strict.json

@@ -0,0 +1,28 @@
+{
+  "permissions": {
+    "disableBypassPermissionsMode": "disable",
+    "ask": [
+      "Bash"
+    ],
+    "deny": [
+      "WebSearch",
+      "WebFetch"
+    ]
+  },
+  "allowManagedPermissionRulesOnly": true,
+  "allowManagedHooksOnly": true,
+  "strictKnownMarketplaces": [],
+  "sandbox": {
+    "autoAllowBashIfSandboxed": false,
+    "excludedCommands": [],
+    "network": {
+      "allowUnixSockets": [],
+      "allowAllUnixSockets": false,
+      "allowLocalBinding": false,
+      "allowedDomains": [],
+      "httpProxyPort": null,
+      "socksProxyPort": null
+    },
+    "enableWeakerNestedSandbox": false
+  }
+}

plugins/frontend-design/skills/frontend-design/SKILL.md

@@ -1,28 +1,27 @@
 ---
 name: frontend-design
-description: Create distinctive, production-grade frontend interfaces with high design quality and full accessibility. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished, accessible code that avoids generic AI aesthetics.
+description: Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
 license: Complete terms in LICENSE.txt
 ---
 
-This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics while ensuring full accessibility for all users. Implement real working code with exceptional attention to aesthetic details, creative choices, and inclusive design.
+This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices.
 
 The user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints.
 
 ## Design Thinking
 
 Before coding, understand the context and commit to a BOLD aesthetic direction:
-- **Purpose**: What problem does this interface solve? Who uses it? Consider the full spectrum of users including those with disabilities.
+- **Purpose**: What problem does this interface solve? Who uses it?
 - **Tone**: Pick an extreme: brutally minimal, maximalist chaos, retro-futuristic, organic/natural, luxury/refined, playful/toy-like, editorial/magazine, brutalist/raw, art deco/geometric, soft/pastel, industrial/utilitarian, etc. There are so many flavors to choose from. Use these for inspiration but design one that is true to the aesthetic direction.
-- **Accessibility**: Accessibility is not a constraint—it's a design opportunity. The best interfaces are both beautiful AND universally usable.
+- **Constraints**: Technical requirements (framework, performance, accessibility).
 - **Differentiation**: What makes this UNFORGETTABLE? What's the one thing someone will remember?
 
-**CRITICAL**: Choose a clear conceptual direction and execute it with precision. Bold maximalism and refined minimalism both work - the key is intentionality, not intensity. Great design serves everyone.
+**CRITICAL**: Choose a clear conceptual direction and execute it with precision. Bold maximalism and refined minimalism both work - the key is intentionality, not intensity.
 
 Then implement working code (HTML/CSS/JS, React, Vue, etc.) that is:
 - Production-grade and functional
 - Visually striking and memorable
 - Cohesive with a clear aesthetic point-of-view
-- Fully accessible to all users
 - Meticulously refined in every detail
 
 ## Frontend Aesthetics Guidelines
@@ -40,53 +39,4 @@ Interpret creatively and make unexpected choices that feel genuinely designed fo
 
 **IMPORTANT**: Match implementation complexity to the aesthetic vision. Maximalist designs need elaborate code with extensive animations and effects. Minimalist or refined designs need restraint, precision, and careful attention to spacing, typography, and subtle details. Elegance comes from executing the vision well.
 
-## Accessibility Excellence
-
-Accessibility is not an afterthought—it's fundamental to great design. Beautiful interfaces must work for everyone. Follow these principles:
-
-### Semantic Structure
-- **Use semantic HTML elements**: `<header>`, `<nav>`, `<main>`, `<article>`, `<section>`, `<aside>`, `<footer>`. These provide meaning to assistive technologies.
-- **Heading hierarchy**: Use `<h1>` through `<h6>` in logical order. Never skip levels. Screen reader users navigate by headings.
-- **Lists and tables**: Use proper `<ul>`, `<ol>`, `<dl>` for lists and `<table>` with `<thead>`, `<tbody>`, `<th scope>` for tabular data.
-- **Landmarks**: Ensure main content is in `<main>`, navigation in `<nav>`. Use `role` attributes only when semantic HTML isn't available.
-
-### Keyboard Navigation
-- **All interactive elements must be keyboard accessible**: Users must be able to Tab to and activate every button, link, and control.
-- **Logical tab order**: Follow visual reading order. Use `tabindex="0"` to make custom elements focusable; avoid positive tabindex values.
-- **Visible focus indicators**: Never remove focus outlines without providing a clear alternative. Style `:focus-visible` with distinctive, on-brand styling.
-- **Skip links**: Provide "Skip to main content" links for keyboard users to bypass repetitive navigation.
-- **Keyboard shortcuts**: For complex interactions, support standard patterns (Escape to close modals, Arrow keys for menus).
-
-### Visual Accessibility
-- **Color contrast**: Maintain WCAG AA minimum ratios—4.5:1 for normal text, 3:1 for large text and UI components. Bold color choices CAN meet contrast requirements.
-- **Don't rely on color alone**: Use icons, patterns, text labels, or underlines alongside color to convey meaning (errors, status, links).
-- **Text sizing**: Use relative units (rem, em) so text scales with user preferences. Never disable zoom.
-- **Reduced motion**: Wrap decorative animations in `@media (prefers-reduced-motion: no-preference)`. Essential animations should be subtle.
-- **High contrast mode**: Test with `forced-colors` media query. Ensure UI remains usable.
-
-### ARIA & Screen Readers
-- **ARIA labels**: Use `aria-label` or `aria-labelledby` for elements without visible text labels. Icon buttons MUST have accessible names.
-- **Live regions**: Use `aria-live="polite"` for dynamic content updates (notifications, loading states). Use `aria-live="assertive"` sparingly.
-- **State attributes**: Communicate state with `aria-expanded`, `aria-selected`, `aria-checked`, `aria-pressed`, `aria-current`.
-- **Hidden content**: Use `aria-hidden="true"` for decorative elements. Use `.visually-hidden` class (not `display: none`) for screen-reader-only text.
-- **First rule of ARIA**: Don't use ARIA if native HTML provides the semantics. A `<button>` is better than `<div role="button">`.
-
-### Interactive Components
-- **Buttons vs links**: `<button>` for actions, `<a href>` for navigation. Never use `<div>` or `<span>` for interactive elements.
-- **Form labels**: Every input needs an associated `<label>` with `for` attribute, or use `aria-label`. Placeholder text is NOT a label.
-- **Error handling**: Associate error messages with inputs using `aria-describedby`. Announce errors to screen readers. Don't rely on color alone.
-- **Modals and dialogs**: Trap focus inside modals. Return focus to trigger element on close. Use `<dialog>` element or proper ARIA roles.
-- **Loading states**: Announce loading with `aria-busy="true"` and `aria-live`. Provide text alternatives to spinners.
-
-### Testing Checklist
-Before considering any interface complete, verify:
-- [ ] Navigate entire interface using only keyboard (Tab, Enter, Space, Escape, Arrow keys)
-- [ ] Test with screen reader (VoiceOver, NVDA, or browser extensions)
-- [ ] Check color contrast with browser DevTools or axe
-- [ ] Resize text to 200% and ensure layout doesn't break
-- [ ] Enable reduced motion and verify animations respect preference
-- [ ] Run automated accessibility audit (axe, Lighthouse)
-
-**CRITICAL**: Accessibility and bold design are not in conflict. High contrast ratios work with dramatic color palettes. Semantic structure enhances, not limits, creative layouts. Motion can be both delightful and respectful of preferences. The goal is inclusive excellence.
-
-Remember: Claude is capable of extraordinary creative work. Don't hold back, show what can truly be created when thinking outside the box and committing fully to a distinctive vision that serves all users.
+Remember: Claude is capable of extraordinary creative work. Don't hold back, show what can truly be created when thinking outside the box and committing fully to a distinctive vision.