Context Mode Output Sandbox
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
Teaches how xc-plugin saves tokens with progressive disclosure, cached responses and consistent configuration, so large device lists and build logs arrive as summaries first.
$ npx skills add conorluddy/xclaude-plugin --skill state-management -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install conorluddy/xclaude-plugin state-management --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/conorluddy/xclaude-plugin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/state-management .claude/skills/state-management && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "state-management" agent skill from https://github.com/conorluddy/xclaude-plugin/tree/main/skills/state-management into .claude/skills/state-management/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "state-management", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/conorluddy/xclaude-plugin/tree/main/skills/state-managementType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add conorluddy/xclaude-plugin --skill state-management -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install conorluddy/xclaude-plugin state-management --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/conorluddy/xclaude-plugin.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/state-management .agents/skills/state-management && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "state-management" agent skill from https://github.com/conorluddy/xclaude-plugin/tree/main/skills/state-management into .agents/skills/state-management/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "state-management", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add conorluddy/xclaude-plugin --skill state-management -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install conorluddy/xclaude-plugin state-management --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/conorluddy/xclaude-plugin.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/state-management .cursor/skills/state-management && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "state-management" agent skill from https://github.com/conorluddy/xclaude-plugin/tree/main/skills/state-management into .cursor/skills/state-management/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "state-management", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/conorluddy/xclaude-plugin.git --path skills/state-management--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add conorluddy/xclaude-plugin --skill state-management -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install conorluddy/xclaude-plugin state-management --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/conorluddy/xclaude-plugin.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/state-management .gemini/skills/state-management && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "state-management" agent skill from https://github.com/conorluddy/xclaude-plugin/tree/main/skills/state-management into .gemini/skills/state-management/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "state-management", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install conorluddy/xclaude-plugin state-managementInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add conorluddy/xclaude-plugin --skill state-management -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/conorluddy/xclaude-plugin.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/state-management .github/skills/state-management && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "state-management" agent skill from https://github.com/conorluddy/xclaude-plugin/tree/main/skills/state-management into .github/skills/state-management/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "state-management", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add conorluddy/xclaude-plugin --skill state-management -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install conorluddy/xclaude-plugin state-management --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/conorluddy/xclaude-plugin.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/state-management .opencode/skills/state-management && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "state-management" agent skill from https://github.com/conorluddy/xclaude-plugin/tree/main/skills/state-management into .opencode/skills/state-management/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "state-management", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
state-managementTeaches how xc-plugin saves tokens with progressive disclosure, cached responses and consistent configuration, so large device lists and build logs arrive as summaries first.
This skill explains how the xc-plugin, an iOS development plugin that groups Xcode and IDB tools into MCP servers, manages state to save tokens. Instead of returning a large dataset, a call returns a short summary, a cache_id and a follow-up query for the full details. The skill presents this as cutting token use by 85 to 90 percent for typical queries.
It also describes the cache. Keys are the first 16 characters of a SHA-256 hash of the operation and its parameters, so identical input gives the same cache_id. Storage is in memory with optional disk persistence and a configurable expiry, and list, build and describe operations are cache-friendly. The agent is shown how to query cached data, invalidate stale entries and set consistent build and simulator settings for repeatable test runs.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 6de4b2c. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are json and typescript).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
xc-plugin State Management loads about 4k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 1,001 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from conorluddy/xclaude-plugin at commit 6de4b2c, republished under its MIT licence (© conorluddy). 1,001 words, ~3,988 tokens.
.claude/skills/state-management/SKILL.md (or your agent's skills folder).Optimizing token efficiency and state management in xc-plugin
The xc-plugin implements sophisticated state management through caching, progressive disclosure, and configuration management. This Skill teaches how to leverage these patterns to minimize token usage, improve performance, and maintain clean state across operations.
Key Benefits:
Use this Skill when you need to:
Optimize Token Usage
Manage Cache State
Handle Configuration
Design Efficient Workflows
Principle: Show essentials first, provide details on-demand.
Instead of returning massive datasets that consume tokens, xc-plugin returns:
Token Efficiency:
Traditional approach: 2000 tokens (full device list)
Progressive disclosure: 100 tokens (summary) + optional 2000 tokens (details)
Average savings: 95% (most queries don't need full details)The plugin uses deterministic caching for expensive operations:
Cache Key Generation:
cache_idCache Storage:
Cache-Friendly Operations:
list operations (device lists, app lists)build operations (build logs, test results)describe operations (accessibility trees)SuccessResult with Progressive Disclosure:
{
success: true,
data: {
summary: "31 devices available, 1 booted",
booted_devices: [...],
cache_id: "a1b2c3d4e5f6g7h8"
},
summary: "Device list retrieved successfully"
}Follow-up Query Pattern:
{
operation: "get-details",
cache_id: "a1b2c3d4e5f6g7h8",
detail_type: "full-list"
}Initial Query (Token-Efficient):
{
"operation": "list",
"parameters": {
"concise": true
}
}Response:
{
"success": true,
"data": {
"summary": {
"total_devices": 47,
"available_devices": 31,
"booted_devices": 1
},
"booted": [
{
"name": "iPhone 15",
"udid": "ABC123...",
"state": "Booted",
"runtime": "iOS 17.0"
}
],
"cache_id": "sim-list-xyz789"
}
}Follow-Up (Only If Needed):
{
"operation": "get-details",
"cache_id": "sim-list-xyz789",
"detail_type": "full-list"
}Token Analysis:
Build Operation:
{
"operation": "build",
"scheme": "MyApp",
"configuration": "Debug",
"output_format": "summary"
}Response with Cache:
{
"success": true,
"data": {
"message": "Build succeeded",
"build_time": "45.2s",
"warnings": 3,
"cache_id": "build-abc123"
},
"summary": "Build completed successfully with 3 warnings"
}Retrieve Full Logs:
{
"operation": "get-details",
"cache_id": "build-abc123",
"detail_type": "full-log"
}Cache Invalidation Scenarios:
Query Current Configuration:
{
"operation": "cache",
"sub_operation": "get-config"
}Response:
{
"cache_enabled": true,
"cache_ttl": 3600,
"max_cache_size": 100,
"persistence_enabled": false
}Update Configuration:
{
"operation": "cache",
"sub_operation": "set-config",
"parameters": {
"cache_ttl": 7200,
"persistence_enabled": true
}
}Pattern for Clean Test State:
1. cache (clear: "all") → Remove all cached data
2. device-lifecycle (erase) → Reset simulator state
3. app-lifecycle (uninstall) → Remove app
4. app-lifecycle (install) → Fresh install
5. app-lifecycle (launch) → Start with clean state
6. (run tests) → Execute test suite
7. cache (clear: "response") → Clean response cacheWhy This Matters:
Level 1: Summary (Always Returned)
{
"summary": {
"key_metric_1": "value",
"key_metric_2": "value",
"action_taken": "description"
},
"cache_id": "unique-identifier",
"next_steps": [
"Suggested action 1",
"Suggested action 2"
]
}Level 2: Detailed Query (On-Demand)
{
"operation": "get-details",
"cache_id": "unique-identifier",
"detail_type": "full-data|errors-only|warnings-only|metadata"
}Always Use For:
Skip For:
Summary Response:
{
"success": false,
"data": {
"tests_run": 45,
"tests_passed": 43,
"tests_failed": 2,
"failed_tests": [
"MyAppTests.LoginTests.testInvalidPassword",
"MyAppTests.LoginTests.testEmptyCredentials"
],
"cache_id": "test-run-def456"
}
}Full Details Query:
{
"operation": "get-details",
"cache_id": "test-run-def456",
"detail_type": "full-log"
}Token Efficiency:
High Cache Value (Long TTL):
list operations (device list changes infrequently)version operations (Xcode version is stable)show-build-settings (project config changes rarely)Moderate Cache Value (Medium TTL):
build operations (results valid until code changes)test operations (results valid until code/tests change)describe operations (UI state changes moderately)Low Cache Value (Short TTL):
device-lifecycle (device state changes frequently)app-lifecycle (app state is dynamic)input/tap operations (UI interactions modify state)// Recommended TTL values
{
simulator_list: 1800, // 30 minutes
device_state: 60, // 1 minute
build_results: 3600, // 1 hour
test_results: 3600, // 1 hour
xcode_version: 86400, // 24 hours
project_schemes: 3600, // 1 hour
accessibility_tree: 10 // 10 seconds
}Automatic Invalidation:
clean invalidates build cache)Manual Invalidation:
{
"operation": "cache",
"sub_operation": "clear",
"parameters": {
"cache_type": "simulator|project|response|all"
}
}Smart Invalidation:
In-Memory Cache (Default):
Disk Cache (Optional):
Enable Disk Persistence:
{
"operation": "persistence",
"sub_operation": "enable",
"parameters": {
"cache_dir": "/tmp/xc-cache"
}
}Query Build Settings:
{
"operation": "show-build-settings",
"scheme": "MyApp",
"configuration": "Debug"
}Common Settings to Cache:
PRODUCT_BUNDLE_IDENTIFIERDEVELOPMENT_TEAMCODE_SIGN_IDENTITYSDKROOTARCHSUse Case:
Query Simulator Configuration:
{
"operation": "list",
"parameters": {
"runtime": "iOS 17.0",
"device_type": "iPhone"
}
}Persist Simulator State:
Debug vs Release Configuration:
Debug:
{
"configuration": "Debug",
"options": {
"parallel": true,
"quiet": false
}
}Release:
{
"configuration": "Release",
"options": {
"parallel": true,
"quiet": true
}
}Set Test Environment:
{
"operation": "app-lifecycle",
"sub_operation": "launch",
"device_id": "iPhone 15",
"app_identifier": "com.example.MyApp",
"parameters": {
"environment": {
"API_URL": "https://staging.example.com",
"MOCK_DATA": "true",
"LOG_LEVEL": "debug"
}
}
}Common Environment Variables:
API_URL - Backend endpointFEATURE_FLAGS - Enable/disable featuresTEST_MODE - Testing-specific behaviorLOG_LEVEL - Logging verbosityUse Progressive Disclosure:
// Good: Request summary first
{
"operation": "list",
"parameters": { "concise": true }
}
// Then query details only if needed
{
"operation": "get-details",
"cache_id": "sim-list-xyz"
}Avoid Verbose Operations:
// Bad: Always verbose
{
"operation": "build",
"options": { "verbose": true }
}
// Good: Quiet by default, verbose on errors
{
"operation": "build",
"options": { "quiet": true }
}Identify Expensive Operations:
build (20-120 seconds)test (10-300 seconds)list with large device sets (1-5 seconds)describe with complex UI (0.5-2 seconds)Cache Strategy:
// First call: Execute and cache
{
"operation": "list"
}
// Response includes cache_id
// Subsequent calls: Use cached data
{
"operation": "get-details",
"cache_id": "previous-cache-id"
}Clean State Pattern:
1. Cache clear (all)
2. Simulator erase
3. App uninstall
4. Fresh app install
5. Launch with test environment
6. Run tests
7. Cache clear (response)Why Each Step:
Detect Stale Cache:
// Check cache timestamp
if (cache_age > ttl) {
invalidateCache(cache_id);
refetch();
}Recovery Strategy:
// If cache miss or stale:
{
"operation": "original-operation",
// Original parameters
}
// Plugin automatically refreshes cacheUser Pattern:
Track Token Usage:
Summary responses: ~100-300 tokens
Full responses: ~1000-5000 tokens
Progressive disclosure savings: 80-95%Optimization Checklist:
concise: true for list operationssummary output format for buildsquiet: true for non-debug buildsBuild Configuration:
{
"scheme": "MyApp",
"configurations": {
"debug": {
"configuration": "Debug",
"destination": "platform=iOS Simulator,name=iPhone 15",
"cache_strategy": "short_ttl",
"output_format": "summary"
},
"release": {
"configuration": "Release",
"destination": "generic/platform=iOS",
"cache_strategy": "long_ttl",
"output_format": "detailed"
}
}
}Test Configuration:
{
"test_scheme": "MyAppTests",
"test_devices": [
"iPhone 15",
"iPad Pro (12.9-inch)"
],
"clean_state": true,
"cache_results": true,
"parallel_execution": false,
"environment": {
"TEST_MODE": "true",
"MOCK_NETWORK": "true"
}
}Cache Configuration:
{
"cache": {
"enabled": true,
"ttl": {
"simulator_list": 1800,
"build_results": 3600,
"test_results": 3600,
"device_state": 60
},
"persistence": {
"enabled": true,
"path": "/tmp/xc-cache",
"max_size_mb": 500
},
"invalidation": {
"auto_invalidate_on_build": true,
"auto_invalidate_on_test": false
}
}
}This Skill applies to all xc-plugin MCP tools:
Cache-Aware Tools:
xcodebuild-list - Returns cache_id for project dataxcodebuild-build - Returns cache_id for build logsxcodebuild-test - Returns cache_id for test resultssimctl-list - Returns cache_id for device listsidb-ui-describe - Returns cache_id for UI treesCache Management Tools:
xcodebuild-get-details - Query cached build datasimctl-get-details - Query cached simulator datacache - Manage cache configurationpersistence - Configure disk cachingxc://reference/cache-architecture - Cache implementation detailsxc://reference/token-optimization - Token efficiency guidexc://workflows/progressive-disclosure - Pattern documentationxc://reference/configuration - Configuration referenceRemember: Progressive disclosure first, full details only when needed. Cache expensive operations. Clear state between tests. 85-90% token savings are achievable with proper state management.
© conorluddy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/state-management of conorluddy/xclaude-plugin.
Open the folder on GitHubat commit 6de4b2c
xc-plugin State Management next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| xc-plugin State Management this skillconorluddy/xclaude-plugin | 183 | — | ~4k | Automated safety check: Pass | MIT | |
| Context Mode Output Sandboxmksglu/context-mode | 26k | — | ~4.1k | Automated safety check: Pass | Custom licence | |
| Context Mode for Antigravity CLImksglu/context-mode | 26k | — | ~850 | Automated safety check: Pass | Custom licence | |
| Foundation Models Os27 Updaterrryam/FoundationModelsKit | 162 | — | ~2.9k | Automated safety check: Pass | MIT | |
| Entroly Context Controljuyterman1000/entroly | 474 | — | ~501 | Automated safety check: Pass | Apache-2.0 | |
| Entroly Evidence Operationsjuyterman1000/entroly | 474 | — | ~528 | Automated safety check: Pass | Apache-2.0 |
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
mksglu/context-mode
Routing rules for using context-mode MCP tools in Antigravity CLI: sandboxed code runs, file analysis, indexed search and web fetches that keep large output out of the conversation.
rryam/FoundationModelsKit
Upgrade any Apple Foundation Models Swift app or package from OS 26-era APIs to OS 27 and Xcode 27 APIs.
juyterman1000/entroly
Surgically select, compress, and recover codebase context using Entroly's MCP tools.
juyterman1000/entroly
Use Entroly for content-blind agent-history audits, explicit baseline/optimized trials, recoverable command or browser evidence, response contracts, and token-efficiency claim verification.
juyterman1000/entroly
Audit and remediate Entroly's MCP marketplace quality with evidence, adversarial validation, and no score gaming.
conorluddy/xclaude-plugin
Guides WCAG 2.1 and VoiceOver accessibility testing for iOS apps, working from the accessibility tree and not from screenshots.
conorluddy/xclaude-plugin
Walks through retrieving, symbolicating and diagnosing iOS crash logs, turning a cryptic stack trace into the function names that actually failed.
conorluddy/xclaude-plugin
Manages iOS Simulator devices and apps through the execute_simulator_command MCP tool instead of raw simctl: boot, create and delete devices, install and launch apps, screenshots and diagnostics.
conorluddy/xclaude-plugin
Accessibility-first UI automation using IDB. An agent skill from conorluddy/xclaude-plugin.
conorluddy/xclaude-plugin
Directs iOS build, test and clean operations through the execute_xcode_command MCP tool instead of raw xcodebuild in the shell, with parameter-level retries on failure.
conorluddy/xclaude-plugin
Instruments integration and performance analysis workflows for iOS apps.
Works with
Categories
Teaches how xc-plugin saves tokens with progressive disclosure, cached responses and consistent configuration, so large device lists and build logs arrive as summaries first. This skill explains how the xc-plugin, an iOS development plugin that groups Xcode and IDB tools into MCP servers, manages state to save tokens. Instead of returning a large dataset, a call returns a short summary, a cache_id and a follow-up query for the full details.
xc-plugin State Management fits situations like: working with large device lists or build logs without flooding the context window; querying or invalidating cached xc-plugin responses; setting up consistent simulator and build configuration for test runs.
Run `npx skills add conorluddy/xclaude-plugin --skill state-management -a claude-code`. Or copy the skill folder (skills/state-management in conorluddy/xclaude-plugin) into .claude/skills/state-management in your project. Claude Code loads it when a task matches its description.
Run `npx skills add conorluddy/xclaude-plugin --skill state-management -a codex`. Or copy the skill folder (skills/state-management in conorluddy/xclaude-plugin) into .agents/skills/state-management in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add conorluddy/xclaude-plugin --skill state-management -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/state-management, .gemini/skills/state-management, .github/skills/state-management and .opencode/skills/state-management in your project.
SKILL.md names no scripts, command-line tools or credentials: xc-plugin State Management is instructions for the agent only. Our summary lists: The xc-plugin installed with its Xcode MCP tools.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
xc-plugin State Management is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with xc-plugin State Management: Context Mode Output Sandbox (mksglu/context-mode, 26k stars), Context Mode for Antigravity CLI (mksglu/context-mode, 26k stars), Foundation Models Os27 Updater (rryam/FoundationModelsKit, 162 stars) and Entroly Context Control (juyterman1000/entroly, 474 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
conorluddy (a GitHub user) maintains it in conorluddy/xclaude-plugin, which has 183 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 12, 2026.
Source: conorluddy/xclaude-plugin on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.