agentmods.dev

x-callback-url:xcall

x-callback-url:xcall is a skill for Claude Code from bendrucker/claude. It costs 37 tokens per session (1,439 once invoked), scanned A, original, MIT.

A command-line bridge for calling macOS app URL schemes, which are special links that let apps such as Things, Bear, and OmniFocus exchange commands and responses.

In plain words
What is it for?
Use it from the command line to send x-callback-url requests to macOS apps that support them.
Why use it?
It lets scripts invoke supported macOS apps and receive their responses synchronously, so the command waits for the result before continuing.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the x-callback-url plugin — 1 skill shipped together

not rated 18repo changed 2mo ago A scan 37 tokens original MIT

Good fit Use it from the command line to send x-callback-url requests to macOS apps that support them.

Compare 6 skills from other repositories ↓
View source ↗ bendrucker/claude
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add bendrucker/claude
Claude Code
/plugin install x-callback-url

Made for: Claude Code.

Or install x-callback-url, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for x-callback-url:xcall

README.md
[![agentmods](https://agentmods.dev/badge/skills/bendrucker/claude/xcall/github.svg)](https://agentmods.dev/skills/bendrucker/claude/xcall)
Your own site
<a href="https://agentmods.dev/skills/bendrucker/claude/xcall"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/xcall/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for x-callback-url:xcall

Your own site · 80×15
<a href="https://agentmods.dev/skills/bendrucker/claude/xcall"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/xcall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,439 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.01439
Opus 5.5 $0.00015 $0.00576
Sonnet 5.5 $0.00007 $0.00288
Haiku 4.5 $0.00004 $0.00144

Measured 2mo ago against content hash 74bfb5e8c6ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

x-callback-url:xcall scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/x-callback-url/skills/xcall/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

xcall

Send x-callback-url requests from the command line and receive responses synchronously.

How It Works

xcall is a Swift CLI that builds into a macOS .app bundle. The .app is required because macOS only delivers URL scheme callbacks to registered applications. On first use, run.sh compiles the source into ~/.cache/claude/x-callback-url/xcall.app and registers the callback scheme (xcall-claude://) with Launch Services.

There is one bundle, shared by every consuming plugin, at a path outside the plugin tree. macOS registers exactly one handler for xcall-claude://, and lsregister -f on a second bundle does not take the scheme back from the first, so a per-consumer bundle makes consumers retire each other's copies in turn. The marketplace cache is content-addressed, so a bundle built beside the source loses its registration to a deleted path on the next plugin update.

Sandbox

Neither half of the bridge survives the command sandbox. lsregister cannot reach Launch Services to register the bundle, and a compiled xcall cannot complete the URL-scheme round trip. So run.sh and build.sh both carry the mac plugin's claude:dangerouslyDisableSandbox marker, which runs them outside it.

The marker hook reads the script named at the head of a command, past any VAR=value prefixes. A wrapper token in front of it (time, env, timeout) hides the script from the hook, the command runs sandboxed, and the callback is lost. Invoke run.sh by path with at most environment assignments ahead of it.

xcall cannot bound its own wait. Any deadline it scheduled would live in applicationDidFinishLaunching, which AppKit never calls when it cannot reach the WindowServer, so the sandboxed case that most needs a deadline is the one where it is never armed. run.sh holds both deadlines instead, from outside the process, and neither phase can wait forever:

  • XCALL_BUILD_TIMEOUT_SECONDS (default 20) bounds the build, and exits 3
  • XCALL_TIMEOUT_SECONDS (default 20) bounds the callback, and exits 4
  • XCALL_LOCK_WAIT_SECONDS (default XCALL_TIMEOUT_SECONDS + 3) bounds the wait for the bridge lock, and exits 5. The default covers one holder ahead, so raise it for a caller queued behind several

Read the full file on GitHub · 101 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago Changed · +3 lines 74bfb5e8c6ae
  2. 2mo ago First seen · 98 lines · 37 tokens per session scan A 57e0f96ed621

Subscribe to this mod's changes

x-callback-url:xcall is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 1,439 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Claude CodeProductivityclaude-code-plugin
Related

x-callback-url:xcall compared with skills from other repositories

x-callback-url:xcall next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
x-callback-url:xcallbendrucker/claudeSkill18todayMITA37Claude Code
release-noteskenryu42/cc-safety-netSkill2.0ktodayMITA65Claude Code, Codex
add-teamsmicrosoft/power-platform-skillsSkill1.1ktodayMITA31Claude Code
relationsLifecycle-Innovations-Limited/claude-opsSkill5503d agoMITA27Claude Code
service-deskcbrock84/headcountSkill2.6k22d agoMITA73Claude Code
recipe-add-integration-testsshinpr/claude-code-workflowsSkill7134d agoMITA19Claude Code
llm-friendly-contextshinpr/claude-code-workflowsSkill7134d agoMITA52Claude Code