agentmods.dev

hotline-dial

hotline-dial is a skill for Claude Code, Codex from jtsternberg/claude-plugins. It costs 56 tokens per session (9,601 once invoked), scanned D, original, MIT.

A tool for contacting another Claude Code workspace to ask a question, delegate work, or collaborate. A workspace is a separate project environment where an agent can work.

In plain words
What is it for?
Use it to send questions or work orders to another workspace, start conference-style collaboration, or launch a detached task in a new workspace tab.
Why use it?
It handles finding the other workspace, choosing a connection method, starting the session, and returning the response in one command.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the hotline plugin — 4 skills shipped together

not rated 5 changed today D scan 56 tokens original MIT
View the source file jtsternberg/claude-plugins
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/jtsternberg/claude-plugins/dial
Any agent
npx skills add jtsternberg/claude-plugins --skill dial
Clone the repo
git clone --depth 1 https://github.com/jtsternberg/claude-plugins

Made for: Claude Code, Codex.

Or install hotline, the plugin that ships this one along with the rest of its 4 skills.

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 hotline-dial

README.md
[![agentmods](https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/dial.svg)](https://agentmods.dev/skills/jtsternberg/claude-plugins/dial)
Your own site
<a href="https://agentmods.dev/skills/jtsternberg/claude-plugins/dial"><img src="https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/dial.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,601 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 findings. Scan, not verified.
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 $0.00056 $0.09601
Opus 5 $0.00028 $0.04800
Sonnet 5 $0.00011 $0.01920
Haiku 4.5 $0.00006 $0.00960

Measured today against content hash e53bb2e1afa6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

hotline-dial scanned grade D with 2 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 today.

The scan reads SKILL.md. This mod also ships 23 executable files (scripts/check-cmux.sh, scripts/check-herdr.sh, scripts/close-superseded-surface.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Set these in `~/.claude/settings.json`'s `"env"` block or the shell:

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

Clean up when the exchange is done: `rm -rf "$CALL_DIR"`.
plugins/hotline/skills/dial/SKILL.md · 579 lines

How it starts

The opening of the file, as written. The whole thing — 579 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hotline: Dial

Dial another workspace to ask questions, delegate work, or collaborate.

dial.sh does the plumbing — identity, resolution, transport choice, session cache, launch, boot wait — in one command and hands back one JSON object. Your job is the judgment: which workspace, which mode, and what to do about the status it returns.

Arguments

  • $0 (optional): Workspace reference — a dirmap ID, path, session ID, or fuzzy name.
  • $1+ (optional): The task/question for the remote workspace.
  • --headless: force the headless transport (claude -p) for this dial even when cmux is up. Debugging the headless path, A/B-ing transports, or wanting claude -p's structured output. Costs programmatic-usage credit; the cmux default doesn't. → --headless
  • --detached / --new-workspace: spawn the callee in a disconnected new workspace tab instead of a side-by-side surface. The tab auto-closes once the response is captured, so nothing is left to watch or clean up. → --placement detached
  • --window <name|ref>: land the callee as a surface in a specific cmux window (find-or-create), for grouping workers by project. A window:<n> ref targets that window; a bare name reuses the window holding a workspace titled <name>. Wins over --detached if both are given. → --window <name|ref>
  • --herdr: host the callee as a herdr agent instead of a cmux surface — a persistent pane owned by the herdr server, so the callee survives a detach, a closed lid, or a dropped SSH session. That is the reason to ask for it: a long work order you do not want tied to the life of a window. Requires herdr running, here or — with --remote below — on another box. Takes any mode, including conference, and either the side or detached placement (herdr splits a pane off yours for both). → --transport herdr
  • --remote <ssh-target>: run the callee on another box — herdr splits a pane and starts claude there, and hotline reads its answer back over ssh. For work that belongs on that machine: its checkout, its GPU, its network. It selects herdr on its own (nothing else can host anywhere but here) and is detached by nature, so --remote <target> alone is the whole invocation. Needs a non-interactive ssh hop plus herdr and claude on that box; if any of that is missing the dial is an error, never a quiet local call. → --remote <ssh-target>

Read the full file on GitHub · 579 lines

Files

What ships with it

28 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. today Changed · +113 lines · +23 tokens per session e53bb2e1afa6
  2. today Changed · +130 lines b78730aa07ef
  3. 4d ago First seen · 336 lines · 33 tokens per session scan D 5498922efa63

Subscribe to this mod's changes

hotline-dial is a skill published in the GitHub repository jtsternberg/claude-plugins (5 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 9,601 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens