Agent skill

Holdline

by CALLE-AI in CALLE-AI/awesome-phone-call-agents

Ask one question of many places by phone and get back only the answers the call actually established.

MITAuto-check passed

Install Holdline

skills CLI

$ npx skills add CALLE-AI/awesome-phone-call-agents --skill holdline -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install CALLE-AI/awesome-phone-call-agents holdline --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/holdline .claude/skills/holdline && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "holdline" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/holdline into .claude/skills/holdline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "holdline", 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

$skill-installer install https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/holdline

Type 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.

skills CLI

$ npx skills add CALLE-AI/awesome-phone-call-agents --skill holdline -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install CALLE-AI/awesome-phone-call-agents holdline --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/holdline .agents/skills/holdline && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "holdline" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/holdline into .agents/skills/holdline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "holdline", 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.

skills CLI

$ npx skills add CALLE-AI/awesome-phone-call-agents --skill holdline -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install CALLE-AI/awesome-phone-call-agents holdline --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/holdline .cursor/skills/holdline && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "holdline" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/holdline into .cursor/skills/holdline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "holdline", 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

$ gemini skills install https://github.com/CALLE-AI/awesome-phone-call-agents.git --path skills/holdline

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add CALLE-AI/awesome-phone-call-agents --skill holdline -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install CALLE-AI/awesome-phone-call-agents holdline --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/holdline .gemini/skills/holdline && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "holdline" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/holdline into .gemini/skills/holdline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "holdline", 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.

GitHub CLI

$ gh skill install CALLE-AI/awesome-phone-call-agents holdline

Installs 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).

skills CLI

$ npx skills add CALLE-AI/awesome-phone-call-agents --skill holdline -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/holdline .github/skills/holdline && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "holdline" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/holdline into .github/skills/holdline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "holdline", 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.

skills CLI

$ npx skills add CALLE-AI/awesome-phone-call-agents --skill holdline -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install CALLE-AI/awesome-phone-call-agents holdline --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/holdline .opencode/skills/holdline && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "holdline" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/holdline into .opencode/skills/holdline/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "holdline", 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.

Facts

Skill name: holdline
GitHub stars: 107
Token cost: ~1.6k tokens
SKILL.md length: 857 words
Files: 4 (incl. references)
Skills in repo: 101
Repo updated: Oct 10, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Ask one question of many places by phone and get back only the answers the call actually established.

Batch phone enquiries where a wrong answer is worse than no answer — supplier stock checks
SKILL.md covers When to use this, Safety, Setup and Tools, plus 4 more sections
Calls npm and git; reaches github.com; needs CALLE_API_KEY
Capacity and availability enquiries

What it does

Holdline is an agent skill from CALLE-AI/awesome-phone-call-agents. Ask one question of many places by phone and get back only the answers the call actually established. Use for batch phone enquiries where a wrong answer is worse than no answer — supplier stock checks, capacity and availability enquiries, claim and case status, directory verification. Includes evidence checking that catches values a call returns for questions it never asked.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/examples.md`, `references/probes.md` and `references/safety.md`).

The repository describes itself as: Portable phone-call Agent Skills, apps, examples, adapters, and scheduler recipes for AI agents. The licence is MIT.

When your agent uses it

Batch phone enquiries where a wrong answer is worse than no answer — supplier stock checks
Capacity and availability enquiries
Claim and case status
Directory verification

Example prompts

“/holdline”

Requirements

Node.js
A credential in CALLE_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 38d4118. It shows what the files ask for, not the result of running them.

Tool permissions
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.
Runs code
Shell commands in SKILL.md call:
- npm
- git
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- CALLE_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Holdline loads about 1.6k tokens when it runs, and up to ~5k if it reads all its reference files. Until then it costs about 97 tokens; SKILL.md has 857 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~97
When it runs · the whole SKILL.md, loaded when a task matches: ~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~5k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from CALLE-AI/awesome-phone-call-agents at commit 38d4118, republished under its MIT licence (© CALLE-AI). 857 words, ~1,583 tokens.

Download SKILL.mdSave it as .claude/skills/holdline/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.

name: holdline
description: Ask one question of many places by phone and get back only the answers the call actually established. Use for batch phone enquiries where a wrong answer is worse than no answer — supplier stock checks, capacity and availability enquiries, claim and case status, directory verification. Includes evidence checking that catches values a call returns for questions it never asked.

holdline

Place a batch of phone enquiries through CALL-E, then check every returned field against the transcript turns the agent actually spoke. A field whose question was never asked does not come back, whatever the model reported.

When to use this

Use it when the same question goes to several places and a confidently wrong answer causes real damage: sourcing a part across suppliers, checking which clinics have capacity, chasing case status across agencies, verifying that a directory listing is still true.

Do not use it for a conversation, for anything requiring negotiation or judgement on the call, or where a person must decide something in the moment. This asks a fixed question and records the answer.

Safety

Real calls reach real people. run_hold requires confirm: true in the same request. There is no setting that removes the confirmation.
Plan first. plan_hold shows the compiled task, every number it would dial, and what the ledger already knows. It never dials.
Do not guess phone numbers, country codes, or subject ids. Ask the user.
Emergency and crisis-line prefixes are refused unconditionally and cannot be enabled by configuration.
Every number in every response is masked. Do not attempt to reconstruct one, and do not echo raw numbers the user gave you back into a report.
An unknown call outcome is never re-dialed. If run_hold returns outcome: "unresolved", report it and stop; a retry rings a second person.

Setup

This directory is documentation. It contains no runnable code. The three tools below are served by an MCP server that lives in a separate repository, and the commands here only work from a clone of it:

bash

git clone https://github.com/Elioz404/HOLDLINE
cd HOLDLINE
npm install
export CALLE_API_KEY=...   # server-side only, never in client code
npm run mcp                # serves plan_hold, run_hold, get_verdict over stdio

Then point your MCP client at that command. Nothing in this skill directory is executable, and running npm inside it will not work.

Without CALLE_API_KEY, plan_hold still works — planning needs no network — and the dialing tools return an error saying exactly what is missing.

To exercise the tools with no CALL-E account at all, from the same clone:

bash

HOLDLINE_SIMULATE=1 npm run mcp

Every response is then tagged simulated: true with a notice saying no telephone was involved. Treat simulated output as a rehearsal, never as a finding, and say so if you report it.

Tools

`plan_hold`

Compiles the task within CALL-E's 255-character limit, validates every number, derives the idempotency key from the authorizing record, and reports which targets the freshness ledger already answers. Dials nothing.

Start here every time.

`run_hold`

Dispatches the batch as one call task with many recipients, then judges each answer separately. Requires confirm: true.

Returns per target: a verdict, the gated result, and the reasons. Fields the transcript does not support are null.

`get_verdict`

Fetches a call by id and judges it. Use it to re-examine a call, or to reconcile one whose outcome was unknown.

Show full SKILL.md (399 more words)Show less

Reading the verdicts

Verdict	Meaning
`verified`	The agent raised the topic and a usable answer came back.
`asked_but_unclear`	The agent asked; the answer was not usable.
`unattributed`	Some question was asked and answered, but none of this field's probes match it, so the answer cannot be pinned here.
`attributed`	No probe matched, but exactly one question went unclaimed and this was the only unmatched field, so the answer can only have come from it. Weaker evidence than a match, and reported as such. Only appears when elimination is enabled.
`never_asked`	Nothing was asked that this value could answer. If a value came back anyway, it is flagged.
`no_transcript`	No transcript, so nothing could be checked.

A batch verdict is verified only when every required field is verified — or attributed, if the caller enabled elimination — and completion confidence clears the floor. There is no partial pass.

never_asked with a value present is the case worth surfacing to the user: the call returned something the conversation does not support.

Writing probes

A probe is the list of phrases that identify the agent raising a topic. Write the words the agent would actually say, not the field name.

json

{ "name": "accepts_new_patients", "asks": ["new patients", "accepting new", "taking patients"] }

Matching is lexical, so a question phrased in words no probe contains reads as unattributed and is withheld. That is the safe direction, but it costs a real answer — see references/probes.md before writing them for a new workflow.

Every result carries unclaimedQuestions: the questions the agent asked that no probe claimed, verbatim. If one of them is the question you meant to ask, add its wording to that field. That is the fix; elimination is the fallback.

Side effects and cancellation

run_hold places outbound calls, billed per call, one per dialable target, dispatched together. Each target carries its own idempotency key derived from batchId, workflow, intent and that target's subject id; running the batch again fetches each existing call rather than dialing anyone a second time.

One call per target rather than one call with many recipients, because a multi-recipient call returns no transcript turns and this skill has nothing to verify without them.

Nothing in this skill schedules recurring work, so there is nothing to cancel. A batch in flight cannot be recalled — the confirmation before dispatch is the only stopping point.

References

references/safety.md — what a phone answer proves, and what it does not.
references/probes.md — writing probes, and the failure they trade against.

Files

SKILL.md and 3 other files (references) in skills/holdline of CALLE-AI/awesome-phone-call-agents.

SKILL.md
references/examples.md
references/probes.md
references/safety.md

Open the folder on GitHubat commit 38d4118

Compare with similar skills

Holdline 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.

Holdline compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Holdline this skillCALLE-AI/awesome-phone-call-agents	107	—	~1.6k	Automated safety check: Pass	MIT	yesterday
PhoneBlockRunAI/ClawRouter	6.6k	—	~2.4k	Automated safety check: Pass	MIT	5 days ago
Five Questionsbrycewang-stanford/Auto-Empirical-Research-Skills	4.6k	—	~1.7k	Automated safety check: Notes	Custom licence	5 days ago
Discovery Question Formnexu-io/open-design	100k	—	~1.5k	Automated safety check: Pass	Apache-2.0	yesterday
Many Chat AutomationComposioHQ/awesome-claude-skills	77k	3 repos	~736	Automated safety check: Pass	None	23 days ago
Ask User QuestionMemTensor/MemOS	12k	—	~1k	Automated safety check: Pass	Apache-2.0	2 days ago

Similar skills

Phone
BlockRunAI/ClawRouter
Verify phone numbers (carrier + SIM-swap fraud signals) and place AI-powered outbound voice calls via BlockRun's gateway (Twilio + Bland.ai).
6.6k GitHub stars~2.4k tokensUpdated 5 days ago
Auto-check passed
Five Questions
brycewang-stanford/Auto-Empirical-Research-Skills
Deeply analyze any empirical economics PDF using the five-question framework (五问框架): research question, identification strategy, core estimand, robustness logic, and scholarly contribution.
4.6k GitHub stars~1.7k tokensUpdated 5 days ago
Documents & OfficeAuto-check: notes
Discovery Question Form
nexu-io/open-design
Structured clarification form for unresolved material requirements.
100k GitHub stars~1.5k tokensUpdated yesterday
Agent WorkflowsAuto-check passed
Many Chat Automation
ComposioHQ/awesome-claude-skills
Automate ManyChat tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.
77k GitHub starsUsed in 3 repos~736 tokens
Productivity & AutomationAuto-check passed
Ask User Question
MemTensor/MemOS
Shows a question as a modal in the interface to clarify a task, collect a preference or get approval, since the user cannot see terminal output.
12k GitHub stars~1k tokensUpdated 2 days ago
Agent WorkflowsAuto-check passed
Phone Harness
milind-soni/OpenMausBot
Control, inspect, test, or automate a physical Android phone connected to OpenMausBot over authorized USB debugging.
4.4k GitHub stars~364 tokensUpdated today
MobileAuto-check passed

More from CALLE-AI/awesome-phone-call-agents

All 101 skills in this repo

Accessible Outing Verifier
CALLE-AI/awesome-phone-call-agents
Demonstrates advisory accessibility-planning checks with offline fixtures and a proposed bounded CALL-E workflow; use for exploring unknown or qualified venue claims without making calls.
107 GitHub stars~1.4k tokensUpdated yesterday
Auto-check passed
Ground Truth Gate
CALLE-AI/awesome-phone-call-agents
A skill your agent uses when an agent holds some evidence for a physical-world claim but the evidence is broader, narrower, or older than the exact question asked, and it must first decide whether a…
107 GitHub stars~3.3k tokensUpdated yesterday
Auto-check passed
Is It Accessible
CALLE-AI/awesome-phone-call-agents
Call a venue and ask the accessibility questions that matter to one specific person — step-free entry, hearing loop, guide dogs, quiet hours, changing places — then return a per-need verdict backed…
107 GitHub stars~4.3k tokensUpdated yesterday
Auto-check passed
Landmark Navigation Assist
CALLE-AI/awesome-phone-call-agents
Turns a pre-written, building-level location config into a CALL-E outbound phone-call task that guides a delivery driver through the last few hundred metres to a specific building using landmarks…
107 GitHub stars~1.6k tokensUpdated yesterday
Auto-check passed
Research Gap Call Verifier
CALLE-AI/awesome-phone-call-agents
Turn cited business research into a bounded, approval-gated phone-call plan that asks only unresolved factual questions, then reconcile CALL-E-compatible results without treating voicemail, refusal…
107 GitHub stars~1.7k tokensUpdated yesterday
Auto-check passed
Structured Outcome Followup Call
CALLE-AI/awesome-phone-call-agents
Place a goal-driven CALL-E call that collects specific structured answers, score those answers against a deterministic rubric you supply, and conditionally trigger a follow-up action — all runnable…
107 GitHub stars~1.4k tokensUpdated yesterday
Auto-check passed

Questions about Holdline

What does Holdline do?

Ask one question of many places by phone and get back only the answers the call actually established. Holdline is an agent skill from CALLE-AI/awesome-phone-call-agents. Ask one question of many places by phone and get back only the answers the call actually established.

When should I use Holdline?

Holdline fits situations like: batch phone enquiries where a wrong answer is worse than no answer — supplier stock checks; capacity and availability enquiries; claim and case status; directory verification.

How do I install Holdline in Claude Code?

Run `npx skills add CALLE-AI/awesome-phone-call-agents --skill holdline -a claude-code`. Or copy the skill folder (skills/holdline in CALLE-AI/awesome-phone-call-agents) into .claude/skills/holdline in your project. Claude Code loads it when a task matches its description.

How do I install Holdline in Codex?

Run `npx skills add CALLE-AI/awesome-phone-call-agents --skill holdline -a codex`. Or copy the skill folder (skills/holdline in CALLE-AI/awesome-phone-call-agents) into .agents/skills/holdline in your project. Codex loads it when a task matches its description.

Can I use Holdline in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add CALLE-AI/awesome-phone-call-agents --skill holdline -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/holdline, .gemini/skills/holdline, .github/skills/holdline and .opencode/skills/holdline in your project.

What does Holdline need to run?

Going by SKILL.md and its folder, Holdline needs the command-line tools its instructions call (npm and git) and credentials named CALLE_API_KEY. Our summary lists: Node.js; A credential in CALLE_API_KEY.

Does Holdline access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Holdline safe to install?

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.

What licence does Holdline use?

Holdline is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Holdline use?

About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.4k tokens, read only when the agent opens those files.

What are the alternatives to Holdline?

Skills that share tags, products or a category with Holdline: Phone (BlockRunAI/ClawRouter, 6.6k stars), Five Questions (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars), Discovery Question Form (nexu-io/open-design, 100k stars) and Many Chat Automation (ComposioHQ/awesome-claude-skills, 77k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Holdline?

CALLE-AI (a GitHub organization) maintains it in CALLE-AI/awesome-phone-call-agents, which has 107 GitHub stars. The repository holds 101 skills in this directory. The repository was last updated on October 10, 2026.

Source: CALLE-AI/awesome-phone-call-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Holdline

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

holdline

When to use this

Safety

Setup

Tools

plan_hold

run_hold

get_verdict

Reading the verdicts

Writing probes

Side effects and cancellation

References

Files

Compare with similar skills

Similar skills

More from CALLE-AI/awesome-phone-call-agents

Questions about Holdline

`plan_hold`

`run_hold`

`get_verdict`