New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Cod Order Confirmation Call

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

Prepare one authorized cash-on-delivery order confirmation call.

MITAuto-check passed

Install Cod Order Confirmation Call

skills CLI
$ npx skills add CALLE-AI/awesome-phone-call-agents --skill cod-order-confirmation-call -a claude-code

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

GitHub CLI
$ gh skill install CALLE-AI/awesome-phone-call-agents cod-order-confirmation-call --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/cod-order-confirmation-call .claude/skills/cod-order-confirmation-call && 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/

Facts

Skill name
cod-order-confirmation-call
GitHub stars
107
Token cost
~1.8k tokens
SKILL.md length
665 words
Files
5 (incl. scripts, references, assets)
Skills in repo
101
Repo updated
First seen
Licence
MIT

At a glance

Prepare one authorized cash-on-delivery order confirmation call.

  • Works in 4 steps: Confirm the operator or the calling… → Confirm to_phone_e164 came from the… → Refuse if do_not_call is true, consent… → …
  • SKILL.md covers When To Use, When Not To Use, Required Inputs and Preflight, plus 7 more sections
  • Runs Python scripts from its folder; calls python3; needs CALLE_API_KEY

What it does

Cod Order Confirmation Call is an agent skill from CALLE-AI/awesome-phone-call-agents. Prepare one authorized cash-on-delivery order confirmation call. Compiles a CALL-E brief and advisory result schema from order rows, leaving result validation and status changes to the calling system or a human. Dry-run preview by default.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts, reference files and assets (for example `assets/sample-order.json`, `references/examples.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.

Example prompts

  • “/cod-order-confirmation-call”

Requirements

  • Python 3
  • A credential in CALLE_API_KEY

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Confirm the operator or the calling system authorized this one confirmation call.
  2. Confirm to_phone_e164 came from the order record and is in a CALL-E supported country.
  3. Refuse if do_not_call is true, consent is not true, or the order has no items.
  4. Run the local preview before any CALL-E plan.

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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    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

Cod Order Confirmation Call loads about 1.8k tokens when it runs, and up to ~2.5k if it reads all its reference files. Until then it costs about 67 tokens; SKILL.md has 665 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.5k

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); the scripts in this folder 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). 665 words, ~1,786 tokens.

Download SKILL.mdSave it as .claude/skills/cod-order-confirmation-call/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
cod-order-confirmation-call
description
Prepare one authorized cash-on-delivery order confirmation call. Compiles a CALL-E brief and advisory result schema from order rows, leaving result validation and status changes to the calling system or a human. Dry-run preview by default.
license
MIT

COD Order Confirmation Call

Use this skill when a shop, marketplace or chat-commerce system has explicit authority to place one disclosed phone call to confirm a cash-on-delivery order the customer already placed. The call reads back the items and total exactly as recorded, confirms the delivery address, records requested changes, and returns a structured disposition. It never invents items, prices or delivery promises.

This skill does not execute calls, validate returned results or change order status itself. The compiler prepares a task and schema; the host must review the advisory result before applying its own rules. The external reference uses heuristic confirmation and cancellation rules, not a guarantee that every ambiguous answer reaches a human.

When To Use

  • Confirm a COD order that arrived through WhatsApp, Instagram, Messenger, a web shop or a marketplace
  • Reduce fake, duplicate or forgotten COD orders before goods are prepared and dispatched
  • Capture an address correction or an item change the customer asks for
  • Produce an evidence-backed disposition for the operations team

When Not To Use

  • First-contact sales, upselling or unsolicited marketing
  • Collecting card details, ID numbers, or any payment on the call
  • Medical, legal, financial, collections or political calls
  • Calling a number that did not come from the order record
  • Hidden retries or recurring reminder schedules

Required Inputs

  • order_ref: short human reference read on the call
  • business_display_name: name disclosed on the call
  • customer_name (optional) and to_phone_e164 (E.164, from the order record)
  • items[]: { name, variant?, quantity, unit_price } from the order rows, not from a chat transcript
  • currency, total, optional delivery_fee
  • delivery_address (optional — if absent the caller collects it)
  • delivery_policy (optional short text the caller may quote)
  • language (optional), timezone (IANA)
  • consent: must be true; do_not_call: must be false

Preflight

  1. Confirm the operator or the calling system authorized this one confirmation call.
  2. Confirm to_phone_e164 came from the order record and is in a CALL-E supported country.
  3. Refuse if do_not_call is true, consent is not true, or the order has no items.
  4. Run the local preview before any CALL-E plan.

Dry-Run Preview

From the repository root (no CALL-E credentials, no network):

bash
python3 skills/cod-order-confirmation-call/scripts/build_task.py skills/cod-order-confirmation-call/assets/sample-order.json

Prints display copies of the compiled CALL-E task, result_schema, and idempotency key with phone-like text masked throughout. It does not dial. The internal build(order) result retains the private task for a separately authorized host integration; do not treat masked preview output as an approved live payload.

CALL-E Goal Template

text
You are calling on behalf of {business_display_name} to confirm a cash-on-delivery order
before it is prepared and dispatched. Disclose that you are an AI assistant.
Customer: {customer_name}. Order reference {order_ref}, placed {placed_at_friendly}.
Items: {quantity} x {item} at {unit_price}; ...
Delivery fee: {delivery_fee}. Total to pay in cash on delivery: {total}.
Delivery address on file: {delivery_address} (or: No delivery address is on file — ask for it).
Delivery policy: {delivery_policy}.
Goal: 1) greet and say you are calling from the shop to confirm their order; 2) read back the
items and the total; 3) confirm the delivery address or collect it; 4) ask if they want any
change and record it precisely; 5) if they no longer want the order, accept politely.
Rules: never invent items, prices, discounts or delivery times not in this brief. If asked
something you do not know, say a team member will follow up. Keep the call under two minutes.
On voicemail, leave a short message saying who you are and end the call.
Show full SKILL.md (268 more words)Show less

Structured Result

json
{
  "disposition": "confirmed | changed | cancelled | voicemail | no_answer | wrong_number | needs_human",
  "confirmed": "yes | no | unknown",
  "address_correct": "yes | no | unknown",
  "delivery_address": "as stated by the customer, or empty",
  "requested_changes": "exact changes requested, or empty",
  "preferred_delivery_window": "stated preference, or empty",
  "customer_notes": "anything else the team should know"
}

Only disposition = confirmed and confirmed = yes with high completion confidence should flip an order to confirmed. changed, voicemail, no_answer, wrong_number, needs_human and any low-confidence result need a human. cancelled may cancel the order only if the calling system's rules allow it.

Live Planning And Execution

The following SDK call executes a real call; it is not a plan. Run it only after final per-call approval of the reviewed task and authorized E.164 destination, and CALL-E authentication:

ts
import { CalleClient } from "@call-e/calle";
const client = new CalleClient({ apiKey: process.env.CALLE_API_KEY! });
const call = await client.calls.create(
  { task, recipients: [{ phones: ["<E164_PHONE>"], region: "<REGION>" }], resultSchema, recipientResultSchema: resultSchema, metadata: { order_ref } },
  { idempotencyKey: `cod-confirm:${order_ref}:1` },
);

Planning via the CALL-E CLI is also valid and is not execution:

bash
calle call plan --to-phone <E164_PHONE> --goal "<reviewed task text>" --timezone Asia/Beirut --language English --region GB

For the CLI, do not execute the resulting plan unless the operator or calling system separately confirms this call. Creating a plan alone is not that approval.

Cancellation And Idempotency

Idempotency key: cod-confirm:{order_ref}:{attempt}. Persist it before the first request and reuse it on retries. One call per order per attempt; never retry automatically on unknown, voicemail or no answer — route to a human.

Before submission, cancel by discarding the preview or plan. After submission, stopping this script or closing a page does not recall an accepted call. Use supported provider controls and treat cancellation as unconfirmed until the provider confirms it. Reconcile an unknown outcome before authorizing another attempt; a stable key is not a crash-proof or permanent duplicate-prevention guarantee.

Reference Implementation

FrontDesk Phone Follow-Through (see docs/community-apps/frontdesk-phone-follow-through.md) runs this skill inside a multi-tenant WhatsApp AI front desk: a Confirm by phone button on the Orders page and an optional auto-confirm timer, with the result written back to the order and posted as a note in the customer's inbox thread.

Safety Notes

Read references/safety.md and references/examples.md before live planning.

© CALLE-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts, references, assets) in skills/cod-order-confirmation-call of CALLE-AI/awesome-phone-call-agents.

  • SKILL.md
  • assets/sample-order.json
  • references/examples.md
  • references/safety.md
  • scripts/build_task.py

Open the folder on GitHubat commit 38d4118

Compare with similar skills

Cod Order Confirmation Call 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.

Cod Order Confirmation Call compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cod Order Confirmation Call this skillCALLE-AI/awesome-phone-call-agents107—~1.8kAutomated safety check: PassMIT
Food Orderingasgeirtj/system_prompts_leaks69k—~1.4kAutomated safety check: PassCC0-1.0
Preparing Deliveryrapidaai/voice-ai745—~678Automated safety check: PassCustom licence
Hermes Agent Skill AuthoringNousResearch/hermes-agent252k—~3.6kAutomated safety check: PassMIT
Configuring Oauth2 Authorization Flowmukul975/Anthropic-Cybersecurity-Skills34k—~1.7kAutomated safety check: PassApache-2.0
Executing Nist Rmf Authorization To Operatemukul975/Anthropic-Cybersecurity-Skills34k—~2.2kAutomated safety check: PassApache-2.0

Similar skills

  • Food Ordering

    asgeirtj/system_prompts_leaks

    Prepare restaurant food orders for delivery or pickup; use for cart, checkout and tracking.

    69k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Preparing Delivery

    rapidaai/voice-ai

    Prepare a verified change for commit, push, or pull request after the user explicitly requests that delivery action.

    745 GitHub stars~678 tokensUpdated 4 days ago
    DevelopmentAuto-check passed

  • Hermes Agent Skill Authoring

    NousResearch/hermes-agent

    Author in-repo SKILL.md files: frontmatter and structure. An agent skill from NousResearch/hermes-agent.

    252k GitHub stars~3.6k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Configuring Oauth2 Authorization Flow

    mukul975/Anthropic-Cybersecurity-Skills

    Configures secure OAuth 2.0 authorization flows, including Authorization Code with PKCE, Client Credentials, and Device Authorization Grant, covering flow selection, PKCE implementation, token…

    34k GitHub stars~1.7k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed

  • Executing Nist Rmf Authorization To Operate

    mukul975/Anthropic-Cybersecurity-Skills

    Drive a federal system through the NIST Risk Management Framework (SP 800-37 Rev 2) to an Authorization to Operate (ATO): Prepare, Categorize (FIPS 199), Select a control baseline (FIPS 200 / SP…

    34k GitHub stars~2.2k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed

  • Authoring Skills

    vercel/next.js

    Official

    How to create and maintain agent skills in .agents/skills/. An agent skill from vercel/next.js.

    143k GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-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 today
    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 today
    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 today
    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 today
    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 today
    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 today
    Auto-check passed

Questions about Cod Order Confirmation Call

What does Cod Order Confirmation Call do?

Prepare one authorized cash-on-delivery order confirmation call. Cod Order Confirmation Call is an agent skill from CALLE-AI/awesome-phone-call-agents. Prepare one authorized cash-on-delivery order confirmation call.

How do I install Cod Order Confirmation Call in Claude Code?

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

How do I install Cod Order Confirmation Call in Codex?

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

Can I use Cod Order Confirmation Call 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 cod-order-confirmation-call -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cod-order-confirmation-call, .gemini/skills/cod-order-confirmation-call, .github/skills/cod-order-confirmation-call and .opencode/skills/cod-order-confirmation-call in your project.

What does Cod Order Confirmation Call need to run?

Going by SKILL.md and its folder, Cod Order Confirmation Call needs Python for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named CALLE_API_KEY. Our summary lists: Python 3; A credential in CALLE_API_KEY.

Does Cod Order Confirmation Call access the network?

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.

Is Cod Order Confirmation Call 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Cod Order Confirmation Call use?

Cod Order Confirmation Call is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cod Order Confirmation Call use?

About 1.8k tokens (SKILL.md is roughly 7.1k 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 701 tokens, read only when the agent opens those files.

What are the alternatives to Cod Order Confirmation Call?

Skills that share tags, products or a category with Cod Order Confirmation Call: Food Ordering (asgeirtj/system_prompts_leaks, 69k stars), Preparing Delivery (rapidaai/voice-ai, 745 stars), Hermes Agent Skill Authoring (NousResearch/hermes-agent, 252k stars) and Configuring Oauth2 Authorization Flow (mukul975/Anthropic-Cybersecurity-Skills, 34k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cod Order Confirmation Call?

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.