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.
npx skills add CALLE-AI/awesome-phone-call-agents --skill calle-invoice-recoverygit clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agentsWrote 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.
[](https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/calle-invoice-recovery)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/calle-invoice-recovery"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/calle-invoice-recovery/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.
<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/calle-invoice-recovery"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/calle-invoice-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.05270 |
| Opus 5 | $0.00023 | $0.02635 |
| Sonnet 5 | $0.00009 | $0.01054 |
| Haiku 4.5 | $0.00005 | $0.00527 |
Grade A, and why
calle-invoice-recovery 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CALL-E Invoice Recovery Skill
A reusable phone-call skill that contacts a named client about an unpaid invoice via CALL-E, holds a multi-turn conversation to understand the client's situation, offers a payment arrangement when appropriate, and records the outcome (paid, committed-to-date, escalated, or unresponsive) for human review. Every action is draft-then-approve: the operator reviews the call script and any proposed arrangement before the call is placed or any commitment is logged.
This edition is a workflow reference and offline preview. The only bundled executable is scripts/dry-run.ts, which cannot place calls. The live workflow and safety requirements below are instructions for an integrating host, not a shipped approval UI, transport, scheduler, or database. The host must provide and verify those controls before live use. See the operator guide.
When To Use
Use this skill when a freelancer or small agency needs to follow up on an overdue invoice with an overseas client via a phone call placed through CALL-E. The client must be reachable in a CALL-E-supported region (US, SG, MY, IN, AE, AU, CA, GB, VN, DE, JP, FR, MX, BR, ID, PH, KE, BD) and the conversation must be conducted in a CALL-E-supported language for that region (default: English; Bengali is not supported, so calls to Bangladesh are placed in English).
When Not To Use
- The client requires a language CALL-E does not support (e.g. Bengali), or is in a region CALL-E does not support.
- The operator has not explicitly authorized the call.
- No invoice reference number and amount are available to anchor the conversation.
- The debt is disputed or involves active legal proceedings — refer to a collections attorney.
Conversation Flow
The flow has five sequential phases. Every phase must complete before the call closes; every branch must terminate in one of the four defined outcomes (paid, committed_to_date, escalated, unresponsive). The agent never closes the call in an undefined state.
What ships with it
6 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.
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.
- today First seen · 326 lines · 47 tokens per session scan A 2d7845aa8d9a
calle-invoice-recovery is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (88 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 5,270 once invoked, about $0.0002 per session on Opus 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 2026-09-12.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.