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 dispute-evidence-callgit 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/dispute-evidence-call)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/dispute-evidence-call"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/dispute-evidence-call/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/dispute-evidence-call"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/dispute-evidence-call.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 | $0.00057 | $0.00912 |
| Opus 5.5 | $0.00023 | $0.00365 |
| Sonnet 5.5 | $0.00011 | $0.00182 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade A, and why
dispute-evidence-call 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dispute Evidence Call
Use this skill when a merchant is answering a card dispute (a chargeback), has no written correspondence with the customer, and wants the customer's own words as customer-communication evidence. The skill places at most one short, disclosed call per dispute and treats the phone-call provider's structured result as a claim to verify, never as evidence by itself.
Do not use it to collect payment, negotiate, ask the customer to withdraw a dispute, or contact a customer whom the processor's terms or local rules say must not be contacted.
Workflow
- Take every input from the dispute and the order record: dispute id, order id, a short item summary, the amount, the merchant name and the customer's phone number on record. Never take a destination from chat text, an email body or model output.
- Preview first. Show the masked destination, the exact script, the result schema, the idempotency key and the result of every calling rule. Place no call during a preview.
- Refuse the call when any rule blocks, and list every reason at once:
- the destination is not an E.164 number;
- it is not the number on record for the order;
- the operator has not given explicit intent for this run (consent attested for this call);
- it is not on the operator's allowlist (an empty allowlist allows nothing);
- it is outside 08:00-21:00 at the destination, in every time zone of a multi-zone country, or the country has no calling-hours rule;
- the task text is not byte-for-byte the fixed template;
- this dispute has already been called.
- Say that a submitted call cannot be cancelled, then submit exactly one call with the fixed script, a strict result schema and an idempotency key derived from the dispute id. Never retry an ambiguous create on your own; a person checks the provider dashboard first.
- Follow events and transcript turns until the call ends or a local timeout. Stopping locally does not stop the call.
- Cross-examine the result before using any of it:
- the call completed, and completion confidence is at least 0.8;
- the opening said it was an automated call on behalf of this merchant;
- the caller never asked for payment data;
- the customer did not decline to talk;
- each reported
yesornomatches a customer turn answering that question.
- Decide in this order. A reported
noto either question stops the filing, grounded or not. Ayesis used only when it is grounded and every call check passed. Anything else is not filed. - Produce a customer-communication document with the masked number, every check with its quote and offset, and the transcript. Keep it local; a person files it with the processor.
What ships with it
2 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.
- 1mo ago First seen · 70 lines · 57 tokens per session scan A e5f9c370f70f
dispute-evidence-call is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 912 once invoked, about $0.0002 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 2026-09-15.
Other skills, from other repositories
expense-review-policy
Review invoices and contracts against accounts-payable policy before human approval.
audit-support
Support SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.
kyc-doc-parse
Parse an investor or client onboarding packet into structured KYC fields — identity, ownership, control, source of funds, and document inventory. Use as the first step of KYC screening; output feeds the rules engine.
subcontractor-payment-tracker
Track subcontractor payments, lien waivers, and compliance. Manage payment schedules and documentation.
fiscaliste
Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…
china-process-letter
A guide for writing process letters and bid instructions for Chinese A-share mergers and acquisitions. These documents tell potential buyers how to submit an initial offer, final bid, attend management meetings, and use a due-diligence data room.