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 verify-contact-claimgit 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/verify-contact-claim)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/verify-contact-claim"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/verify-contact-claim/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/verify-contact-claim"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/verify-contact-claim.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.02553 |
| Opus 5 | $0.00037 | $0.01277 |
| Sonnet 5 | $0.00015 | $0.00511 |
| Haiku 4.5 | $0.00007 | $0.00255 |
Grade A, and why
verify-contact-claim 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 12d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Contact Claim
Somebody got a call, a voicemail or a text claiming to be their bank, a delivery firm, a school or a clinic. They want to know whether it was real before they ring anybody back.
This skill checks a contact event, not a standing fact. It does not ask whether the institution exists. It asks whether that institution contacted this person about this subject inside the window the claim file names, an hour by default.
It drives the runnable
verify-contact-claim app, which
rings one number only, the trusted number from the claim file, states that it is an
automated assistant calling on behalf of a named person and returns a verdict, the
callee's own words and the number the customer should be using.
When to use
- A voicemail, a text or a missed call asking the person to ring back.
- The user asks whether a message that claims to be their bank is real.
- The number in the message is not the number printed on the card.
- The user is about to ring the number they were given. Check it first.
When not to use
- A scam call is live on the other line. This takes minutes, not seconds. Tell the user to hang up and ring the printed number themselves.
- There is no trusted number from the customer's own card, statement or bill. Do not search the web for one and never use the number that made contact.
- The claim carries an account number, a card number, a one time code, a PIN, a password, a date of birth or a national id. Remove it, then preview again.
- The user wants the number that contacted them dialled. Refuse and say why.
- Anything medical, legal, financial advice or an emergency. Read
references/safety.md. - The user wants a friendlier answer after a refusal to confirm. One run per claim.
The claim file
| Field | Notes |
|---|---|
claim_id |
3 to 64 characters of letters, digits, dot, dash or underscore. It travels into the idempotency key, so a retry reuses the call instead of ringing twice. |
customer.name |
Who the contact was about. Spoken on the call. |
contact.claimed_to_be |
Who the message said it was. Spoken. |
contact.channel |
voicemail, text_message, missed_call or answered_call. |
contact.arrived_at |
ISO 8601 with an offset, for example 2026-07-31T09:12:00-07:00. |
contact.claimed_about |
The subject in a few neutral words, 80 characters. Spoken. |
contact.number_shown |
The number the handset showed. Never dialled. Masked in output. |
contact.asked_for |
What the caller wanted the customer to do. Scanned, never spoken, never sent. |
trusted_number.phone |
E.164. The only number that gets dialled. Read off the customer's own card or bill. |
trusted_number.printed_on |
Where they read it, in their own words. Required, so the anchor is written down. A source that is the message, the handset, a caller id, a link or a search result is refused. |
trusted_number.region |
Optional, for example US. |
policy.recent_window_minutes |
The window the question asks about. 60 by default, 15 to 240. |
policy.per_call_timeout_seconds |
240 by default, 60 to 600. |
policy.language |
BCP 47, en-US by default. |
policy.min_confidence |
Floor on CALL-E's completion confidence. 0.5 by default. |
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.
- 12d ago First seen · 182 lines · 75 tokens per session scan A 94deda8f94e2
verify-contact-claim is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (88 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 2,553 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…