Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agentsnpx agentmods add skills/calle-ai/awesome-phone-call-agents/countercallWrote 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/countercall)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/countercall"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/countercall/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/countercall"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/countercall.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 | $0.00077 | $0.02785 |
| Opus 5.5 | $0.00031 | $0.01114 |
| Sonnet 5.5 | $0.00015 | $0.00557 |
| Haiku 4.5 | $0.00008 | $0.00279 |
Grade A, and why
countercall 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 23d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CounterCall
Pak Yanto took the morning off work, rode forty minutes to the Samsat counter, and was turned away because his photocopy was folio instead of A4. He lost a day's income, and he still did not know what else was missing for tomorrow.
Public service counters publish requirement lists that are incomplete, outdated, or quietly contradicted at the window. The one reliable source is the office's phone line, and that line is busy, IVR-gated, and answered on the fourth try. So people do not call. They travel, they queue, and they get turned away over one document.
This skill makes the call instead, and returns a checklist the person can screenshot and take with them.
It is a good fit for CALL-E's design: low-frequency, personal, high-stakes phone work against a number that a human would otherwise have to redial all morning.
Before you start
This skill places a real phone call to a real public office. Confirm with the user:
- which procedure they are asking about, in the office's own words
- which office, and the phone number in E.164 format, from the office's published page
- that they want a call placed now
Never infer a phone number. Not from a directory, not from a similar office, not by guessing a country code. A number enters the flow only when a human has read it off the office's own published page. Calling the wrong number means an automated caller reaches a stranger, which is the worst thing this skill can do.
Safety boundaries
This skill gathers counter requirements only.
- It does not submit an application, book an appointment, pay a fee, or commit the user to anything. It asks and reports.
- It does not give legal or immigration advice. If a clerk suggests an alternative route, report it verbatim as something the clerk said, never as a recommendation.
- A clerk's spoken answer is informational, not legally binding, and every rendered result says so. Requirements change and individual counters apply discretion.
- It states plainly at the start of the call that it is an automated assistant, and why it is calling. If the person declines to answer, it thanks them and ends the call. It does not persist, re-ask, or call back the same day.
- One call per office per procedure per day. These are public service lines staffed by people with a queue in front of them. The idempotency key enforces this; do not remove it.
- When the clerk is unsure, the result says unsure. It never fills a gap with what is typical, and it never presents a hedge as a fact. A person may travel across a city on the strength of this answer.
- Call offices during their published opening hours only. A public line ringing out at
22:00 is not a data point, it is a nuisance. The code does not check this: the seed
file carries no hours, and
call.mjs --liveandbench.mjs --livewill dial at any time of day. Checking the office's hours before either is the operator's job.
What ships with it
10 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.
- data/offices.json 322 B
- references/examples.md 4.6 KB
- references/result-contract.md 4.3 KB
- references/safety.md 4.0 KB
- scripts/_lib.mjs 8.3 KB runs code
- scripts/call.mjs 5.0 KB runs code
- scripts/contract.mjs 9.8 KB runs code
- scripts/preflight.mjs 5.8 KB runs code
- scripts/render.mjs 5.5 KB runs code
- scripts/transport.mjs 11 KB runs code
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.
- 23d ago First seen · 230 lines · 77 tokens per session scan A 9771dc6ec127
countercall is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 2,785 once invoked, about $0.0003 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 2026-09-27.
Other skills, from other repositories
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…