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/phone-scoutWrote 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/phone-scout)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/phone-scout"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/phone-scout/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/phone-scout"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/phone-scout.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 | $0.00036 | $0.05707 |
| Opus 5.5 | $0.00014 | $0.02283 |
| Sonnet 5.5 | $0.00007 | $0.01141 |
| Haiku 4.5 | $0.00004 | $0.00571 |
Grade A, and why
phone-scout 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 11d 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 — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PhoneScout — Multi-Agent Phone Research
Research the real world by phone. Give PhoneScout a research objective like "find a restaurant for 8 tonight with vegetarian options under R500" and it discovers businesses, calls them through CALL-E, extracts structured results, verifies against your constraints, and returns an evidence-backed ranked recommendation.
PhoneScout thinks in terms of research objectives, not phone calls. Phone calls are the execution mechanism underneath the research workflow. When the user asks "find me…", "compare…", "research…" — NOT "call…" — this is the skill.
When to use
- "Find me a restaurant in [city] for [N] people with [requirements]"
- "Compare dentists near me that can see me this week for under R[amount]"
- "Research hotels that have [feature] and check availability"
- "Which [business type] in [area] can do [thing] before [deadline]?"
When NOT to use
- Making a booking/reservation → use
call-e-bookingskill - Just looking up a phone number → web search / maps
- One simple question about one business → direct CALL-E call via
call-e-booking - General web research with no phone verification needed → web search
Interactive gathering (ask before calling)
The user rarely gives every detail upfront. Never guess or assume missing information. Ask follow-up questions until you have enough to build a well-scoped research plan. Ask the user for any missing fields below.
First-run setup (host-dependent preferences)
On every task, check the current request or consented host memory for these three keys. If any are missing, ask the user one question at a time. This CLI does not implement persistent memory; ask again when the host has not retained it:
| Memory key | Question if missing | Why |
|---|---|---|
currency |
"What currency do you usually use? R, $, €, £?" | Budget prompts say $500 instead of R500 |
home_city |
"Which city are you in? (or where do you search most?)" | Becomes the default when you don't mention a city |
timezone |
"What timezone are you in? e.g. Africa/Johannesburg, America/New_York" | Log timestamps match your local time |
What ships with it
4 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.
- 11d ago First seen · 461 lines · 36 tokens per session scan A 37bedbae2bc1
phone-scout is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 5,707 once invoked, about $0.0001 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 2026-10-09.
Other skills, from other repositories
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
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.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
oma-scholar
Search academic literature and generate, validate, or compare Knows paper sidecars. Use for claim/evidence analysis and literature synthesis.
oma-hwp
Convert Hangul HWP, HWPX, or HWPML documents to Markdown with kordoc. Use for text, table, and image extraction from these formats.
browser_cdp
A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.