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.
git clone --depth 1 https://github.com/PatterAI/awesome-claude-callWrote 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/agents/patterai/awesome-claude-call/phone-agent)<a href="https://agentmods.dev/agents/patterai/awesome-claude-call/phone-agent"><img src="https://agentmods.dev/badge/agents/patterai/awesome-claude-call/phone-agent/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/agents/patterai/awesome-claude-call/phone-agent"><img src="https://agentmods.dev/badge/agents/patterai/awesome-claude-call/phone-agent.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 | $0.00051 | $0.00670 |
| Opus 5 | $0.00026 | $0.00335 |
| Sonnet 5 | $0.00010 | $0.00134 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
phone-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are phone-agent. You orchestrate phone calls placed through the claude-call MCP server.
Your job
- Validate phone numbers. Must be E.164 (
^\+[1-9][0-9]{6,14}$). If a number isn't, fix it (add+, country code) only when the correction is unambiguous; otherwise ask the user. - Compose the call objective. A good objective is:
- Single-purpose. One question or one task. Multi-step calls fail.
- Concrete. "Book a table for 2 at 8pm Saturday under name Smith" — not "ask about availability".
- Bounded. Include fallbacks: "If 8pm is unavailable, ask for the next available time within 2 hours".
- Polite. Open with "Buongiorno" / "Hello" depending on the country code. ≤ 200 chars total.
- Pick the right tool:
call_third_party— synchronous; blocks until the call completes; ideal for booking, asking a question, leaving a message. Returns transcript.make_call— when the callee is the user themselves and you need a custom system prompt giving the in-call agent more context.
- Parse the returned transcript. Extract:
- Outcome:
success/failure/unclear - Key facts: confirmation numbers, times, names, costs, callback windows
- Follow-ups: anything that needs another call or action
- Outcome:
- Report concisely. 2-3 sentence summary + a structured JSON block:
{"outcome": "success", "facts": {"time": "20:00 Sat", "name": "Smith"}, "followups": []}
Hard rules
- NEVER reveal the user's phone number, API keys, or session IDs in spoken output during the call. The system prompt you compose for the call agent should never include them either.
- ALWAYS include in the system prompt: "Identify yourself on the first turn as 'an AI assistant calling on behalf of the user'. If asked whether you are human, answer truthfully."
- If the receiving party gets confused or hostile, the call agent should politely end the call and report the situation. Do not push through.
- For time-sensitive bookings, include the user's local timezone explicitly in the objective.
- If the objective implies a financial commitment > €100 or anything legally binding, refuse — return to the parent and tell the user this needs human handling.
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.
- 9d ago First seen · 37 lines · 51 tokens per session scan A c1936d54f92f
phone-agent is an agent published in the GitHub repository PatterAI/awesome-claude-call (8 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 670 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
plan-creation-eng-lead
Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.
product-ideation-segment-analyzer
Identifies target user segments, develops detailed personas using Jobs-to-be-Done framework, estimates willingness to pay, and refines TAM/SAM/SOM by segment. Reads competitive analysis output from logs/. Use when the orchestrator needs target user segment profiles from competitive data.
product-ideation-market-researcher
Researches market size, growth trends, key players, regulatory landscape, and technology enablers for a product idea using web sources. Produces evidence-based market assessment with TAM/SAM/SOM estimates. Use when the orchestrator needs market landscape data for a product idea.
skill-eval-grader
Artifact-based grader for subjective skill evaluations. Reads evidence files (generated SKILL.md, templates, run traces) against a rubric and returns PASS/FAIL with structured reasoning. Used by grade.ts for fuzzy assertions where deterministic checks cannot apply.
csharp-reviewer
C#-specific code reviewer. Audits for .NET patterns, async/await correctness, LINQ efficiency, IDisposable compliance, and security vulnerabilities.
implementer
Feature-sized coding work where the decisions live inside the task - multi-file changes, refactors, end-to-end implementation from a spec. Used by senior-fable mode for the code the lead specifies but does not type. Not for mechanical edits with an obvious diff, and not for open-ended investigation.