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 call-reviewgit 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/call-review)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-review"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-review/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/call-review"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-review.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 | $0.00072 | $0.00831 |
| Opus 5 | $0.00036 | $0.00415 |
| Sonnet 5 | $0.00014 | $0.00166 |
| Haiku 4.5 | $0.00007 | $0.00083 |
Grade A, and why
call-review 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 today.
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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Call Review
Use this skill after a CALL-E call task has reached a terminal status and before its structured_result is used for anything that matters (booking, closing a ticket, updating a record, paying).
When To Use
- a call task reports
task_completed: trueand you are about to act on the result - a batch of calls finished and you want to know which results can be trusted without reading every transcript
- a reviewer asks "did the agent say it was an AI" or "why was this call slow"
When Not To Use
- to decide whether to place a call (that is a consent and authorization question; see the safety references in this repository)
- as the only check on an irreversible or financial action; the verdict is advice for a human disposition
- on a call that has not reached a terminal status
Setup
Fetch the terminal snapshot with the official SDK or CLI (read-only):
calle calls get <call_id> # or: client.calls.get(call_id)
Optionally run the console in this repository (apps/web/call-review-console) which performs every check below and records the disposition.
Workflow
- Status first.
statusmust becompleted.failed,cancelledor afailure_codeon the attempt is an automaticreject; nothing else needs checking. - Structured result vs. transcript. For every leaf field, find the turn that supports the value. Numbers must be spoken (a reported
9amneeds "9", "nine", "9 a.m." in a callee turn). A value with no supporting turn is an unsupported claim; one unsupported claim is areject. Boolean and enum fields (yes/no/confirmed) need a turn read in context, not a keyword hit. - Timing. From
transcript_turns[].offset_seconds: response latency = agent turn start − previous callee turn start. Report p50 and p95; p95 above 6 s or two or more overlaps (a turn starting before the previous one) isneeds_human. Silences over 4 s are listed with their position. - Compliance. The agent must disclose it is an AI in its turns, ideally the first. A callee stop or opt-out request ("stop calling", "remove my number", "don't call again") must be the last exchange; any agent turn after it that is not a goodbye is a
reject. Card, account or ID-like numbers read aloud by the agent are areject. - Verdict.
approveonly when every field is supported or read-and-confirmed, timing is within limits and compliance passes. Otherwiseneeds_human(timing, unreadable fields) orreject(failed call, unsupported claim, ignored stop, no disclosure, sensitive readback). Write the reasons in one line each. - Disposition. Record who reviewed, when, the verdict and a note. Never edit the call's result to make it pass.
What ships with it
3 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.
- today First seen · 50 lines · 72 tokens per session scan A 325ec7624ca7
call-review is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (88 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 831 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 2026-09-12.
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…