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 incident-escalation-callgit 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/incident-escalation-call)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/incident-escalation-call"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/incident-escalation-call/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/incident-escalation-call"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/incident-escalation-call.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 | $0.01292 |
| Opus 5 | $0.00037 | $0.00646 |
| Sonnet 5 | $0.00015 | $0.00258 |
| Haiku 4.5 | $0.00007 | $0.00129 |
Grade A, and why
incident-escalation-call 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incident Escalation Call
Use this skill when an incident needs a human owner and "notification sent" is not evidence that anybody heard it.
It does not invent an escalation mechanism. It drives the runnable
ringdown app, which resolves who is on call
right now, places one CALL-E call per person in ladder order, accepts only a
commitment with an owner and an ETA, re-derives that acknowledgement from the
raw transcript over MCP — a second transport the writing path never touched —
and returns an exit code plus a hash-chained ledger.
When to use
- A monitoring alert, a failed deploy or a user-facing outage needs a named owner with a spoken commitment, and the on-call rotation is defined.
- The on-call engineer is asleep or away from a keyboard, which is exactly when a phone call beats a push notification, an email or a chat message.
- The user asked to page, escalate or wake up whoever is on call.
When not to use
- The user is the on-call engineer and is already in this conversation. Tell them here.
- You do not have a rotation file with enrolled contacts in E.164 form and on-call windows that cover this moment. Do not guess a number, a country code, a region or a name.
- Anything medical, legal, financial advice or an emergency. See
references/safety.md. - Ringing somebody again after an explicit decline. A no is final for the run.
How it works
- You write an incident file — id, title, severity, service, summary, the
ladder of scopes, the acknowledgement policy — or produce one from a raw
alert payload with
adapt. The rotation file lists who covers each scope and when. - You run
previewand show the user the resolved ladder and the exact call task. Preview opens no socket and reads no credentials. - On the user's go-ahead you run it live. The app calls one person at a time, top of the ladder first. An acknowledgement needs an owner and an ETA spoken by the person who answered; a bare "yeah, sure" does not advance anything and the ladder moves on.
- After the ladder settles, the app re-reads the calls over MCP and checks the recorded verdict against transcripts fetched on that second channel.
- You read the exit code. Nothing else counts as an acknowledgement.
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 · 110 lines · 75 tokens per session scan A 90ed0eaad538
incident-escalation-call 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 1,292 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…