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 neighbour-welfare-sweepgit 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/neighbour-welfare-sweep)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/neighbour-welfare-sweep"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/neighbour-welfare-sweep/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/neighbour-welfare-sweep"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/neighbour-welfare-sweep.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 | $0.00191 | $0.02707 |
| Opus 5.5 | $0.00076 | $0.01083 |
| Sonnet 5.5 | $0.00038 | $0.00541 |
| Haiku 4.5 | $0.00019 | $0.00271 |
Grade A, and why
neighbour-welfare-sweep 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 1mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neighbour Welfare Sweep
Use this skill when a hazard is affecting an area, someone holds a list of people who may be in danger because of it, and the agent has to reach all of them by phone, work out who actually needs something, and get the ones in trouble to a human.
The people on that list are frail, elderly, isolated, or dependent on equipment that needs electricity. They will under-report. Some of them will not pick up. Both of those are the point, and the two rules below are what separate this from an automated call round.
The two rules
1. Silence is a finding, not an error
In an outbound sales or staffing cascade, a call nobody answers means "move on" and costs nothing. Here it is frequently the most important thing the sweep learns. An unanswered call to a man whose oxygen concentrator is plugged into a wall socket, during a blackout, is the finding.
So: UNREACHABLE is a first-class outcome, not an exception. An unanswered, failed, or unreadable call goes into the decision function with the person's triage attached, comes back with an outcome and a reason, and escalates. And every person on the roster with no outcome at all — never dialled, opted out, budget ran out — is named in the output with the reason. A sweep is judged by whether anybody was quietly dropped, not by how many calls it made.
2. The agent never summons emergency services
The ladder is EMERGENCY_CONTACT (the agent may call the person the neighbour nominated) → BLOCK_CAPTAIN (the agent notifies the coordinator) → RESPONDER (the agent prepares a page and stops). A responder handoff is a document with released_at = null, which means it has told nobody anything, and the only way out of it is a named human releasing it.
The same boundary applies to anything the workflow sends. Community resources — a volunteer with water, a ride to a cooling centre, a portable battery, an outreach nurse — may be committed by the agent, because a wasted trip is a recoverable mistake. An ambulance, a fire crew or a police welfare check may be proposed, routed and fully prepared, and then stays proposed until a named human approves it, because a false ambulance call takes a unit away from somebody else's emergency and that is not recoverable.
What ships with it
7 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.
- 1mo ago First seen · 105 lines · 191 tokens per session scan A d0eeee8ae678
neighbour-welfare-sweep is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 191 tokens to every session and 2,707 once invoked, about $0.0008 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 2026-09-18.
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…