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 powerback-outage-welfare-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/powerback-outage-welfare-call)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/powerback-outage-welfare-call"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/powerback-outage-welfare-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/powerback-outage-welfare-call"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/powerback-outage-welfare-call.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 | $0.00069 | $0.01587 |
| Opus 5.5 | $0.00028 | $0.00635 |
| Sonnet 5.5 | $0.00014 | $0.00317 |
| Haiku 4.5 | $0.00007 | $0.00159 |
Grade A, and why
powerback-outage-welfare-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 6d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PowerBack Outage Welfare Call
Use this skill when an emergency coordinator or district office must find out, during a power outage, which households on life-support equipment are actually in trouble — and must do it faster than a person can work down a paper roster.
A map can show who is at risk. Only a call finds out who needs help right now.
The design premise: being confidently wrong about whether someone is alive is worse than admitting you do not know. Every ambiguous outcome gets its own terminal state and routes to a human, rather than becoming a clean-looking statistic.
When to use
- An outage or disaster has hit a district with known electricity-dependent residents.
- You have a roster and need a call order, not just a call list.
- You need results as actionable buckets (dispatch / follow up / retry / safe / do-not-disturb).
- You want every call previewed and approved before it is placed.
When not to use
- Medical triage, diagnosis, or anything that replaces emergency services.
- Unsolicited outreach, marketing, or lead generation.
- Recurring schedules — pair with a scheduler wrapper and re-confirm consent.
- Any context where a wrong answer would remove someone from a follow-up list without a human ever seeing the case.
Workflow
- Read
references/safety.md. It separates code gates from prompt constraints — they are not the same guarantee, and this skill does not pretend they are. - Build the roster. Each entry validates against
references/call_input.schema.json: E.164phone,scenario,language, and adisclosure_allowlist. - Rank:
python run_batch.py— call order only, nothing dialled. - Preview:
python run_batch.py --show-preview— shows the operator exactly what the agent will be told to say, with the number masked. - Simulate:
python run_batch.py --simulate— full loop againstFakeAdapter, entirely offline, prints the triage board. - Check the live request without placing one:
python scripts/check_sdk_contract.pybinds the request this skill would send against the publishedcalle-ai==1.0.1create()signature. Offline, no key. - Live: set
CALLE_API_KEY,PB_ALLOW_REAL_CALL=1,PB_ALLOWED_DESTINATIONS(comma-separated E.164 numbers the operator has authorised) andPB_BATCH_ID(a durable batch id, so a retry cannot place a second call to the same household), then callengine.run(..., mode="live", human_confirmed=True). Five separate gates, on purpose. An empty or unsetPB_ALLOWED_DESTINATIONSauthorises nothing — there is no wildcard. Live calling is not exposed as a CLI flag.
What ships with it
13 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.
- assets/synthetic_roster.json 2.3 KB
- references/call_input.schema.json 2.2 KB
- references/call_result.schema.json 2.9 KB
- references/examples.md 8.0 KB
- references/safety.md 6.1 KB
- references/sdk_contract.md 4.0 KB
- run_batch.py 4.2 KB runs code
- scripts/__init__.py 87 B runs code
- scripts/adapters.py 15 KB runs code
- scripts/check_sdk_contract.py 3.8 KB runs code
- scripts/consent.py 3.1 KB runs code
- scripts/engine.py 7.5 KB runs code
- scripts/triage.py 3.2 KB runs code
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.
- 6d ago First seen · 131 lines · 69 tokens per session scan A c7858c30aa8b
powerback-outage-welfare-call is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 1,587 once invoked, about $0.0003 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 2026-10-14.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…