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 priority-call-waterfallgit 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/priority-call-waterfall)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/priority-call-waterfall"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/priority-call-waterfall/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/priority-call-waterfall"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/priority-call-waterfall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 93 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00048 | $0.01351 |
| Opus 5 | $0.00024 | $0.00675 |
| Sonnet 5 | $0.00010 | $0.00270 |
| Haiku 4.5 | $0.00005 | $0.00135 |
Grade A, and why
priority-call-waterfall 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Priority Call Waterfall
Use this skill when the user has one concrete opportunity (an open appointment slot, an uncovered shift, an unassigned job, an unacknowledged incident) and a priority-ordered list of candidates, and wants each candidate called in order until one accepts.
priority-call-waterfall is a calling-pattern skill. It does not add a CALL-E backend
API, a queue service, or a daemon. It turns one authorized "fill this opening" request
into a strictly sequential series of one-off CALL-E calls with a hard stop at the first
acceptance.
When To Use
Use this skill for:
- backfilling a freed appointment slot from a waitlist (a cancellation or no-show)
- finding coverage for an open shift from a ranked list of staff
- dispatching one job to the first available provider on a call-down list
- escalating an incident through an on-call chain until someone acknowledges
- any "call these people in order until one says yes" request with a single opening
When Not To Use
Do not use this skill to:
- call multiple candidates in parallel or race candidates against each other
- continue calling after a candidate has accepted
- offer the same opening to more than one person at a time
- broadcast announcements, promotions, or anything that is not a real single opening
- build a recurring schedule (pair with a scheduler skill instead; each waterfall run is a one-shot workflow)
- guess phone numbers, priorities, consent, or the opening's details
- call third-party numbers unless the user states the candidates expect these calls (an existing waitlist, staff roster, or on-call rotation is that expectation)
Core Workflow
- Confirm the user explicitly wants the opening filled by phone now.
- Collect the waterfall fields:
- the opening: what it is, when it is, and any details a candidate needs to decide
- the candidate list: name, E.164 phone number, and priority (lower calls first)
- an optional per-run call cap (default: call every listed candidate at most once)
- an optional deadline after which the waterfall must stop even without an acceptance
- Ask for any missing required field. Do not infer phone numbers or priorities.
- Validate the input with
scripts/validate-waterfall-input.mjswhen a structured payload is available. Reject duplicate phone numbers and duplicate priorities. - Show the user a masked preview: the opening, the calling order, and the cap. Get explicit confirmation before the first call.
- Call candidates strictly one at a time, in priority order:
- build a goal that names the business or requester, the candidate, the opening,
and asks for a clear yes or no (see
references/goal-and-result.md) - request a structured result with a required
acceptedfield (yesorno) - place exactly one CALL-E call and wait for its terminal status
- treat an ambiguous provider outcome (voicemail, no answer, unclear answer, timeout, or failed call) as a halt condition; it must not automatically start another call or conflicting side effect.
- only a clear 'no' counts as a decline that allows moving to the next candidate.
- build a goal that names the business or requester, the candidate, the opening,
and asks for a clear yes or no (see
- Stop conditions, checked after every call:
- a candidate accepted → record who, stop immediately, never call the rest
- the list, cap, or deadline is exhausted → stop and report the opening unfilled
- Report the outcome using the Output Format below.
What ships with it
4 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.
- 9d ago First seen · 127 lines · 48 tokens per session scan A 33d4086d5533
priority-call-waterfall is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (88 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 1,351 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
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…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
magpie-security-issue-import-from-md
Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.