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 holdfor-post-visit-followupgit 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/holdfor-post-visit-followup)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/holdfor-post-visit-followup"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/holdfor-post-visit-followup/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/holdfor-post-visit-followup"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/holdfor-post-visit-followup.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 | $0.00102 | $0.02139 |
| Opus 5 | $0.00051 | $0.01069 |
| Sonnet 5 | $0.00020 | $0.00428 |
| Haiku 4.5 | $0.00010 | $0.00214 |
Grade A, and why
holdfor-post-visit-followup 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HoldFor post-visit follow-up
Two phone calls with a named human between them.
- The Check-in Call rings a patient a few days after an appointment, asks five bounded questions at her pace, and returns a structured result.
- A member of practice staff reads it and grants a Release, or does not.
- The Rebooking Call rings the practice's own booking line inside that Release, carrying her own words.
Nothing in step 3 can happen without step 2. That is the whole shape of the skill.
Terms in bold with a capital are defined in CONTEXT.md and are
load-bearing. Do not substitute "ticket" for Review Item, "approval" for
Release, or "escalation" for Stop Condition.
What this skill does not do
Neither call decides anything clinical, and neither writes to a patient record. There is no write path to the clinical record, by design and not by omission. See ADR 0001.
The Check-in Call carries no authority to cause the Rebooking Call. A patient saying yes is an answer, not an instruction — only a Release, granted by a named human who read the transcript, places the second call. See ADR 0003.
When to use
- An appointment happened, the practice operates this workflow, and the patient has recorded consent to be called.
- It is the patient's Due Day — day 3 after the appointment, stepped forward off a weekend. One day, and the call is not placed on any other.
- The patient is an adult with an existing care relationship with the practice.
When not to use
- No recorded consent. There is no fallback and no implied consent; the call is simply not placed.
- Any day but the Due Day, weekends included. This is a refusal, not an error.
- The patient can use the online portal comfortably. Then "use the portal" is a complete answer and this call has no reason to exist.
- Anything clinical is being asked of the agent. Read the Safety Line and stop.
- Cold outreach, marketing, screening a population, or any call to someone the practice has no existing relationship with.
What ships with it
6 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 · 172 lines · 102 tokens per session scan A 47cda09076e9
holdfor-post-visit-followup is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (88 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 2,139 once invoked, about $0.0005 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.