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 afterhold-ivr-errandgit 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/afterhold-ivr-errand)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/afterhold-ivr-errand"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/afterhold-ivr-errand/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/afterhold-ivr-errand"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/afterhold-ivr-errand.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 | $0.00000 | $0.03993 |
| Opus 5.5 | $0.00000 | $0.01597 |
| Sonnet 5.5 | $0.00000 | $0.00799 |
| Haiku 4.5 | $0.00000 | $0.00399 |
Grade A, and why
afterhold-ivr-errand scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
TOKEN=$(curl -s -X POST http://127.0.0.1:8787/v1/auth/register \ How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
afterhold-ivr-errand
AfterHold is a workspace + safety layer in front of the CALL-E call runtime.
You (the assistant using this skill) send one outbound call per "mission", poll until terminal, and
write a structured brief. You do not hold CALL-E keys — the AfterHold API does. You talk to
AFTERHOLD_API_BASE over HTTPS with a JWT bearer token.
When to use
Use this skill when the user wants to delegate a phone task to CALL-E without making the call themselves. Examples:
- "Call BlueDart and ask if AWB 8821 is out for delivery."
- "Reschedule my 4:30 PM appointment at Dr. Mehta's clinic to tomorrow."
- "Confirm a 7:30 PM table for two at Pizza Hut Bandra."
- "Check the status of my electricity outage ticket."
Do not use this skill for:
- Anything requiring payments, money movement, or account cancellation (refused by policy).
- Medical advice or clinical interpretation (refused by policy).
- Legal advice or legal-record destruction (refused by policy).
- Mass/batch calls (v1 is one recipient per mission).
Inputs
The user (or another tool) supplies:
| Field | Type | Required | Notes |
|---|---|---|---|
e164 |
string (E.164) | yes | Destination phone. Must be on the user's allowlist. |
display_name |
string | yes | Human label, e.g. "BlueDart Chennai Hub". |
goal |
string | yes | Natural-language description of what to achieve. |
language |
BCP-47 | no | Default en-IN. |
archetype |
enum | no | courier | clinic | restaurant | utility | general. Default general. |
schedule_at |
ISO ms | no | Default null (call now). If set, the server will start when due. |
extract_schema |
JSON Schema | no | Default canonical envelope (see references/result-schema.md). |
Outputs
The skill returns a Brief:
{
"outcome": "resolved" | "needs_human" | "voicemail" | "unavailable" | "refused" | "failed",
"summary_for_user": "string",
"facts": { "...": "..." },
"next_step": "string?",
"callee_role": "string?",
"confidence": 0..1,
"evidence": [{ "quote": "..." }]
}
What ships with it
12 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.
- examples/clinic.json 973 B
- examples/courier.json 1.0 KB
- examples/restaurant.json 985 B
- examples/utility.json 982 B
- references/examples.md 1.4 KB
- references/failure-mapping.md 2.4 KB
- references/result-schema.md 2.3 KB
- references/safety.md 2.1 KB
- references/server.md 3.7 KB
- references/task-template.md 2.5 KB
- scripts/dry-run.mjs 4.0 KB runs code
- scripts/run-mission.mjs 4.8 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.
- 7d ago First seen · 329 lines · 0 tokens per session scan A 062d32d8db9c
afterhold-ivr-errand is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,993 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-13.
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.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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.
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…