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 late-hold-triagegit 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/late-hold-triage)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/late-hold-triage"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/late-hold-triage/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/late-hold-triage"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/late-hold-triage.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 | $0.00062 | $0.01614 |
| Opus 5.5 | $0.00025 | $0.00646 |
| Sonnet 5.5 | $0.00012 | $0.00323 |
| Haiku 4.5 | $0.00006 | $0.00161 |
Grade A, and why
late-hold-triage 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Late Hold Triage
Use this skill when a booked guest is late right now and the floor needs a yes, a no, or a human — not a guess — before the held slot is given away.
late-hold-triage is a one-recipient decision skill. It does not add a CALL-E
backend queue, a campaign, or a waitlist dialer. It places at most one outbound
call to the late guest, reads a structured result, and compares the spoken ETA
to the hold that is still on the clock.
This is the missing half of next-day confirmation and first-accept cascades:
appointment-call-confirmcalls tomorrow's whole book in advancestandby/priority-call-waterfalloffer a freed slot down a list- this skill calls the late guest who still owns the slot and only then recommends whether a human should start a cascade
It never dials the waitlist. A RELEASE_NOW is a recommendation to the host,
not permission to ring the next person.
When To Use
Use this skill when:
- a restaurant, salon, clinic front desk, or repair shop is holding a slot for a guest who has passed the booked start time
- staff need a spoken ETA, not a text that may never arrive
- the hold has a hard end (
hold_until) and giving the slot away too early or too late both cost money - the operator asks something like "they're 12 minutes late — do we still hold table 7?"
When Not To Use
Do not use this skill to:
- confirm tomorrow's appointments — that is
appointment-call-confirm - fill a slot that is already free — that is
standbyorpriority-call-waterfall - call anyone other than the late guest on this run
- diagnose, treat, collect a debt, or discuss legal or medical substance
- infer a phone number, timezone, or hold end the operator did not supply
- treat silence, voicemail, or an unreadable answer as a release
Required Inputs
Ask for any of these that is missing. Do not infer one from locale, the phone number, or an earlier unrelated chat.
| Field | Notes |
|---|---|
guest_name |
Spoken on the call so the right person can confirm identity |
phone |
E.164, supplied by the operator |
slot_start |
ISO 8601 with timezone — when the booking began |
hold_until |
ISO 8601 with timezone — when the house stops holding |
business_name |
Who the call says it is calling for |
context |
One logistics sentence, e.g. "table for two at the window" |
What ships with it
9 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/authorized_numbers.example.txt 254 B
- assets/dry_run_outcomes.json 457 B
- assets/sample_holds.csv 464 B
- references/examples.md 2.1 KB
- references/result-schema.md 2.7 KB
- references/safety.md 3.5 KB
- requirements.txt 19 B
- scripts/test_triage_late_hold.py 6.5 KB runs code
- scripts/triage_late_hold.py 23 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.
- 1mo ago First seen · 152 lines · 62 tokens per session scan A d92909f5858e
late-hold-triage is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 1,614 once invoked, about $0.0002 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 2026-09-15.
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…