Late Hold Triage

What it does

Example prompts

• “Use the late-hold-triage skill to place one outbound CALL-E call to a guest who is already late for a held table or appointment, captures a…”
• “/late-hold-triage”

Requirements

• Python 3

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Collect the required fields. Refuse to invent a number or a hold end.
2. 2Dry-run first. Print the masked destination, remaining hold minutes, and
3. 3If the hold has already expired at --now, stop. Do not call a guest
4. 4Live mode requires both --confirm (operator intent) and
5. 5Place exactly one CALL-E call with the shared result_schema in
6. 6Decide with the deterministic rules in Runtime Workflow. Do not ask a
7. 7Report one of KEEP_HOLD, RELEASE_NOW, NEEDS_HUMAN, or

What it can do on your machine

Read from SKILL.md and the folder at commit 38d4118. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 2 files in scripts/ (Python), which the agent can run.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Late Hold Triage loads about 1.6k tokens when it runs, and up to ~3.7k if it reads all its reference files. Until then it costs about 70 tokens; SKILL.md has 831 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~70

When it runs · the whole SKILL.md, loaded when a task matches

~1.6k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from CALLE-AI/awesome-phone-call-agents at commit 38d4118, republished under its MIT licence (© CALLE-AI). 831 words, ~1,614 tokens.

name

late-hold-triage

description

Places one outbound CALL-E call to a guest who is already late for a held table or appointment, captures a structured still-coming plus ETA result, and decides KEEP_HOLD, RELEASE_NOW, or NEEDS_HUMAN against the remaining hold window without calling the waitlist.

license

MIT

if now >= hold_until:
    HOLD_EXPIRED          # no call
else if spoken status is no_answer, voicemail, unclear, or missing:
    NEEDS_HUMAN           # never auto-release on silence
else if still_coming is false OR released is true:
    RELEASE_NOW
else if still_coming is true AND eta_minutes is an integer:
    if eta_minutes <= minutes_until(hold_until):
        KEEP_HOLD
    else:
        RELEASE_NOW       # they cannot arrive inside the hold
else:
    NEEDS_HUMAN

© CALLE-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files (scripts, references, assets) in skills/late-hold-triage of CALLE-AI/awesome-phone-call-agents.

• SKILL.md
• assets/authorized_numbers.example.txt
• assets/dry_run_outcomes.json
• assets/sample_holds.csv
• references/examples.md
• references/result-schema.md
• references/safety.md
• requirements.txt
• scripts/test_triage_late_hold.py
• scripts/triage_late_hold.py

Open the folder on GitHubat commit 38d4118