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 call-human-escalation-request-auditorgit 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/call-human-escalation-request-auditor)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-human-escalation-request-auditor"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-human-escalation-request-auditor/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/call-human-escalation-request-auditor"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-human-escalation-request-auditor.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 | $0.00092 | $0.02044 |
| Opus 5.5 | $0.00037 | $0.00818 |
| Sonnet 5.5 | $0.00018 | $0.00409 |
| Haiku 4.5 | $0.00009 | $0.00204 |
Grade A, and why
call-human-escalation-request-auditor 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 11d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
call-human-escalation-request-auditor
The callee's demand for a human is the highest-trust moment in the call. Grade it honestly.
Voice agents can now plausibly pass as human in three-party conversation, which makes the moment a callee says "let me talk to a real person" a trust crossroads: the agent can honor it, fake it, ignore it, or - worst - claim to be the human being asked for. That last failure is realistic, not hypothetical, and regulators already treat AI-caller identity as regulated territory. This skill grades how the agent handled the demand, from the transcript alone.
Why this skill exists
- Existing skills cover the other directions:
call-reviewchecks stop-request and DNC phrasings on the agent side, and skills such asincident-escalation-callhelp an agent escalate to humans. None audits the callee-to-human direction: did the agent respond honestly when the person demanded a person? call-answer-evasion-auditorgrades honesty answers to direct identity questions; this skill covers the escalation demand that often surrounds them, and delegates pure identity probes back to it automatically.
When To Use
- after any call where the callee may have asked for a person ("can I speak to a human", "Manager. Now.")
- when tuning an agent's escalation policy, to measure how it actually behaved under a demand instead of how you hope it behaves
- before connecting a new goal template to production, to baseline the escalation behavior of the previous prompt version
When Not To Use
- identity probes alone ("are you a robot?"): the skill never grades these
as requests - it records them in
delegated_identity_probeswith a note pointing behavioral honesty grading to the call-answer-evasion-auditor - to prove a transfer physically occurred; the skill reads the transcript only, and an HONORED grade means the agent acknowledged and committed on the record, nothing more
- non-English calls; the request, role, and grading lexicons are English
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.
- references/example-goal.txt 567 B
- references/example-transcript-deflected.json 595 B
- references/example-transcript-false-claim.json 456 B
- references/example-transcript-ignored.json 560 B
- references/example-transcript.json 634 B
- references/examples.md 7.3 KB
- references/safety.md 2.2 KB
- scripts/human_escalation_request_auditor.py 18 KB runs code
- scripts/test_human_escalation_request_auditor.py 17 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.
- 11d ago First seen · 165 lines · 92 tokens per session scan A f6f9a6fa0a3d
call-human-escalation-request-auditor is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 2,044 once invoked, about $0.0004 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 2026-10-09.
Other skills, from other repositories
fto-triage
Freedom-to-operate triage — a structured first look at potentially blocking patents, not an FTO opinion. Use when a product, process, or feature is being evaluated for blocking patents, when asked whether anything stops a launch, or to build a claim-chart first pass against the most plausible patents before patent…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.