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-leading-question-guardgit 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-leading-question-guard)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-leading-question-guard"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-leading-question-guard/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-leading-question-guard"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-leading-question-guard.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 | $0.00080 | $0.01051 |
| Opus 5.5 | $0.00032 | $0.00420 |
| Sonnet 5.5 | $0.00016 | $0.00210 |
| Haiku 4.5 | $0.00008 | $0.00105 |
Grade A, and why
call-leading-question-guard 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 16d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
call-leading-question-guard
A leading question does not ask - it instructs the answer, then collects a signature.
How a question is worded shapes what comes back. "What day works best for you?" and "You can pick up on Friday, right?" are both questions, but only one hands the person a decision; the other hands them a form to sign. On a phone call, where answers are spoken and immediately acted on, that wording pressure can end up driving bookings and record updates. This skill grades the agent's interrogation wording, not the callee's answers.
When To Use
- after any CALL-E call where the agent elicits decisions (dates, times, amounts, plan choices) from the person
- when a recorded value was affirmed immediately after an agent question and you want to know how the question was framed
- before placing calls, to craft a neutral-elicitation goal that opens open-form and confirms in bounded closed form
- as a review aid alongside sibling conduct skills on the same transcript
When Not To Use
- on the callee's questions - only agent turns are scanned
- to prove coercion; a flagged form is not proof the answer was coerced, and a confident person may genuinely agree - the card routes to review, always
- during a call; strictly post-call analysis plus pre-call goal crafting
- non-English transcripts; the form families are English lexical patterns
Workflow
Audit a finished call
python3 scripts/leading_question_guard.py analyze \
--transcript path/to/call-result.json
Reads the real get_call_run result shape ({status, result: {transcript}})
or the flat fixture shape used by sibling skill fixtures; no goal file
is needed. Emits a card:
questions[]: every agent question sentence, classified asTAG/NEGATIVE_INTERROGATIVE/PRESUPPOSITION/COERCIVE(leading) orOPEN/CLOSED(neutral)tainted_elicitation[]: values the callee affirmed (affirmation word plus a weekday, ordinal date, amount, or clock time in the same turn) within two turns of a leading question - candidates for neutral re-confirmation, never auto-invalidationsverdict:NEUTRAL_ELICITATION/LEADING_QUESTIONS_DETECTED/LEADING_TAINTED/NO_QUESTIONS_ASKED, plusunclearpaths (empty transcript, no agent turns)
What ships with it
8 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 271 B
- references/example-transcript-leading-untainted.json 638 B
- references/example-transcript-neutral.json 727 B
- references/example-transcript.json 818 B
- references/examples.md 4.9 KB
- references/safety.md 2.2 KB
- scripts/leading_question_guard.py 14 KB runs code
- scripts/test_leading_question_guard.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.
- 16d ago First seen · 97 lines · 80 tokens per session scan A b7a2d98215ac
call-leading-question-guard is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 1,051 once invoked, about $0.0003 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 2026-10-04.
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.