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-answer-evasion-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-answer-evasion-auditor)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-answer-evasion-auditor"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-answer-evasion-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-answer-evasion-auditor"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-answer-evasion-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 | $0.00068 | $0.01626 |
| Opus 5.5 | $0.00027 | $0.00650 |
| Sonnet 5.5 | $0.00014 | $0.00325 |
| Haiku 4.5 | $0.00007 | $0.00163 |
Grade A, and why
call-answer-evasion-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 15d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
call-answer-evasion-auditor
A callee who asks a straight question deserves a straight answer.
On a voice call, a dodged question is louder than a wrong one. A caller who asks "are you a robot?" and hears "great question!" stops trusting every sentence that follows; a caller who asks "how did you get my number?" and hears a counter-question hangs up. Evasion destroys more calls than imperfect information does, because it is audible as evasion. This skill audits the agent's answers to every direct question the callee asked.
Grading is lexical, derived from the QEvasion response-clarity taxonomy: each callee question (identity, yes-no, or information/wh) is graded against the next two agent turns as CLEAR, PARTIALLY_CLEAR, or EVASIVE, with a mechanism label for every non-clear answer. It is wording analysis, not intent detection.
When To Use
- after any CALL-E call where the callee asked direct questions and the transcript should show candid answers
- when reviewing whether identity ("are you a robot?"), provenance ("how did you get my number?"), or commitment questions were answered or dodged
- before placing calls, to craft an answer-first goal template with a canned truthful identity answer and a provenance line
- alongside
call-repair-sequence-auditor, which owns bare repair initiators ("Sorry, what was that?") that this skill skips
What It Checks
Questions asked by the callee only; agent questions are never graded.
| Verdict | Meaning |
|---|---|
DIRECT_ANSWERS |
every callee question answered clearly |
PARTIAL_EVASION |
some answer arrived, but not as the direct reply (e.g. a yes/no token buried after an acknowledgment) |
EVASION_DETECTED |
at least one question received no clear answer |
NO_CALLEE_QUESTIONS |
the callee asked nothing gradeable |
| Mechanism (evasive/partial answers) | Meaning |
|---|---|
identity_evasion |
an identity question got no truthful AI/self disclosure |
deflection |
the window contains a counter-question instead of an answer |
non_answer_ack |
"great question" style acknowledgment with no answer |
defer |
"we'll get to that" / "as I mentioned" postponement |
unanswered |
agent turns exist but none address the question |
no_response |
no agent turn follows the question |
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 634 B
- references/example-transcript-evasive.json 954 B
- references/example-transcript-partial.json 627 B
- references/example-transcript.json 893 B
- references/examples.md 5.1 KB
- references/safety.md 1.4 KB
- scripts/answer_evasion_auditor.py 15 KB runs code
- scripts/test_answer_evasion_auditor.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.
- 15d ago First seen · 119 lines · 68 tokens per session scan A 29aedc7f5211
call-answer-evasion-auditor is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 1,626 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 2026-10-05.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…