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-semantic-phishing-honeybotgit 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-semantic-phishing-honeybot)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-semantic-phishing-honeybot"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-semantic-phishing-honeybot/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-semantic-phishing-honeybot"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-semantic-phishing-honeybot.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 | $0.00041 | $0.00551 |
| Opus 5.5 | $0.00016 | $0.00220 |
| Sonnet 5.5 | $0.00008 | $0.00110 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
call-semantic-phishing-honeybot 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Phishing Honeybot
The supplied helper uses regex over synthetic transcript text and returns candidate URLs, wallet strings, phone-like strings, and predefined response suggestions. It does not determine that a person is a scammer, operate a call, browse extracted URLs, or send threat reports. Any future engagement must be operator-authorized, bounded, stoppable, and separate from this offline demonstration.
Scientific Foundation
| Paper / Concept | Relevance |
|---|---|
| Active Defense & Honeybots | Email scam-baiting research motivates this design; it does not establish phone-call duration or effectiveness. |
| Social Engineering Taxonomy | Uses established psychological countermeasures (acting confused, feigning compliance) to trigger the scammer into repeating technical instructions (IoCs). |
| Vishing Kill-Chain Analysis | Targets the "Action/Exploitation" phase of the voice phishing kill chain to capture the final payload (e.g. the Bitcoin wallet). |
How it works
- Supply a synthetic transcript turn and fictional caller identifier; no call is answered or intercepted.
- The helper applies regex to the text to extract candidate indicators.
- It dynamically generates a
bait_prompttailored to the scammer's current objective:- If the scammer wants Bitcoin, the bot feigns ignorance about crypto to drag out the call.
- If the scammer provides a URL, the bot pretends its antivirus blocked it to gather alternative domains.
- Candidates are returned in
HoneybotResponse; they are neither verified nor automatically logged/shared.
Expected Outcomes & Metrics
These are unvalidated design targets for a future integration, not measurements or effects of the local helper.
| Metric | Target | Notes |
|---|---|---|
| IoC Extraction Rate | > 75% | Successfully pulling a wallet or URL from a known scam script. |
| Call Duration (Stalling) | > 5 mins | Time wasted per scammer. |
Limitations & Known Constraints
- Pattern Matching Limits: The current IoC extraction relies on basic regex (e.g. base58 for Bitcoin). It may miss newer or obfuscated wallet formats.
- Integration Boundary: No LLM or calling loop is included. A future host must impose an operator-controlled stop and duration limit; returned
continue_baitingis a suggestion, not authority to continue a call.
What ships with it
5 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.
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 · 40 lines · 41 tokens per session scan A 80bfcbab951c
call-semantic-phishing-honeybot is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 551 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 2026-09-19.
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…