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 agentmods add skills/wittyreference/twilio-claude-plugin/ivr-crawlernpx skills add wittyreference/twilio-claude-plugin --skill ivr-crawlergit clone --depth 1 https://github.com/wittyreference/twilio-claude-pluginWrote 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/wittyreference/twilio-claude-plugin/ivr-crawler)<a href="https://agentmods.dev/skills/wittyreference/twilio-claude-plugin/ivr-crawler"><img src="https://agentmods.dev/badge/skills/wittyreference/twilio-claude-plugin/ivr-crawler.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.04297 |
| Opus 5 | $0.00006 | $0.02148 |
| Sonnet 5 | $0.00003 | $0.00859 |
| Haiku 4.5 | $0.00001 | $0.00430 |
Grade C, and why
ivr-crawler scanned grade C with 2 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 5d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s http://localhost:4040/api/tunnels | python3 -c " Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:4040/api/tunnels | python3 -c " How it starts
The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: ivr-crawler description: Crawl and map IVR phone trees autonomously. Use when mapping an existing IVR system, migrating an IVR to Twilio, or analyzing IVR structure. Triggers on "crawl IVR", "map IVR", "IVR migration", "replicate IVR".
IVR Crawler
Autonomously maps any IVR phone system by calling it, navigating every branch via DTMF, and producing a structured tree. The output feeds /ivr-migrator to rebuild the IVR on Twilio.
Evidence: Live-tested 2026-03-25 against GlobalTech Solutions test IVR. 22 calls, 22 nodes, 10m 44s, 100% completion. Account ACxx...xx
Scope
CAN
- Crawl any phone number's IVR via outbound calls
- Navigate menus using DTMF (
sendDigitsoncalls.create()) - Detect menu options, dead ends, transfers, hold music, callbacks, business hours
- Handle multi-language IVRs (detected per-node via Claude analysis)
- Detect cycles (return-to-menu, redirects) and avoid infinite exploration
- Output structured JSON (
IvrTree) and ASCII tree visualization - Speak through ConversationRelay for speech-only menus
- Generate VoiceXML 2.1 from crawl output (VXML generator)
- Parse customer-provided VXML documents into IvrTree IR (VXML parser)
- Generate Twilio Serverless Functions from VXML (full VXML-to-TwiML pipeline)
- Round-trip validation: IvrTree → VXML → parse → TwiML → deploy → crawl → compare
CANNOT
- Navigate auth-protected IVRs without test credentials — but CAN navigate payment IVRs when test data (account, ZIP, card) is provided via scenario configuration
- Interact with IVRs that use only speech recognition (no DTMF) beyond basic keyword navigation
- Guarantee timing alignment with every IVR (some need longer
sendDigitsdelays) - Make calls without a Twilio phone number and valid credentials
- Run without ngrok or another WebSocket tunnel
Quick Decision
| Need | Action |
|---|---|
| Map an existing IVR | Run /ivr-crawler with the phone number |
| Migrate IVR to Twilio | Run /ivr-crawler first, then /ivr-migrator on the output |
| Customer has VXML docs | Parse VXML → IvrTree IR → generate TwiML handlers directly |
| Generate VXML from crawl | Use generateVxml(tree) to create VoiceXML for customer review |
| Test our own IVR | Call +15550100009 (GlobalTech test IVR) or crawl it |
| Debug a failed crawl | Check validate_call(callSid) for the failing call |
What ships with it
1 file 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.
- 5d ago First seen · 292 lines · 13 tokens per session scan C b62b4fba3530
ivr-crawler is a skill published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 4,297 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…