validate

A command for checking whether Twilio calls, messages, recordings, and transcripts actually worked. Twilio is a communications service; an HTTP 200 response only means its request was accepted, not that the user experience succeeded.

In plain words
What is it for?
Use it after Twilio operations to inspect resource status, debugger alerts, call notifications, Voice Insights errors, and recording or transcript quality.
Why use it?
It catches failures that a basic API response can miss, such as an error message during a call, delivery problems, or unusable recording content.

Command

Install

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.

agentmods
npx agentmods add commands/wittyreference/twilio-claude-plugin/validate
Clone the repo
git clone --depth 1 https://github.com/wittyreference/twilio-claude-plugin
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,250 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.01250
Opus 5 $0.00015 $0.00625
Sonnet 5 $0.00006 $0.00250
Haiku 4.5 $0.00003 $0.00125

Measured yesterday against content hash 78b90c2020d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate 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 yesterday.

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.

commands/validate.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Validation

Deep validation of Twilio operations beyond HTTP 200 OK responses.

Purpose

A 200 OK from Twilio API doesn't guarantee success. A call can be "completed" from Twilio's perspective but still fail from the user's perspective (e.g., hearing "application error has occurred" instead of AI conversation).

This command invokes the MCP validation tools to verify:

  • Resource status is truly successful
  • Debugger has no related alerts
  • Call notifications show no errors
  • Voice Insights has no error tags
  • Content quality (recordings, transcripts) shows no error messages

Usage

<user_request> $ARGUMENTS </user_request>

MCP Tools Available

Use these tools via the MCP server:

validate_call

Deep validate a call - checks status, notifications, events, Voice Insights, and optionally content quality.

Call SID: $CALL_SID
Options:
- validateContent: true (check recordings/transcripts for error patterns)
- minDuration: 15 (seconds - shorter calls may indicate errors)
- forbiddenPatterns: ["application error", "please try again"]
- intelligenceServiceSid: "GAxxxx" (for transcript analysis)

validate_message

Deep validate a message - checks delivery status and debugger alerts.

Message SID: $MESSAGE_SID
Options:
- waitForTerminal: true (wait for delivered/undelivered/failed)
- timeout: 30000 (ms)

validate_debugger

Check Twilio debugger for errors in a time window.

Options:
- lookbackSeconds: 300 (5 minutes)
- resourceSid: "CAxxxx" (filter to specific resource)
- logLevel: "error" | "warning" | "notice" | "debug"

validate_voice_ai_flow

Comprehensive validation for Voice AI flows - validates call, recording, transcript, message, and sync state.

Required:
- callSid: "CAxxxx"

Optional:
- recordingSid: "RExxxx"
- transcriptSid: "GTxxxx"
- smsSid: "SMxxxx"
- syncDocumentName: "conversation-xxx"
- forbiddenPatterns: ["error", "sorry"]
- intelligenceServiceSid: "GAxxxx"

validate_two_way

Validate a two-way conversation between two calls (AI agent + customer).

Read the full file on GitHub · 189 lines

Changes

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.

  1. yesterday First seen · 189 lines · 30 tokens per session scan A 78b90c2020d9

Subscribe to this mod's changes

validate is a command published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 1,250 once invoked, about $0.0002 per session on Opus 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 2026-08-31.