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/deep-validationnpx skills add wittyreference/twilio-claude-plugin --skill deep-validationgit clone --depth 1 https://github.com/wittyreference/twilio-claude-pluginWhat 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 | $0.00010 | $0.03308 |
| Opus 5 | $0.00005 | $0.01654 |
| Sonnet 5 | $0.00002 | $0.00662 |
| Haiku 4.5 | $0.00001 | $0.00331 |
Grade A, and why
deep-validation 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.
How it starts
The opening of the file, as written. The whole thing — 507 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: deep-validation description: Validation patterns beyond HTTP 200. Use when building validation logic, testing Twilio integrations, or understanding status progression, Voice Insights, and debugger alert patterns.
Deep Validation Patterns for Twilio
This skill covers validation patterns that go beyond simple API response checking. Load this skill when testing Twilio integrations or building validation into workflows.
Why Deep Validation Matters
A 200 OK from Twilio API doesn't guarantee success. The operation may be queued but:
- TwiML validation could fail later
- Carrier could reject the message
- Webhook could return errors
- Call could fail to connect
- Voice quality could be degraded
Tests that only check for 200 OK give false confidence.
The Deep Validation Pattern
For each operation type, check multiple signals after API operations:
SMS/MMS Validation
interface MessageValidation {
// Primary: Check message status progression
resourceStatus: {
passed: boolean;
status: 'queued' | 'sending' | 'sent' | 'delivered' | 'undelivered' | 'failed';
};
// Secondary: Check for debugger alerts
debuggerAlerts: {
passed: boolean;
alerts: Alert[]; // Error codes 30003, 30004, etc.
};
// Optional: Check callback data (if callbacks configured)
callbackReceived: {
passed: boolean;
data: object;
};
}
Status progression: queued → sending → sent → delivered
Common failure codes:
| Code | Meaning |
|---|---|
| 30003 | Unreachable destination |
| 30004 | Message blocked |
| 30005 | Unknown destination |
| 30006 | Landline or unreachable |
| 30007 | Carrier violation |
Voice Call Validation
interface CallValidation {
// Primary: Check call status
resourceStatus: {
passed: boolean;
status: 'queued' | 'ringing' | 'in-progress' | 'completed' | 'busy' | 'no-answer' | 'failed';
};
// Secondary: Check call events for HTTP errors
callEvents: {
passed: boolean;
events: Event[]; // HTTP requests/responses during call
};
// Secondary: Check debugger for TwiML errors
debuggerAlerts: {
passed: boolean;
alerts: Alert[];
};
// Quality: Voice Insights call summary
voiceInsights: {
passed: boolean;
summary: {
callQuality: string;
disposition: string;
jitter: number;
packetLoss: number;
};
};
}
// The enhanced Voice Insights check now interprets specific quality tags
// (high_jitter, high_packet_loss, silence, etc.), SIP response codes
// (range-based + 20 specific codes), and edge-specific quality metrics
// against thresholds. See [Voice Insights skill](/skills/voice-insights/SKILL.md)
// for full diagnostic workflows.
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.
- yesterday First seen · 507 lines · 10 tokens per session scan A 69697559c400
deep-validation is a skill published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 3,308 once invoked, about $0.0001 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.