agentmods.dev

verify-phone-agent

verify-phone-agent is a skill for Claude Code from bobbylkchao/ai-phone-agent. It costs 28 tokens per session (105 once invoked), scanned A, original, MIT.

A verification procedure for changes to an AI phone agent, including its TypeScript code, settings, dependencies, or call flows. It runs formatting, lint checks, tests, and a production build in a fixed order.

In plain words
What is it for?
Use it after changing the phone agent to run the required checks and report each result, with any remaining manual probe noted for call-flow work.
Why use it?
It gives a consistent completion check and stops at the first failed step. For call-flow changes, it also makes clear that a manual Amazon Connect or HTTP check may still be needed.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

not rated 110repo 1mo ago A scan 28 tokens original MIT

Good fit Use it after changing the phone agent to run the required checks and report each result, with any remaining manual probe noted for call-flow work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bobbylkchao/ai-phone-agent/verify-phone-agent
View source ↗ bobbylkchao/ai-phone-agent
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.

Any agent
npx skills add bobbylkchao/ai-phone-agent --skill verify-phone-agent
Clone the repo
git clone --depth 1 https://github.com/bobbylkchao/ai-phone-agent

Made for: Claude Code.

Wrote 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.

agentmods badge for verify-phone-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/bobbylkchao/ai-phone-agent/verify-phone-agent/github.svg)](https://agentmods.dev/skills/bobbylkchao/ai-phone-agent/verify-phone-agent)
Your own site
<a href="https://agentmods.dev/skills/bobbylkchao/ai-phone-agent/verify-phone-agent"><img src="https://agentmods.dev/badge/skills/bobbylkchao/ai-phone-agent/verify-phone-agent/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.

agentmods 80×15 button for verify-phone-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/bobbylkchao/ai-phone-agent/verify-phone-agent"><img src="https://agentmods.dev/badge/skills/bobbylkchao/ai-phone-agent/verify-phone-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 105 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00028 $0.00105
Opus 5.5 $0.00011 $0.00042
Sonnet 5.5 $0.00006 $0.00021
Haiku 4.5 $0.00003 $0.00011

Measured 1mo ago against content hash 2f7f27eb5da3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify-phone-agent 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.

.claude/skills/verify-phone-agent/SKILL.md · 16 lines

What it actually says

Verify AI Phone Agent changes

Run in order and stop on the first failure:

  1. npm run format
  2. npm run lint:ci
  3. npm run test:ci
  4. npm run build

Report each result. For call-flow changes, also describe the relevant manual Amazon Connect or HTTP probe that remains.

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. 1mo ago First seen · 16 lines · 28 tokens per session scan A 2f7f27eb5da3

Subscribe to this mod's changes

verify-phone-agent is a skill published in the GitHub repository bobbylkchao/ai-phone-agent (110 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 105 once invoked, about $0.0001 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 2026-09-13.

LanguagesTestingai-phoneai-phone-agentamazon-connectjavascriptnodejsopenai
Related

verify-phone-agent compared with skills from other repositories

verify-phone-agent next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
verify-phone-agentbobbylkchao/ai-phone-agentSkill1101mo agoMITA28Claude Code
psl-ast-layersprisma/ormSkill48k2d agoApache-2.0A78Claude Code, Codex
ast-visitor-patternprisma/ormSkill48k2d agoApache-2.0A65Claude Code, Codex
no-bare-castsprisma/ormSkill48k2d agoApache-2.0A52Claude Code, Codex
bumping-biomeprisma/ormSkill48k2d agoApache-2.0A96Claude Code, Codex
ax-cpp-aiax-llm/axSkill3.0k2d agoApache-2.0A47Claude Code, Codex
ax-cpp-genax-llm/axSkill3.0k2d agoApache-2.0A48Claude Code, Codex