agentmods.dev

cxas-composite-voice-agent-optimizer

cxas-composite-voice-agent-optimizer is a skill for Claude Code, Codex from GoogleCloudPlatform/cxas-scrapi. It costs 141 tokens per session (9,452 once invoked), scanned A, original, Apache-2.0.

A tool for checking and adjusting Google Cloud CX Agent Studio and Customer Engagement Suite voice-agent configurations for Gemini Composite V1. It produces prioritized readiness reports and can apply automated fixes to local agent files.

In plain words
What is it for?
Use it when adapting or reviewing a CXAS voice agent for Gemini Composite V1, generating an HTML or Markdown assessment, or applying supported configuration fixes.
Why use it?
Changing a voice agent to a different model can affect voice naturalness, persona consistency, and language coverage. This identifies and addresses those configuration issues.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

not rated 116repo +2 changed 3d ago A scan 141 tokens original Apache-2.0

Good fit Use it when adapting or reviewing a CXAS voice agent for Gemini Composite V1, generating an HTML or Markdown assessment, or applying supported configuration fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/googlecloudplatform/cxas-scrapi/cxas-composite-voice-agent-optimizer
View source ↗ GoogleCloudPlatform/cxas-scrapi
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 GoogleCloudPlatform/cxas-scrapi --skill cxas-composite-voice-agent-optimizer
Clone the repo
git clone --depth 1 https://github.com/GoogleCloudPlatform/cxas-scrapi

Made for: Claude Code, Codex.

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 cxas-composite-voice-agent-optimizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/googlecloudplatform/cxas-scrapi/cxas-composite-voice-agent-optimizer/github.svg)](https://agentmods.dev/skills/googlecloudplatform/cxas-scrapi/cxas-composite-voice-agent-optimizer)
Your own site
<a href="https://agentmods.dev/skills/googlecloudplatform/cxas-scrapi/cxas-composite-voice-agent-optimizer"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/cxas-scrapi/cxas-composite-voice-agent-optimizer/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 cxas-composite-voice-agent-optimizer

Your own site · 80×15
<a href="https://agentmods.dev/skills/googlecloudplatform/cxas-scrapi/cxas-composite-voice-agent-optimizer"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/cxas-scrapi/cxas-composite-voice-agent-optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,452 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 $0.00141 $0.09452
Opus 5.5 $0.00056 $0.03781
Sonnet 5.5 $0.00028 $0.01890
Haiku 4.5 $0.00014 $0.00945

Measured 3d ago against content hash f9533ed901e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cxas-composite-voice-agent-optimizer 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 3d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/audit_agent.py, scripts/tests/audit_agent_test.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/cxas-composite-voice-agent-optimizer/SKILL.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CXAS Composite Voice Agent Optimizer

This skill audits, optimizes, and remediates Google Cloud CX Agent Studio (CXAS) and Customer Engagement Suite (CES) agent configurations for Gemini Composite v2 voice naturalness, persona stability, and multi-language parity.

All core operations execute purely on local workspace files (app.json, global_instruction.txt, agents/*/instruction.txt, tools/, callbacks/). The cxas CLI can be used to manage local agent workspaces (cxas pull, cxas lint, cxas push).

Migrating to Composite v2 has three parts:

  1. Model, voice & speaking style. Set modelSettings.model to gemini-composite-v2 (temperature and speakingRate are not Composite v2 requirements and are untouched by --remediate), configure prebuilt Chirp 3 HD voices (defaulting to Aoede, <locale>-Chirp3-HD-Aoede) or custom cloned voices (customVoiceSamples[] with "voiceInstructionMode": "NO_INSTRUCTION"), clear Director's Notes, and keep prebuilt speaking style instructions (synthesizeSpeechConfigs.<lang>.instruction) empty ("") or concise (≤ 25 words — ideally a ~12-word speaker-identity profile; custom cloned voices always use "").
  2. Audio tags. Use English angle brackets (<warm>, <breath>, <short pause>), which are read aloud far less often than square brackets ([warm]) and followed more reliably. Put style and sound tags at the start of the sentence they color, use only pause tags mid-sentence (after punctuation), never write closing tags (</prosody> before speech becomes <prosody rate="100%">), and replace poorly performing or translated tags with evaluated English ones.
  3. Prompt hygiene & conditional text normalization. Merge the affective delivery guidelines into the global instruction and resolve contradictions. Rely on platform runtime inline TTS text normalization for en-*, fr/fr-CA, and es/es-US (do not add generic text normalization rules there); include a Scope:-guarded <instruction id="text normalization for speech"> block only when the app declares unsupported locales or needs domain-specific spoken overrides (42 GB of 100 GB, Mbps, /IPA/).

Read the full file on GitHub · 322 lines

Files

What ships with it

6 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.

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. 3d ago Changed · +10 lines · +33 tokens per session f9533ed901e3
  2. 9d ago Changed · -4 lines · +38 tokens per session a2de29f96e54
  3. 1mo ago Changed · +26 lines d93c1f638037
  4. 1mo ago First seen · 290 lines · 70 tokens per session scan A 5247802db493

Subscribe to this mod's changes

cxas-composite-voice-agent-optimizer is a skill published in the GitHub repository GoogleCloudPlatform/cxas-scrapi (116 stars, last pushed yesterday), licensed Apache-2.0. It adds 141 tokens to every session and 9,452 once invoked, about $0.0006 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 2026-09-12.

Building agentsLocalization
Related

cxas-composite-voice-agent-optimizer compared with skills from other repositories

cxas-composite-voice-agent-optimizer next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cxas-composite-voice-agent-optimizerGoogleCloudPlatform/cxas-scrapiSkill116yesterdayApache-2.0A141Claude Code, Codex
intl-expansionalirezarezvani/claude-skillsSkill29kyesterdayMITA27Claude Code
azure-ai-translation-text-pymicrosoft/skillsSkill3.2kyesterdayMITA60Claude Code
chinese-documentationjnMetaCode/superpowers-zhSkill8.5k11d agoMITA62Claude Code
hardenfengshao1227/ccg-workflowSkill6.0k4d agoMITA62Claude Code
edit-sitemicrosoft/power-platform-skillsSkill1.1kyesterdayMITA104Claude Code
asc-subscription-localizationrorkai/app-store-connect-cli-skillsSkill1.1kyesterdayMITA60Claude Code