tts

tts is a skill for Claude Code, Codex from Glad-Labs/poindexter. It costs 49 tokens per session (2,555 once invoked), scanned A, original, Apache-2.0.

A pronunciation rule set for text-to-speech (TTS), technology that reads written text aloud. Operators can change how words and abbreviations are spoken by editing JSON settings in the database.

In plain words
What is it for?
Configuring spoken replacements for terms such as NVMe, PostgreSQL, VRAM, and storage units before text is sent to the speech engine.
Why use it?
Written forms such as abbreviations, product names, and technical terms may sound wrong when read aloud. These rules let operators correct or add pronunciations without changing code.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Configuring spoken replacements for terms such as NVMe, PostgreSQL, VRAM, and storage units before text is sent to the speech engine.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/glad-labs/poindexter/tts
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 Glad-Labs/poindexter --skill tts
Clone the repo
git clone --depth 1 https://github.com/Glad-Labs/poindexter

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 tts

README.md
[![agentmods](https://agentmods.dev/badge/skills/glad-labs/poindexter/tts/github.svg)](https://agentmods.dev/skills/glad-labs/poindexter/tts)
Your own site
<a href="https://agentmods.dev/skills/glad-labs/poindexter/tts"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/tts/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 tts

Your own site · 80×15
<a href="https://agentmods.dev/skills/glad-labs/poindexter/tts"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/tts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,555 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 $0.00049 $0.02555
Opus 5 $0.00024 $0.01277
Sonnet 5 $0.00010 $0.00511
Haiku 4.5 $0.00005 $0.00255

Measured 10d ago against content hash bd0fefec160b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

tts 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 10d 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.

src/cofounder_agent/skills/content/tts/SKILL.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TTS pronunciation skill

Controls how the pipeline converts written text to natural spoken audio. Two app_settings keys are the operator interface — both accept JSON and are merged on top of the built-in defaults at render time.

Keys

tts_pronunciations

JSON object mapping a written form to its spoken replacement. Applied as plain string substitutions (case-insensitive). Pure-letter tokens (no punctuation) are matched with word boundaries so short abbreviations like "GB" do not fire inside longer words like "RGB".

DB entries add to (or override) the built-in defaults. To change an existing default, set the same key with a new value. To add a new entry, include only the new key — existing defaults are unaffected.

Format:

{ "written": "spoken", "written2": "spoken2" }

Example — add a custom pronunciation and override an existing one:

poindexter settings set tts_pronunciations \
  '{"NVMe": "N V Me", "PostgreSQL": "post gres"}'

Built-in defaults (seeded at first boot; edit via poindexter settings set):

Written Spoken
VRAM Vee RAM
SRAM Ess RAM
DRAM Dee RAM
PB petabyte
TB terabyte
GB gigabyte
MB megabyte
KB kilobyte
GHz gigahertz
MHz megahertz
kHz kilohertz
Gbps gigabits per second
Mbps megabits per second
Kbps kilobits per second
fps frames per second
GitFlow git flow
GitHub git hub
GitLab git lab
DevSecOps dev sec ops
DevOps dev ops
FastAPI fast A P I
PostgreSQL postgres
GraphQL graph Q L
TypeScript type script
JavaScript java script
CI/CD See Eye See Dee
CI See Eye

Read the full file on GitHub · 243 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. 10d ago First seen · 243 lines · 49 tokens per session scan A bd0fefec160b

Subscribe to this mod's changes

tts is a skill published in the GitHub repository Glad-Labs/poindexter (5 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 2,555 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.