Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add chendrizzy/claude-tts/plugin install claude-ttsWrote 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.
[](https://agentmods.dev/skills/chendrizzy/claude-tts/tts-setup)<a href="https://agentmods.dev/skills/chendrizzy/claude-tts/tts-setup"><img src="https://agentmods.dev/badge/skills/chendrizzy/claude-tts/tts-setup/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.
<a href="https://agentmods.dev/skills/chendrizzy/claude-tts/tts-setup"><img src="https://agentmods.dev/badge/skills/chendrizzy/claude-tts/tts-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.01820 |
| Opus 5 | $0.00023 | $0.00910 |
| Sonnet 5 | $0.00009 | $0.00364 |
| Haiku 4.5 | $0.00005 | $0.00182 |
Grade C, and why
tts-setup scanned grade C with 2 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 8d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
If `command -v uv` fails, install it: `curl -LsSf https://astral.sh/uv/install.sh | sh`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
If `command -v uv` fails, install it: `curl -LsSf https://astral.sh/uv/install.sh | sh`. How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-tts — First-Run Setup
First-run setup for the claude-tts plugin, invoked by /tts:setup. It is
idempotent and re-runnable; /tts:doctor re-checks health anytime.
Fail-stop contract: run the steps in order. After each step, verify it
succeeded. If a step cannot complete, report which step failed and the
single most likely remediation, then STOP — do not continue past a failed
step. Never hardcode absolute personal paths; the config dir is
~/.config/claude-tts and the socket is
${CLAUDE_TTS_SOCKET:-${XDG_RUNTIME_DIR:-/tmp}/claude-tts.sock}.
Let ROOT = the plugin/daemon root (${CLAUDE_PLUGIN_ROOT} when invoked as a
plugin). Run all Python through the project's uv venv: uv run python ....
Step 1 — Detect platform + architecture
Run uname -s (Darwin/Linux) and uname -m (arm64/x86_64). Record both. On
Darwin+arm64 the machine is Apple Silicon (Kokoro is available). Background
service install is automated on both platforms (launchd on macOS, systemd --user on Linux); Step 7 falls back to a manual launch only when no systemd
user session is present.
Step 2 — Ensure uv + environment
If command -v uv fails, install it: curl -LsSf https://astral.sh/uv/install.sh | sh.
Then create the env and install deps from ROOT: uv sync --extra edge (this
project is a uv-managed application — its dependencies live in pyproject.toml
and the default edge-tts engine is the edge extra; there is no
requirements.txt). Verify uv run python -c "import edge_tts" succeeds.
Remediation on failure: ensure network access and that ~/.local/bin is on PATH.
Step 3 — Choose the speech engine
Default: edge-tts (cross-platform, no ML deps). If Apple Silicon, offer Kokoro
(uv run python -c "import mlx_audio" to check; the MLX model pulls on first use).
If a Voicebox app is reachable at its configured URL, offer voicebox. Record
the chosen engine and a default voice_name (en-US-AvaNeural for edge-tts).
If no ML engine is available and uv sync --extra edge cannot install edge-tts
(e.g. offline), choose say (macOS) / espeak (Linux) — the zero-dependency
system engine. It always produces audio on a bare machine (using the OS
default voice; voice_name is ignored for this engine).
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.
- 8d ago First seen · 131 lines · 45 tokens per session scan C 0a71907f0e45
tts-setup is a skill published in the GitHub repository chendrizzy/claude-tts (1 stars, last pushed 22d ago), licensed MIT. It adds 45 tokens to every session and 1,820 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
scroll-craft
Build premium scroll-driven landing pages for service, product, food, and drink brands. Plan the visitor journey, page grammar, emotional peak, and bespoke signature move. Create dimensional heroes with independent visual planes, restrained motion, and separate mobile composition. Use supplied photos and footage or…
a11y-audit
Dedicated WCAG 2.2 AA/AAA accessibility audit across 10 dimensions (A1-A10) covering semantic HTML, keyboard navigation, ARIA patterns, color contrast, forms, images/media, responsive/zoom, motion/animation, reading/content, and legal compliance. Goes far beyond surface-level design-review checks with deep…
wp-responsive
Responsive design patterns — mobile-first breakpoints, fluid typography, responsive images, touch targets.
wp-cli-patterns
WP-CLI-first principle — use WP-CLI instead of generating PHP code whenever possible, with command reference, ACF seeding patterns, and environment-aware execution.
wp-aos-animator
WordPress AOS animation installer — audits, installs, enqueues, initializes, and seeds Animate On Scroll on every visual element across all PHP templates. Use when the user asks to add scroll animations, AOS, fade-in effects, entrance animations, or "make elements appear on scroll" in any WordPress theme.
design-audit
Full project design audit that orchestrates all agents, scores across 12 dimensions, and generates a prioritized action plan. Use when the user asks to audit their design, run a design review or UX audit, review their UI, or asks how their design looks.