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 skills add Engr-FaizanAli/text-to-speech-mcp --skill project-tts-respondergit clone --depth 1 https://github.com/Engr-FaizanAli/text-to-speech-mcpWrote 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/engr-faizanali/text-to-speech-mcp/project-tts-responder)<a href="https://agentmods.dev/skills/engr-faizanali/text-to-speech-mcp/project-tts-responder"><img src="https://agentmods.dev/badge/skills/engr-faizanali/text-to-speech-mcp/project-tts-responder/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/engr-faizanali/text-to-speech-mcp/project-tts-responder"><img src="https://agentmods.dev/badge/skills/engr-faizanali/text-to-speech-mcp/project-tts-responder.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 | $0.00079 | $0.01241 |
| Opus 5 | $0.00039 | $0.00620 |
| Sonnet 5 | $0.00016 | $0.00248 |
| Haiku 4.5 | $0.00008 | $0.00124 |
Grade A, and why
project-tts-responder 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TTS Responder
This skill drives the speak_text tool exposed by the Text to Speech MCP
server: a local, no-API-key server that gives any MCP client a voice using the
speech synthesizer built into the host operating system.
Choosing a mode
Use the mode the user asks for. If they do not say, default to Batch.
A host project can make one mode the standing default by saying so in its own agent instructions, for example "narrate every response in Batch mode unless the user opts out". Without that, this skill applies only when the user asks for audio.
1. Batch — one playback at the end of the turn
Display every intermediate update and the final response normally, calling
nothing yet. After the final response has been sent and is visible, make a
single speak_text call containing every visible intermediate update in
chronological order followed by the exact final response, separated by blank
lines. That is the only speak_text call for the turn.
Send the final response first, so it is on screen before playback starts. Nothing further should follow the playback call unless it fails.
2. Streaming — narrate as you go
For each visible intermediate update: display the text, then call speak_text
with that exact text, and wait for playback to finish before producing the next
update. Do the same for the final response last.
Streaming suits demos and walkthroughs. It costs one call per update, so it is the wrong default for ordinary work.
3. Read specific content on request
When asked to read, play, or speak a named file or block of text, call
speak_text once with that content verbatim. Add no commentary inside the
call. If the content exceeds the tool's input limit, say which part you are
reading and read a clearly stated excerpt.
What to read aloud
Only user-visible assistant content:
- Progress updates already sent during this turn.
- The final answer, exactly as sent.
- Command results only when they already appear in those visible messages.
- File paths and report names when they help.
- Any interactive question or interrupt, including every option offered.
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.
- 12d ago First seen · 128 lines · 79 tokens per session scan A 4e01a56e2b59
project-tts-responder is a skill published in the GitHub repository Engr-FaizanAli/text-to-speech-mcp (1 stars, last pushed 23d ago), licensed MIT. It adds 79 tokens to every session and 1,241 once invoked, about $0.0004 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
agent-desktop
Reliable computer use via native OS accessibility trees. Use when an AI agent needs to see and operate desktop applications (click buttons, fill forms, navigate menus, read UI state, toggle checkboxes, scroll, drag, type text, take screenshots, manage windows, use clipboard, manage notifications). Covers 59 command…
harness-design-fuzzing
Reference vocabulary for designing instrumented harnesses that drive vulnerability discovery — design classes (trigger-driven vs coverage-driven), tiered scope (T1 isolated function / T2 multi-component / T3 full build), systematic input exploration, the two-coverage distinction (fuzzer-feedback vs audit)…
memory-safety-c-cpp
Reference vocabulary for memory-safety vulnerabilities in native C/C++ code — bug-class taxonomy, common arithmetic patterns that lead to corruption, dispatch-family discipline, type-confusion idioms, use-after-free patterns, and exploitability factors. Read when analyzing, hypothesizing, designing harnesses for, or…
email-formatting
Markdown formatting conventions for email summary documents — heading depth, list style, line length, emoji policy, and a mandatory provenance footer. Read this when producing a markdown report that summarizes one or more email messages so the output matches the project's house style.
json-schema-emails
Canonical shape of the .workflow/emails/emails.json file passed between the fetch and summarize states — required fields (sender, recipient, subject, date, body), types, and field semantics. Read this whenever you write or read emails.json so producer and consumer agree on the shape.
kmsg
Use KMSG to read, watch, and send KakaoTalk messages safely from a coding agent. Use whenever the user mentions KakaoTalk or kmsg and wants chat discovery, recent messages, monitoring, text or image delivery, setup checks, or CLI troubleshooting. Do not use for other messaging platforms or private KakaoTalk protocol…