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 ARCASSystems/FounderOS --skill add-mouthgit clone --depth 1 https://github.com/ARCASSystems/FounderOSWrote 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/arcassystems/founderos/add-mouth)<a href="https://agentmods.dev/skills/arcassystems/founderos/add-mouth"><img src="https://agentmods.dev/badge/skills/arcassystems/founderos/add-mouth.svg" alt="Measured on agentmods" 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 | $0.00171 | $0.01735 |
| Opus 5 | $0.00086 | $0.00868 |
| Sonnet 5 | $0.00034 | $0.00347 |
| Haiku 4.5 | $0.00017 | $0.00173 |
Grade A, and why
add-mouth 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 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.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a mouth
Runs on: local-exec - the happy path runs a local Python setup that writes a gitignored voice/ config and a say helper, then speaks through your machine. On a read-only or cloud surface, explain the options but do NOT claim the mouth is wired or that anything spoke - it has not until the user runs it locally.
The OS ships complete as text. This adds a mouth: it can speak an answer out loud or render it to an audio file you keep. It is the voice-OUT half of the sensory layer, and it is deliberately separate from add-voice (the full talk-and-listen loop). You can have a mouth without ever holding a conversation - useful when you want a brief read back while your hands are busy, or a draft heard aloud before you send it.
This is the swappable mouth from the brain / mouth / hands scaffold. The brain (your files and answers) stays the same; the mouth is how it speaks. Nothing here is required.
The accessibility floor (the rule that governs the default)
The default mouth is your operating system's own built-in speech - Windows SAPI, macOS say, Linux espeak or spd-say. No extra key, no paid service, no pip install, no model download. It speaks on the subscription-free tools your machine already has. Everything past that is opt-in and disclosed.
The options
| Option | What it adds | Needs | Default? |
|---|---|---|---|
| OS-native | Speak through your machine's built-in voice; render to a file | nothing extra | YES |
| Piper | A noticeably better voice that still runs fully offline | one download + Piper on PATH | no - opt-in, free |
| ElevenLabs | Broadcast-quality voice for something you publish | a paid API key | no - opt-in, paid |
| Browser | The voice the add-voice page already uses, inside that loop |
the add-voice skill |
no - that is the voice loop |
Full detail, the exact install per option, and the cost-and-locality trade are in references/mouth-options.md. The trade is load-bearing: the engine you pick changes voice quality, whether your text leaves the machine, and whether it costs anything. State it before they commit, never after.
What ships with it
3 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.
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 · 89 lines · 171 tokens per session scan A 59e8f9b78cb2
add-mouth is a skill published in the GitHub repository ARCASSystems/FounderOS (5 stars, last pushed 24d ago), licensed MIT. It adds 171 tokens to every session and 1,735 once invoked, about $0.0009 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
slidev
Create and present web-based slidedecks for developers using Slidev with Markdown, Vue components, code highlighting, animations, and interactive features. Use when building technical presentations, conference talks, code walkthroughs, teaching materials, or developer decks.
adv-art
Plan, generate, normalize, validate, and publish visual assets for an ADV.JS game. Use when creating character tachie and expression variants, backgrounds, CG illustrations, thumbnails, or an asset manifest; replacing placeholders with original artwork; preparing immutable CDN/COS object paths; or auditing provenance…
aov-mingyu-api
An interface to the aov.cc public API for Chinese astrology, divination, tarot, calendars, and related prompt generation.
image-gen
Generate images for the user's vault — pick the right provider, gather reference images from notes when relevant, write the result to assets/generated/, and surface the markdown reference. Use this when the user asks for any picture, illustration, mood image, poster, or visual companion to a note.
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
deck-ai
Generate modern presentation decks (PDF) from markdown content. Local open-source alternative to Gamma — uses Slidev for layouts and Unsplash for imagery. Invoke when the user asks to "make a deck", "build slides from this", or "turn this into a presentation".