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 agentmods add skills/understudy-ai/understudy/sagnpx skills add understudy-ai/understudy --skill saggit clone --depth 1 https://github.com/understudy-ai/understudyWhat 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 | $0.00016 | $0.00706 |
| Opus 5 | $0.00008 | $0.00353 |
| Sonnet 5 | $0.00003 | $0.00141 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
sag 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 2d 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.
This is a copy
95% identical to sag — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
sag
Use sag for ElevenLabs TTS with local playback.
API key (required)
ELEVENLABS_API_KEY(preferred)SAG_API_KEYalso supported by the CLI
Quick start
sag "Hello there"sag speak -v "Roger" "Hello"sag voicessag prompting(model-specific tips)
Model notes
- Default:
eleven_v3(expressive) - Stable:
eleven_multilingual_v2 - Fast:
eleven_flash_v2_5
Pronunciation + delivery rules
- First fix: respell (e.g. "key-note"), add hyphens, adjust casing.
- Numbers/units/URLs:
--normalize auto(oroffif it harms names). - Language bias:
--lang en|de|fr|...to guide normalization. - v3: SSML
<break>not supported; use[pause],[short pause],[long pause]. - v2/v2.5: SSML
<break time="1.5s" />supported;<phoneme>not exposed insag.
v3 audio tags (put at the entrance of a line)
[whispers],[shouts],[sings][laughs],[starts laughing],[sighs],[exhales][sarcastic],[curious],[excited],[crying],[mischievously]- Example:
sag "[whispers] keep this quiet. [short pause] ok?"
Voice defaults
ELEVENLABS_VOICE_IDorSAG_VOICE_ID
Confirm voice + speaker before long output.
Chat voice responses
When Peter asks for a "voice" reply (e.g., "crazy scientist voice", "explain in voice"), generate audio and send it:
# Generate audio file
sag -v Clawd -o /tmp/voice-reply.mp3 "Your message here"
# Then include in reply:
# MEDIA:/tmp/voice-reply.mp3
Voice character tips:
- Crazy scientist: Use
[excited]tags, dramatic pauses[short pause], vary intensity - Calm: Use
[whispers]or slower pacing - Dramatic: Use
[sings]or[shouts]sparingly
Default voice for Clawd: lj2rcrvANS3gaWWnczSX (or just -v Clawd)
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.
- 2d ago First seen · 88 lines · 16 tokens per session scan A ad43fcf04751
sag is a skill published in the GitHub repository understudy-ai/understudy (456 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 706 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to sag, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
whatsapp-send-skill
Send WhatsApp messages to contacts, groups, or channels. Supports text, images, videos, audio, documents, stickers, locations, and contacts.
audio-skill
Control Android audio - get/set volume, mute/unmute for media, ringtone, notification, and call volumes.
speech-skill
Convert text to spoken audio and transcribe audio to text, across multiple speech providers (OpenAI, ElevenLabs, Deepgram, Groq, Sarvam AI).
vrm-springbone-physics
Debugging and fixing VRM SpringBone physics issues in three-vrm, including hair/clothing physics that flies upward, sticks out horizontally, or behaves unnaturally.
tts-error-reporting
Convention for reporting errors from multiprocessing TTS workers to the main process frontend. Use this skill when modifying, adding, or debugging TTS workers in ttsclient.py to ensure connection errors, quotas, and API limits correctly display Toast notifications to the user rather than failing silently.
release-openclaw-maintainer
Prepare or verify OpenClaw stable, beta, and extended-stable releases, including backport discovery, changelogs, release notes, publish commands, and artifacts.