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 commands/sonicfieldlabs/akouo/voicegit clone --depth 1 https://github.com/sonicfieldlabs/akouoWrote 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/commands/sonicfieldlabs/akouo/voice)<a href="https://agentmods.dev/commands/sonicfieldlabs/akouo/voice"><img src="https://agentmods.dev/badge/commands/sonicfieldlabs/akouo/voice.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 | $0.00000 | $0.00641 |
| Opus 5 | $0.00000 | $0.00320 |
| Sonnet 5 | $0.00000 | $0.00128 |
| Haiku 4.5 | $0.00000 | $0.00064 |
Grade A, and why
voice 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 6d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/voice
Purpose
/voice is the voice and speech command. It separates vocal sound, transcript content, ASR output, TTS, voice-agent behavior, identity caution, consent, and access paths.
When To Use
Use /voice for:
- spoken audio
- transcripts and captions
- podcasts, radio, interviews, and voice notes
- ASR, diarization, TTS, dubbing, voice cloning, and voice agents
- voice interfaces and agentic workflows
- identity, consent, intelligibility, or accessibility concerns
Skills Called
akouo-routeras an implicit planning pass that supplies the evidence inventory, risks, and forbidden assumptions the synthesis must respectvoice-speech-listeningtransductive-media-listeningaccessibility-normative-listeningcritical-political-listeningwhen identity, consent, surveillance, platform, dataset, labor, or institutional stakes appear
Execution Order
- Run
voice-speech-listeningto separate vocal sound, speech content, transcript, identity claims, and voice mediation. - Run
transductive-media-listeningwhen ASR, TTS, voice agents, voice cloning, codecs, platforms, or model outputs are involved. - Run
accessibility-normative-listeningto audit captions, transcript path, intelligibility, hearing assumptions, and alternate access. - Run
critical-political-listeningwhen the voice is tied to consent, surveillance, labor, dataset, identity, archive, platform, or institutional risk. - Synthesize with strict separation between heard voice, text evidence, model output, interpretation, speculation, and unknowns.
Expected Output
Use schemas/command-output.schema.json.
The output must include:
- what is voice evidence, transcript evidence, model evidence, or only prompt evidence
- identity and consent cautions
- transcript, caption, ASR, or diarization limits
- access paths and missing access paths
- mediation chain when known
- recommended next mode
Guardrails
- A transcript is not the whole voice.
- A voice is not proof of identity, age, gender, ethnicity, disability, sincerity, or emotion.
- ASR and diarization are representations, not neutral capture.
- Treat consent, dataset provenance, and platform mediation as unknown unless supplied.
- Keep accessibility integral to voice analysis, not an optional afterthought.
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.
- 6d ago First seen · 66 lines · 0 tokens per session scan A 0d8a8fd3d5ce
voice is a command published in the GitHub repository sonicfieldlabs/akouo (10 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 641 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.