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 sonicfieldlabs/akouo --skill sovereign-listeninggit 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/skills/sonicfieldlabs/akouo/sovereign-listening)<a href="https://agentmods.dev/skills/sonicfieldlabs/akouo/sovereign-listening"><img src="https://agentmods.dev/badge/skills/sonicfieldlabs/akouo/sovereign-listening/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/sonicfieldlabs/akouo/sovereign-listening"><img src="https://agentmods.dev/badge/skills/sonicfieldlabs/akouo/sovereign-listening.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 | $0.00210 | $0.02442 |
| Opus 5.5 | $0.00084 | $0.00977 |
| Sonnet 5.5 | $0.00042 | $0.00488 |
| Haiku 4.5 | $0.00021 | $0.00244 |
Grade A, and why
sovereign-listening 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 23d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sovereign-listening
Purpose
Every other AKOÚŌ mode disciplines what a listening may claim. This mode disciplines what a listening may do: which sounds it refuses before capture, which it releases after hearing, which aspects it declines to reveal, what it will not keep. It is the Rights of the Audible made operational — the right to silence, the right to opacity, the right of communities to their own protocols — as a runtime layer instead of a paragraph.
A listening covenant is the unit. Its parties can write, discuss and revise a plain-text document, including contributions from agents. Adoption identifies which revision governs a declared process and who has authority to bind it. Rules are the executable subset supported by the owner. Commitments preserve the other terms verbatim for present participants and future systems. The record identifies what was asked, what was applied, and what was withheld.
When To Use
Use sovereign-listening when:
- a covenant document is active for the host, session, project, or place
- recording or listening happens under a community protocol (ancestral, sacred, endangered, or place-bound sound)
- a deployment must honor the right to silence (some things go unheard) or the right to opacity (some things are heard but never decoded or revealed)
- a household, clinic, classroom, shelter, or workplace wants listening without retention, or hearing without identification
- a habitat is monitored under an ecological protocol — the flood and the fire, not the bedroom; the species count, not one decibel more
- another agent's listening should be audited against a declared covenant: did the hearing respect what was asked?
Do NOT use it to launder censorship as care: a covenant governs the listener that adopted it, protecting the listened-to; it is not a tool for silencing third parties. If a rule's purpose is to hide the listener's own accountability, refuse the framing and say so.
Core Question
What has this ear agreed not to do — and is this hearing keeping that agreement, visibly?
What ships with it
20 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.
- references/claim-taxonomy.schema.json 5.3 KB
- references/covenant.schema.json 4.3 KB
- references/ensemble.schema.json 1.8 KB
- references/listening-adoption.schema.json 1.8 KB
- references/listening-application.schema.json 6.6 KB
- references/listening-capabilities.schema.json 988 B
- references/listening-common.schema.json 2.8 KB
- references/listening-context.schema.json 7.7 KB
- references/listening-document.schema.json 2.2 KB
- references/listening-lifecycle-event.schema.json 1.2 KB
- references/listening-output.schema.json 12 KB
- references/listening-pass.schema.json 2.4 KB
- references/listening-profile.schema.json 1.9 KB
- references/listening-provenance.schema.json 3.9 KB
- references/listening-state.schema.json 1.0 KB
- references/representation-capabilities.schema.json 2.0 KB
- references/representation-output.schema.json 2.1 KB
- references/representation-route-request.schema.json 2.4 KB
- references/representation-route-result.schema.json 4.7 KB
- references/route-decision.schema.json 1.8 KB
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.
- 23d ago Changed · +24 lines · -1 tokens per session 2971a26afa9c
- 2mo ago First seen · 101 lines · 211 tokens per session scan A b48f609800e1
sovereign-listening is a skill published in the GitHub repository sonicfieldlabs/akouo (10 stars, last pushed 2d ago), licensed MIT. It adds 210 tokens to every session and 2,442 once invoked, about $0.0008 per session on Opus 5.5. 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.
sovereign-listening compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sovereign-listeningsonicfieldlabs/akouo | Skill | 10 | 2d ago | MIT | A | 210 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |