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 memory-lineage-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/memory-lineage-listening)<a href="https://agentmods.dev/skills/sonicfieldlabs/akouo/memory-lineage-listening"><img src="https://agentmods.dev/badge/skills/sonicfieldlabs/akouo/memory-lineage-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/memory-lineage-listening"><img src="https://agentmods.dev/badge/skills/sonicfieldlabs/akouo/memory-lineage-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 | $0.00175 | $0.02561 |
| Opus 5 | $0.00088 | $0.01281 |
| Sonnet 5 | $0.00035 | $0.00512 |
| Haiku 4.5 | $0.00017 | $0.00256 |
Grade A, and why
memory-lineage-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 11d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memory-lineage-listening
Purpose
memory-lineage-listening is the memory ear of akoúō. It listens to the present sound through what the store already holds: earlier listening records, their claims, their provenance, and their lineage links.
A stored sound-memory is not a frozen copy of a past event. Replaying or re-reading a record reactualizes it under new conditions, so every comparison is a new listening, not a lookup. This mode keeps that distinction audible: it reports what the store suggests while marking memory as its own evidence stream, never as direct proof about the present sound.
This is also the mode that writes memory well. When a workflow registers a listening into a store, this ear decides what the record should carry: which claims, which apparatus declaration, which lineage note, and which uncertainties must travel with the sound into every later context.
When To Use
Use this skill for:
- comparing a current sound against stored listening records
- recurrence questions: have we heard this, or something kin to it, before?
- lineage questions: what does this sound derive from, vary, answer, or repeat?
- change-over-time questions across a series of recordings of the same place, instrument, voice, or system
- registering a new listening into a sound-memory store with lineage notes
- reviewing what an archive holds about a sound, and what it conspicuously lacks
- auditing a store: duplication, gaps, absent provenance, dead or unattributable records
Core Question
What do our stored listenings suggest about this sound, what is this sound's lineage, and what must the present listening refuse to inherit from memory?
Conceptual Refinements
- Memory is an evidence stream of its own. Claims that come from stored records take
source: "memory"and never migrate intoheardormeasuredfor the present sound. - A store reflects its curation, not the world. Absence from the store is not novelty in the world; presence in the store is not importance. Say which store was consulted and how far the query reached.
- Records reactualize. A stored record was produced by a specific apparatus under a specific contract; comparing it to the present sound compares two listenings, not two sounds. Prefer comparing claims-with-provenance over comparing summaries.
- Lineage is a relation between records, not a causal proof. "Derived from", "variant of", "response to", and "recurrence of" are curatorial links; keep them in
interpretedunless the store carries verified provenance for the derivation. - Dead records count. A record with missing provenance, a broken media reference, or an unreachable source is still lineage information; report it as an archive-of-absence rather than discarding it.
- Memory can be extractive. Recording someone's sound into a store is an act with consent and access stakes; registering a listening should carry the capture conditions and rights notes the store requires, and flag their absence.
What ships with it
7 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/ensemble.schema.json 1.8 KB
- references/listening-context.schema.json 7.7 KB
- references/listening-output.schema.json 11 KB
- references/listening-pass.schema.json 2.4 KB
- references/listening-provenance.schema.json 3.9 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.
- 11d ago First seen · 138 lines · 175 tokens per session scan A 440cbf605a5f
memory-lineage-listening is a skill published in the GitHub repository sonicfieldlabs/akouo (10 stars, last pushed 1mo ago), licensed MIT. It adds 175 tokens to every session and 2,561 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
tts-voice
Convert text to natural speech audio. Uses Edge-TTS (free) or OpenAI TTS. Excellent Chinese voice support.
image-gen
Generate images via DALL-E, Stable Diffusion, or free alternatives. Supports multi-channel delivery.
ppt-author
Create and edit PowerPoint (.pptx) presentations programmatically. Requires python-pptx.
voice-note
Convert voice messages to text (STT) and text to voice (TTS). Supports Whisper local model and Edge-TTS.
higgsfield-recall
Use this skill AUTOMATICALLY before writing any Higgsfield prompt. Query the memory databases for relevant past failures and pre-apply known fixes before the user even hits generate. Triggers include: any request to write a Higgsfield prompt, any use of the higgsfield-prompt skill, any mention of generating a video or…
higgsfield-recall
Use this skill AUTOMATICALLY before writing any Higgsfield prompt. Query the memory databases for relevant past failures and pre-apply known fixes before the user even hits generate. Triggers include: any request to write a Higgsfield prompt, any use of the higgsfield-prompt skill, any mention of generating a video or…