remember

remember is a command for coding agents from sonicfieldlabs/akouo. It costs 0 tokens per session (760 once invoked), scanned A, original, MIT.

A command for recording and comparing listening experiences in a sound-memory store. It tracks how a sound relates to earlier sounds, such as a variation, response, or repetition.

In plain words
What is it for?
Use it to register a new listening, compare it with stored records, preserve its lineage, review existing records, or check what the archive lacks without writing a new record.
Why use it?
It prevents important listening observations from being lost and helps reveal how sounds change over time.

Command

Install

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.

agentmods
npx agentmods add commands/sonicfieldlabs/akouo/remember
Clone the repo
git clone --depth 1 https://github.com/sonicfieldlabs/akouo

Wrote 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.

agentmods badge for remember

README.md
[![agentmods](https://agentmods.dev/badge/commands/sonicfieldlabs/akouo/remember.svg)](https://agentmods.dev/commands/sonicfieldlabs/akouo/remember)
Your own site
<a href="https://agentmods.dev/commands/sonicfieldlabs/akouo/remember"><img src="https://agentmods.dev/badge/commands/sonicfieldlabs/akouo/remember.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 760 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00760
Opus 5 $0.00000 $0.00380
Sonnet 5 $0.00000 $0.00152
Haiku 4.5 $0.00000 $0.00076

Measured 3d ago against content hash 90d2c4551325, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

remember 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 3d 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.

commands/remember.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/remember

Purpose

/remember is the memory command of akoúō. It situates one sonic object in its lineage against a sound-memory store and registers the present listening into that store.

Use it when a listening should not evaporate: when the sound belongs to a series, an archive, a practice, or a body of work whose memory matters.

When To Use

Use /remember for:

  • registering a listening into an akousma/akousmata-style store or any sound-memory record system
  • comparing a new sound against stored records before deciding it is new
  • longitudinal listening: same place, instrument, voice, or system across time
  • keeping lineage: what a sound derives from, varies, answers, or repeats
  • reviewing what the store already holds — and lacks — about a sound

For memory comparison WITHOUT writing, run the same chain under a read-only preset (recall in presets/presets.json) or state explicitly that no record should be created.

Skills Called

  • akouo-router
  • memory-lineage-listening (primary)
  • acoulogical-object-listening (secondary)
  • signal-inspection-listening (corrective)

Execution Order

  1. Run akouo-router; confirm store availability is part of the evidence inventory.
  2. Run acoulogical-object-listening for a fresh perceptual description that memory must not overwrite.
  3. Run memory-lineage-listening against the consulted records.
  4. Run signal-inspection-listening as corrective when apparent recurrence or change could be apparatus difference.
  5. Synthesize; populate the memory block (akousma_id, akousmata_refs, lineage_note) on outputs the host will store.
  6. When the host store speaks akousma spec v1.2, pass through its location (where heard) and capture (past/future direction + window seconds) blocks untouched — they are the host's record, not listening claims. Claims that lean on them take source: "metadata"; location is consent-scoped and never travels further than the store the host names.

Expected Output

Read the full file on GitHub · 68 lines

Changes

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.

  1. 3d ago First seen · 68 lines · 0 tokens per session scan A 90d2c4551325

Subscribe to this mod's changes

remember is a command published in the GitHub repository sonicfieldlabs/akouo (10 stars, last pushed 22d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 760 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.