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/sonicfieldlabs/akouo/reference-layernpx skills add sonicfieldlabs/akouo --skill reference-layergit 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/reference-layer)<a href="https://agentmods.dev/skills/sonicfieldlabs/akouo/reference-layer"><img src="https://agentmods.dev/badge/skills/sonicfieldlabs/akouo/reference-layer.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 | $0.00145 | $0.01597 |
| Opus 5 | $0.00072 | $0.00798 |
| Sonnet 5 | $0.00029 | $0.00319 |
| Haiku 4.5 | $0.00015 | $0.00160 |
Grade A, and why
reference-layer 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
reference-layer
Purpose
reference-layer is the conceptual mapping ear of akoúō. It does not listen to the sound directly. It listens to the listening: it takes a sonic object, a prior listening output, or a research intent and maps it to concepts, methodologies, traditions, research routes, questions, cautions, and adjacent listening modes.
Like akouo-router, this is a meta-skill. The router decides how to listen before analysis; the reference layer decides where the listening sits in existing methods and what could responsibly come next in research.
When To Use
Use this skill for:
- turning a listening report into research routes and questions
- mapping a sonic object or method question to sound studies concepts and traditions
- essay, thesis, project, workshop, and fieldwork method development
- naming cautions before deeper interpretation
- choosing adjacent listening modes for the next pass
- the mapping step inside
/reference,/study, and/method
Core Question
Which concepts, methods, traditions, questions, and cautions does this listening situation activate, and which adjacent ears should hear it next?
Conceptual Refinements
- A reference is a route, not an authority: naming a concept or tradition opens a path of inquiry; it never proves an interpretation.
- Methods and concepts answer to the object: every mapped route must stay tied to the actual sound, prompt, archive, or prior listening output.
- Traditions are situated: sound studies categories travel with histories and exclusions; do not universalize Western or Northern framings as default method.
- Cautions are part of the map: each conceptual route carries its own overreach risks, and the map must name them alongside the affinities.
- The reference layer inherits the claim discipline: concepts and traditions belong to
interpretedreasoning; they never upgrade a claim's evidence category. - References should distinguish a source of sound from a source of listening: apparatus, corpus, platform, archive, field relation, and inherited terminology can all condition the ear.
- Several temporal passes are not one timeless object. When a route spans seasons, archives, revisions, or model generations, name those times and the cuts between them.
What ships with it
8 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/reference-map.schema.json 1.2 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.
- 3d ago First seen · 113 lines · 145 tokens per session scan A 1db29ed699a3
reference-layer is a skill published in the GitHub repository sonicfieldlabs/akouo (10 stars, last pushed 22d ago), licensed MIT. It adds 145 tokens to every session and 1,597 once invoked, about $0.0007 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
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…
extracting-pii-entities
Detect PHI/PII spans in clinical text with OpenMed's extractpii without altering the text. Use when the user wants to find names, dates, MRNs, phone numbers, addresses, SSNs, or other identifiers and get their offsets and labels (not redact them), inspect what would be removed before de-identifying, route spans to a…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
tooluniverse-electron-microscopy
Search and analyze electron microscopy data — cryo-EM density maps (EMDB), fitted atomic models (PDB), raw micrograph datasets (EMPIAR), and cryo-electron tomography volumes (CryoET Data Portal). Use for finding 3D structural data on a protein/complex, comparing experimental EM resolution to AlphaFold confidence, and…
tooluniverse-drug-research
Comprehensive drug profiling — mechanism, primary/secondary targets, drug interactions, clinical-trial status, adverse events (FAERS), pharmacogenomics, and approval history. Use for full drug investigation reports, 'tell me about drug X' queries, and assembling drug profiles for clinicians, researchers, or regulatory…