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 prismatic7/MASA --skill sound-matter-processinggit clone --depth 1 https://github.com/prismatic7/MASAWrote 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/prismatic7/masa/sound-matter-processing)<a href="https://agentmods.dev/skills/prismatic7/masa/sound-matter-processing"><img src="https://agentmods.dev/badge/skills/prismatic7/masa/sound-matter-processing/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/prismatic7/masa/sound-matter-processing"><img src="https://agentmods.dev/badge/skills/prismatic7/masa/sound-matter-processing.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 | $0.00034 | $0.00485 |
| Opus 5.5 | $0.00014 | $0.00194 |
| Sonnet 5.5 | $0.00007 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
sound-matter-processing 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 1mo 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.
What it actually says
Sound matter processing
Use this procedure when an agent or conventional workflow needs to granulate, extract, reduce, fragment, timestretch, or pitch-shift a representation described by a MASA record. MASA plans and accounts the operation; an external engine performs it.
- Validate the source record and confirm the input representation exists and is available (
matter.validate/masa validate). - Compose a processing request with
matter.plan_processingormasa process template <operation>and edit it: exact input representation identifiers, typed parameters, determinism requirement, and output contract. Validate it withmasa process check. - Resolve policy before any engine runs: the request's
policyRefsname the policies the engine evaluation must cite. Unknown authority, unknown provider terms, or a prohibition on any input blocks the operation; refusal is an outcome, not an error. - Under host authority, hand the request to a granular, spectral, or time-pitch engine through its adapter. The engine returns descendant representations and one OperationReceipt whose Tool names the engine and version, whose parameters echo the typed request parameters, and whose determinism declares seed state.
- Record the results in a derived record: preserve the input representation unchanged, add each descendant with a new identifier, add the receipt to history, and add a lineage relation (
masa:granulated-from,masa:isolated-from,masa:segmented-from, ormasa:derived-from) whoseoperationRefnames the receipt. - Revalidate (
masa validate). A failed, refused, or cancelled engine run keeps its receipt and produces no descendants. - When a listening host is attached (an audio-capable model or listening service), listening passes MAY select regions, strata, or grain schemes — record them as passes and claims, never as unattributed parameters. Re-listen to descendants in new passes when the workflow needs verified accounts of the result.
- Publish descendants only through the public-safe-export procedure; processed matter inherits the policy questions of its sources.
Never treat granulation as destruction of the source, an extraction as the sound's essence, or technical access to bytes as permission to process them.
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.
- 1mo ago First seen · 20 lines · 34 tokens per session scan A e572e14e9a94
sound-matter-processing is a skill published in the GitHub repository prismatic7/MASA (0 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 485 once invoked, about $0.0001 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.
Other skills, from other repositories
metasounds
Create and modify MetaSound Source assets — add/connect nodes, wire pins, set input defaults, and play procedurally (MetaSoundService). Use when the user asks to create a MetaSound, build or edit a MetaSound graph, add operator/input/output nodes, or generate procedural audio.
spoken-response-desktop
Read and embed an assistant response aloud in ChatGPT Desktop (Codex), Antigravity App, OpenCode Desktop, or T3 Code.
create-speech-recording-desktop
Create and embed a speech recording in ChatGPT Desktop (Codex), Antigravity App, OpenCode Desktop, or T3 Code.
spoken-response-controls
Read an assistant response aloud with clickable Agent Voice playback controls. Use when the user explicitly requests controlled playback on a compatible desktop renderer.
create-speech-recording-controls
Turn text into speech with Agent Voice and clickable playback controls. Use when the user explicitly requests controlled playback on a compatible desktop renderer.
create-speech-recording
Turn text into speech with Agent Voice. Use for creating audio recordings and speaking text aloud.