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 BlackBeltTechnology/pi-agent-dashboard --skill soundcraftgit clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboardWrote 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/blackbelttechnology/pi-agent-dashboard/soundcraft)<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/soundcraft"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/soundcraft/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/blackbelttechnology/pi-agent-dashboard/soundcraft"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/soundcraft.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 | $0.00091 | $0.02254 |
| Opus 5.5 | $0.00036 | $0.00902 |
| Sonnet 5.5 | $0.00018 | $0.00451 |
| Haiku 4.5 | $0.00009 | $0.00225 |
Grade A, and why
soundcraft 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 yesterday.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SoundCraft — headless audio editing and mixing
SoundCraft is ArtCraft's DAW-style editor (sessions, tracks, clips, fades, mixer). pi-craft provisions the
headless soundcraft-cli (no desktop app). Choosing between apps, the discover → execute → save → verify loop
and the MCP policy live in craft-studio; this skill is the SoundCraft dialect and its traps.
What it is for / formats
Imports and bounces wav aiff flac (bounce: format, bit_depth 16/24/32f); info FILE summarises an audio
file or a session. Project file: .scraft (the session; its audio lives in an Audio Files/ folder beside it).
Hand-off to a video editor: bounce wav (see craft-studio).
CLI dialect
pi-craft soundcraft exec <args…> passes <args…> to soundcraft-cli verbatim. Unlike FilmCraft there is no
exec <id>: one invocation = one run (a list of --cmds, optional bounce).
pi-craft soundcraft exec commands [FILTER] # list ids; FILTER is positional (see Traps)
pi-craft soundcraft exec describe <id> # params + "enabled" now / "disabled_reason"
pi-craft soundcraft exec run [--in S.scraft | --demo] --cmd ID[=JSON] [--cmd …] [--bounce OUT.wav] [--start SEC --end SEC] [--save S.scraft]
pi-craft soundcraft exec script FILE [--in S] [--save S] [--bounce OUT] # FILE: one `ID JSON` per line
pi-craft soundcraft exec info FILE.wav|S.scraft # file or session summary (track/clip listing)
pi-craft soundcraft exec run --in S.scraft --inspect # session JSON: selection, sources, tracks
pi-craft soundcraft exec convert IN OUT [--bit-depth 16|24|32f] [--rate HZ] [--normalize]
- Commands run in order and stop at the first failure (exit
1, no bounce written). - Each command prints
id: {json}on stdout;--bounceprints one JSON line last:{"lufs":…,"peak_db":…,"true_peak_db":…,"seconds":…,"path":…}— read it, then confirm withpi-craft verify. - Params after
=are one JSON object (--cmd 'clip.gain={"db":-6}'); a bare id has no params (--cmd edit.select_all). - Positions (
at,length,start,endinside commands) are samples (48000 = 1 s at 48 kHz);--start/--endofrunare seconds. Relative file paths are accepted.
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.
- yesterday First seen · 132 lines · 91 tokens per session scan A 24097e2f4424
soundcraft is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (319 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 2,254 once invoked, about $0.0004 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 2026-10-15.
Other skills, from other repositories
goga-cookbook
Principles for applying DSL specification in cell and CODEMANIFEST design.
goga-plan-by-design
Compile a design document into a ralphex execution plan.
goga-review-plan
Verify execution plan completeness and correctness.
goga-define-challenge
Challenge the complete product definition before the PRD is generated.
goga-define-project
Understand the current project before defining a product change that must fit into an existing product.
goga-define-requirements
Define the product requirements that describe what the product must do to deliver the established user experience and achieve the agreed product goals.