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 music-edit-to-lengthgit 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/music-edit-to-length)<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/music-edit-to-length"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/music-edit-to-length/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/music-edit-to-length"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/music-edit-to-length.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 | $0.00084 | $0.01328 |
| Opus 5.5 | $0.00034 | $0.00531 |
| Sonnet 5.5 | $0.00017 | $0.00266 |
| Haiku 4.5 | $0.00008 | $0.00133 |
Grade A, and why
music-edit-to-length scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 19d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
music-edit-to-length
Input: a music-map/1 from music-analysis (run it first). Output: <out>.wav,
<out>_edit.json and, with --preview, <out>.m4a for listening. The edit file
feeds beat-sync-video and the picture edit.
Scripts run in the quick-tier venv (.venv-music, see music-analysis step 0);
PKG=<this skill dir>/../../...
Procedure
- Analyse —
music-analysis→track_map.json. Read the sections, classes and drop candidates; confirm the drop by ear. - Identify blocks — mark the sections and genre/energy blocks (e.g. tech-house groove bars 1–32, trance breakdown/build 33–65, groove again 66–105). Joins may only connect material from the same block family.
- Score joins —
A join plays through the end of bar A and continues at bar B. Per factor: chroma and timbre similarity of the outgoing bars A−1..A against B's run-up in the source (B−2..B−1 — a match means the music arrives where B expects it), level jump,.venv-music/bin/python "$PKG/.pi/skills/music-edit-to-length/scripts/score_joins.py" track_map.json \ --candidates auto --target-duration 90 --anchor-bar 66 .venv-music/bin/python "$PKG/.pi/skills/music-edit-to-length/scripts/score_joins.py" track_map.json --from-bar 12 --to-bar 17section_boundary,class_change.score = 0.4·chroma + 0.4·timbre − 0.02·|jump dB| − 0.5·[groove/drop ↔ breakdown/build] + 0.1·[section boundary]. Prefer ≥ 0.75 with no class change. The score is advisory: automatic classes cannot always tell a genre boundary (a trance build and a tech-house groove both have drums and bass) — your block marking in step 2 decides. - Render —
The map defaults to.venv-music/bin/python "$PKG/.pi/skills/music-edit-to-length/scripts/edit_music.py" track.wav music/track_edit90 \ 1:13 17:25 25:33 66:82 102:197.0 --preview<audio stem>_map.jsonnext to the audio; pass--map music/track_map.jsonwhen it lives elsewhere (e.g. afteranalyze_music.py --out-dir). Segments are 1-basedstart_bar:endwhereendis an exclusive bar,END, or seconds with a decimal point. Joins are 30 ms equal-power crossfades. - Click check — every join reports
click_ok; the script warns on stderr when a join's sample step exceeds 1.1× the source at the same bar. Pick another join or keep the crossfade (--no-xfadeis diagnostic only). - Preview — the
.m4ais written next to the wav. - Listen before lock — ask the user to listen to the
.m4abefore the picture edit is locked todownbeats_video. Do not sync video to an unapproved edit. - Iterate — keep every rejected version with a
_vNsuffix (track_edit90_v1.wav+_v1_edit.json) and write a one-line note of the rejection reason next to it (README/AGENTS row), e.g. "v2 rejected: jumps from tech-house groove into the trance build at 0:31".
What ships with it
2 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.
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.
- 19d ago First seen · 84 lines · 84 tokens per session scan A fc162f8babd3
music-edit-to-length is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (319 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 1,328 once invoked, about $0.0003 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 2026-09-27.
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.