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 speaker-idgit 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/speaker-id)<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/speaker-id"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/speaker-id/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/speaker-id"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/speaker-id.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 | $0.00080 | $0.01854 |
| Opus 5.5 | $0.00032 | $0.00742 |
| Sonnet 5.5 | $0.00016 | $0.00371 |
| Haiku 4.5 | $0.00008 | $0.00185 |
Grade A, and why
speaker-id 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.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Speaker ID enrollment
Give diarized transcripts real names, and repair the drift that clustering diarizers produce on long recordings. Post-hoc relabeling — it does not create diarization, it relabels an existing one.
pi-voiceid analyze --srt talk.srt # drift report, no enrollment needed
pi-voiceid enroll --name "Alice" --srt talk.srt --label "Speaker 1"
pi-voiceid label --srt talk.srt --dry-run # always dry-run first
pi-voiceid label --srt talk.srt # writes talk.named.srt
The source SRT is never overwritten. Everything runs locally on CPU via
sherpa-onnx; no audio or embedding leaves the machine.
How it works
- Each anonymous cluster is profiled with a speaker-embedding model, sampling segments across the whole timeline (drift is temporal).
- Cluster centroids are centered (a multi-speaker mean subtracted) and compared by cosine to the enrolled voiceprints.
- A cluster is named only when the absolute threshold, the margin over the runner-up, and a minimum share of agreeing segments all pass. Otherwise the anonymous label is kept — never guessed.
- Several clusters may map to one name: that is the drift repair.
Setup (one time)
The embedding model is not vendored. On first enroll/label it is fetched
into ~/.pi/models/speaker/ (28 MB). Model choice is the single biggest
accuracy factor — see BENCHMARK.md. Do not "upgrade" to a
bigger model without re-running the benchmark: the 114 MB VoxCeleb leader
scored worse than the 28 MB default on real meeting audio.
The native binding sherpa-onnx-node is an optional dependency. When it is
absent, transcription still works and pi-voiceid fails with an actionable
message naming the dependency and the install command.
Voiceprint library
Default store: ~/.pi/voiceprints/voiceprints.json. Override with --store or
the PI_VOICEPRINT_STORE env var. This is biometric-derived data about
identifiable people: it lives outside the repo by default, it is overridable,
and it must never be committed. If you point --store inside a repository, add
it to that repo's .gitignore.
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.
- 1mo ago First seen · 166 lines · 80 tokens per session scan A d76b9950a3c0
speaker-id is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (319 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 1,854 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 2026-09-12.
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.