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 Elumenotion/GuideAnts --skill audiocpp-asrgit clone --depth 1 https://github.com/Elumenotion/GuideAntsWrote 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/elumenotion/guideants/audiocpp-asr)<a href="https://agentmods.dev/skills/elumenotion/guideants/audiocpp-asr"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/audiocpp-asr/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/elumenotion/guideants/audiocpp-asr"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/audiocpp-asr.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 | $0.00064 | $0.00586 |
| Opus 5 | $0.00032 | $0.00293 |
| Sonnet 5 | $0.00013 | $0.00117 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
audiocpp-asr-extended 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 6d 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.
This is a copy
100% identical to audiocpp-asr-extended — 72 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
audio.cpp extended ASR (experimental)
Paths — fixed layout, do not probe or re-derive. The sandbox CWD is the
notebook's output directory. This skill's scripts live under
Skills/audiocpp-asr/scripts/ relative to it. Write deliverables with
bare filenames; never prefix with Output/.
Product ASR is multipart upload with no language control. This skill stages the
file (/files) then calls raw /asr/v1/audio/transcriptions on the GPU host.
Environment (required for PC → the GPU host)
AUDIOCPP_SKILL_BASE_URL=http://<gpu-host-lan-ip>:8112/audiocpp-skill
AUDIOCPP_SKILL_TOKEN=<same as the GPU host GA_AUDIOCPP_SKILL_TOKEN>
An ASR model must already be loaded on the GPU host (GuideAnts Settings → Local models / API lifecycle).
Preflight
python3 Skills/audiocpp-asr-extended/scripts/preflight.py --for asr-extended
Trust its verdict. With the gateway env set, it checks GPU host ASR via the gateway (not sandbox loopback).
Transcribe
python3 Skills/audiocpp-asr-extended/scripts/engine_tool.py transcribe \
uploads/clip.wav [--language de]
The script stages the file on the GPU host and returns JSON text. Engine model id is
always qwen3-asr. Prefer WAV; other formats may need ffmpeg conversion first.
Sideload (advanced)
Fetching a non-catalog qwen3-family snapshot downloads onto the GPU host under
/models-local/skill/asr/…. Loading it into the product ASR wrapper still
requires GPU host-side /asr/admin/load (and replaces the user’s loaded model) —
ask before doing that; prefer Settings / API lifecycle for durable loads.
python3 Skills/audiocpp-asr-extended/scripts/fetch_model.py <hf-repo-id> \
--dest /models-local/asr/<DirName>
Related
Speaker-labeled transcripts: audiocpp-diarize.
Reporting
End by telling the user what worked and what was blocked, quoting preflight evidence.
What ships with it
4 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.
- 6d ago Changed · -10 lines · -24 tokens per session 7b01056dcbdd
- 10d ago First seen · 79 lines · 88 tokens per session scan A 948263528783
audiocpp-asr-extended is a skill published in the GitHub repository Elumenotion/GuideAnts (57 stars, last pushed yesterday), licensed Apache-2.0. It adds 64 tokens to every session and 586 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to audiocpp-asr-extended, differing in 72 lines, and is treated as a copy.
Other skills, from other repositories
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
foundation-models
On-device LLM integration using Apple's Foundation Models framework. Use when implementing AI text generation, structured output, or tool calling.
analytics-interpretation
Interpret app metrics and make data-driven decisions. Covers DAU/MAU, retention, LTV, ARPU, App Store Connect analytics, AARRR funnel analysis, cohort analysis, and diagnostic decision trees. Use when user wants to understand their metrics, diagnose problems, or build a data-driven growth plan.
app-namer
Turn an app idea into validated, App-Store-ready name candidates. Use when the user says "name my app", "what should I call it", "app name ideas", "help me name this app", "is this name available", or needs to pick a brandable, ownable name before reserving it in App Store Connect.
in-app-events
Generates In-App Event metadata templates for App Store Connect — event names, descriptions, badge types, image specs, and deep link configuration. Use when creating events for App Store visibility, engagement campaigns, or seasonal promotions.
test-generator
Generate test templates for unit tests, integration tests, and UI tests using Swift Testing and XCTest. Use when adding tests to iOS/macOS apps.