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-asr-extendedgit 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-extended)<a href="https://agentmods.dev/skills/elumenotion/guideants/audiocpp-asr-extended"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/audiocpp-asr-extended/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-extended"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/audiocpp-asr-extended.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 54 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00088 | $0.00820 |
| Opus 5 | $0.00044 | $0.00410 |
| Sonnet 5 | $0.00018 | $0.00164 |
| Haiku 4.5 | $0.00009 | $0.00082 |
Grade A, and why
audiocpp-asr-extended scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST http://127.0.0.1:8082/admin/load \ Copies of this mod
1 near-identical copy found in the catalogue:
- audiocpp-asr-extended — 100% identical, 72 lines differ
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
audio.cpp extended ASR (experimental)
The GuideAnts ASR wrapper (127.0.0.1:8082) takes multipart uploads with no
language control. The raw engine it spawns (127.0.0.1:18082) accepts a
server-local path and a language hint — and the sandbox shares its
filesystem, so any workspace file qualifies. The wrapper also loads bare model
directories the catalog doesn't list (unlike the strictly-gated TTS wrapper).
Preflight
python3 Skills/audiocpp-asr-extended/scripts/preflight.py --for asr-extended
Trust its verdict over this document. open: false means no ASR model is
loaded — ask the user to load one via GuideAnts Settings → Local models.
Warnings tell you whether the sideload path (below) is available.
Transcribing by path (with language hint)
python3 Skills/audiocpp-asr-extended/scripts/engine_tool.py transcribe \
clip.wav [--language de]
- No upload and no gateway size cap — the engine reads the file in place.
- The engine model id is always
qwen3-asr(fixed by the wrapper), whatever snapshot is actually loaded. - Input should be WAV for the raw engine; for other formats, either convert
with ffmpeg first or use the wrapper upload (
POST :8082/transcribe, multipart fieldaudio), which re-encodes to 16 kHz mono itself.
Sideloading a non-catalog ASR snapshot
The ASR wrapper's /admin/load accepts any bare directory under
/models-local/asr whose leaf name matches the model_id. The engine family
defaults to qwen3_asr, so only qwen3_asr-family snapshots work (other
families would need the GA_ASR_ENGINE_FAMILY env at service start — a compose
change, out of skill scope).
python3 Skills/audiocpp-asr-extended/scripts/fetch_model.py <hf-repo-id> \
--dest /models-local/asr/<DirName>
curl -s -X POST http://127.0.0.1:8082/admin/load \
-H "Content-Type: application/json" -d '{"model_id": "<DirName>"}'
Warning — this replaces the user's loaded ASR model. Ask before doing it, and offer to restore afterwards:
What ships with it
3 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.
- 7d ago Changed 9e437eb44e06
- 11d 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 88 tokens to every session and 820 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
idea-generator
Brainstorm and rank iOS/macOS app ideas tailored to developer skills. Use when user says "what should I build", "give me app ideas", "I don't know what to build", "brainstorm app ideas", or "help me find an app idea".
milestone-celebration
Generates achievement celebration UI with confetti animations, badge unlocks, progress milestones, haptic feedback, and optional share-to-social. Use when user wants to celebrate achievements, show confetti, display milestone badges, or trigger rewards on key thresholds.
share-card
Generates shareable card images from app content (achievements, stats, quotes) for social media sharing. Use when user wants to create share images, social cards, shareable content cards, or export app content as images with ShareLink integration.
social-export
Generates infrastructure for exporting app content to social platforms (Instagram Stories, TikTok, Twitter/X) with platform-specific formatting, aspect ratios, and metadata. Use when user wants social media export, share to stories, or platform-specific sharing pipelines.
watermark-engine
Generates a watermark overlay system for images and video with configurable positioning, opacity, tiling, and paywall integration for automatic removal on subscription or purchase. Use when user wants to add branding, attribution, or free-tier watermarks to visual content.
game-feel
Game feel ("juice") for Apple apps — celebration choreography, haptic vocabulary design, sound-effect layers, and the event×channel feedback audit. Use when big moments fall flat, when designing haptics or SFX, or when auditing whether every meaningful event actually reaches the user.