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-timed-transcriptgit 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-timed-transcript)<a href="https://agentmods.dev/skills/elumenotion/guideants/audiocpp-timed-transcript"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/audiocpp-timed-transcript.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00069 | $0.00952 |
| Opus 5 | $0.00034 | $0.00476 |
| Sonnet 5 | $0.00014 | $0.00190 |
| Haiku 4.5 | $0.00007 | $0.00095 |
Grade A, and why
audiocpp-timed-transcript 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 4d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
audio.cpp time-coded transcripts (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-timed-transcript/scripts/ relative to it. Write deliverables with
bare filenames (e.g. -o meeting); never prefix with Output/.
Product ASR returns text only. Word timings come from AudioCPP’s
qwen3_forced_aligner over the GPU host raw gateway (/private/v1/tasks/run), then
words are grouped into SRT / WebVTT / segment JSON (industry caption formats).
Authority: upstream audio.cpp
model_specs/qwen3_forced_aligner.json, docs/models/qwen3.md,
app/server/runtime.cpp (/v1/audio/transcriptions is text-only;
timed fields are on /v1/tasks/run).
Environment (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>
ASR must already be loaded on the GPU host (Settings / API lifecycle).
Phase 0 gate (once per GPU host image)
python3 Skills/audiocpp-timed-transcript/scripts/fetch_model.py \
audio-cpp/audio.cpp-gguf \
--dest /models-local/skill/asr/Qwen3-ForcedAligner-0.6B-GGUF \
--include Qwen3-ForcedAligner-0.6B-GGUF/qwen3-forced-aligner-0.6b-q8_0.gguf \
--strip-prefix Qwen3-ForcedAligner-0.6B-GGUF/
# ROCm host builds need --backend rocm (not cuda)
python3 Skills/audiocpp-timed-transcript/scripts/spawn_engine.py start \
--path /models-local/skill/asr/Qwen3-ForcedAligner-0.6B-GGUF \
--family qwen3_forced_aligner --task align --backend rocm
python3 Skills/audiocpp-timed-transcript/scripts/spawn_engine.py status
If status is not ready (e.g. missing model spec), update the GPU host guideants-ai
audiocpp image. Do not add a PyTorch aligner.
Transcribe
python3 Skills/audiocpp-timed-transcript/scripts/timed_transcribe.py \
uploads/clip.wav -o clip --language English
What ships with it
8 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.
- scripts/fetch_model.py 7.0 KB runs code
- scripts/merge_diarized.py 7.2 KB runs code
- scripts/preflight.py 16 KB runs code
- scripts/skill_gateway_client.py 6.8 KB runs code
- scripts/spawn_engine.py 14 KB runs code
- scripts/test_merge_diarized.py 2.2 KB runs code
- scripts/test_timed_transcribe.py 3.5 KB runs code
- scripts/timed_transcribe.py 16 KB runs code
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.
- 4d ago First seen · 86 lines · 69 tokens per session scan A 90f4373f66ba
audiocpp-timed-transcript is a skill published in the GitHub repository Elumenotion/GuideAnts (57 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 952 once invoked, about $0.0003 per session on Opus 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 2026-09-03.
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.
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.
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.
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.