Atomic Agent is a local-first AI agent that runs its control loop and state on a user's machine while using local or cloud models. It drives browsers, edits files, runs approved commands, remembers context, schedules follow-ups, and connects to external tools, with the catalogue providing skills for its use.
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 agentmods add skills/atomicbot-ai/atomic-agent/audio-transcribenpx skills add AtomicBot-ai/atomic-agent --skill audio-transcribegit clone --depth 1 https://github.com/AtomicBot-ai/atomic-agentWrote 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/atomicbot-ai/atomic-agent/audio-transcribe)<a href="https://agentmods.dev/skills/atomicbot-ai/atomic-agent/audio-transcribe"><img src="https://agentmods.dev/badge/skills/atomicbot-ai/atomic-agent/audio-transcribe.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.00803 |
| Opus 5 | $0.00029 | $0.00402 |
| Sonnet 5 | $0.00012 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
audio-transcribe 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 5d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
audio-transcribe
Turn spoken audio into text locally with whisper.
Whisper writes a plain-text transcript next to the audio; you then read that file
and answer from its content. The chat model never "hears" the audio — whisper
does the listening as a separate process, so this works regardless of model size.
Setup health check (run first, every session)
Verify with one solo step:
[{ "tool": "os.shell.run", "args": { "cmd": "whisper", "args": ["--help"] } }]
Outcome map:
exit 0+ usage text → ready, proceed.command not found: whisper→ enter Setup playbook → "whisper missing".
Setup playbook (when prerequisites are missing)
whisper missing
Reply (solo reply step):
"
whisperis not installed. I can install it:brew install openai-whisper(also needsffmpeg). Install it?"
On yes:
[{ "tool": "os.shell.run", "args": { "cmd": "brew", "args": ["install", "openai-whisper", "ffmpeg"] } }]
On Linux: pipx install openai-whisper (or pip install openai-whisper) plus
apt-get install ffmpeg. The first transcription downloads the model weights to
~/.cache/whisper.
When to use
- The task references an audio attachment (
.mp3,.m4a,.wav,.ogg,.flac,.webm) and the answer depends on what is said in it. - "What does the speaker say…", "list the ingredients mentioned…", "which page numbers are read aloud…".
When NOT to use
- The audio only needs format conversion / trimming — that's the
ffmpegskill. - The attachment is an image / document — use vision or
fs.read_document.
How to transcribe
- Transcribe to a
.txtnext to the audio (one solo step). Pick the model by need:smallis a good speed/accuracy default; usemediumwhen accuracy matters and the clip is short.
[{ "tool": "os.shell.run", "args": { "cmd": "whisper", "args": ["audio.mp3", "--model", "small", "--output_format", "txt", "--output_dir", ".", "--language", "en"] } }]
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.
- 5d ago First seen · 88 lines · 58 tokens per session scan A 50e79475a9d6
audio-transcribe is a skill published in the GitHub repository AtomicBot-ai/atomic-agent (2,491 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 803 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 2026-08-30.
Other skills, from other repositories
lilbee-mcp
Search and manage the user's local lilbee knowledge base over MCP. Use whenever the user has indexed code, docs, PDFs, or web pages into lilbee and you need cited answers, or whenever they ask you to ingest content, swap models, or tune retrieval against their library. Every fact returned cites file and line.…
lilbee-mcp-wiki
Wiki layer for lilbee. Use only when the user explicitly asks about wiki / concept / entity / synthesis pages, or when lilbeestatus shows a built wiki. Requires the lilbee-mcp skill to be active for the underlying MCP connection.
tiktok-video
一句话需求 → 成品竖屏短视频:写分镜、自动搜免费素材、TTS 配音、逐字卡拉OK字幕、BGM、ffmpeg 合成 1080x1920 MP4(零 API key 可用).
harness-init-runner
Initialize a lightweight repo-local Node.js harness (harness/ + .harness/) WITHOUT AIOS dependency. Use ONLY when you need a standalone, portable harness. If AIOS is installed, use aios-long-running-harness instead — it has rex Command hosting, ContextDB integration, and checkpoint recovery.
run-inferbench-backend
Build, launch, smoke-test and drive the InferBench FastAPI backend (:7777) and its inference-engine orchestration. Use when asked to run, start, launch, boot, smoke-test, benchmark, or drive the inferbench backend / API / engines (llama.cpp, ollama, vLLM, SGLang, TGI), or to verify an engine actually starts and runs a…
manage-llm-server
Inspect and control the local LLM server(s) via llama-launcher — list profiles, see what's running, switch models, tail logs. Use when the user wants to know what model is loaded, change models, start/stop or restart the server, or troubleshoot a stuck load.