What is augent CLAUDE.md?

Project instructions for Augent, an audio-focused MCP server that can download, transcribe, search, and analyze audio from web URLs. They also document a command-line downloader for extracting audio from video sites.

Use them to download audio from supported video URLs, save it to a chosen folder, process several URLs, transcribe files, or search audio for keywords. The documented downloader handles YouTube, Vimeo, SoundCloud, Twitter, TikTok, and many other sites.

They explain the intended audio workflow and the downloader's limits, so an agent knows which commands and project behavior to preserve.

How AugentDevs/augent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to AugentDevs/augent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/AugentDevs/augent/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/AugentDevs/augent

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/augentdevs/augent/claude-md/github.svg)](https://agentmods.dev/instructions/augentdevs/augent/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/augentdevs/augent/claude-md"><img src="https://agentmods.dev/badge/instructions/augentdevs/augent/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/augentdevs/augent/claude-md"><img src="https://agentmods.dev/badge/instructions/augentdevs/augent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 6,656 This file is loaded in full into every session.

When invoked 6,656 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.06656	$0.06656
Opus 5.5	$0.02662	$0.02662
Sonnet 5.5	$0.01331	$0.01331
Haiku 4.5	$0.00666	$0.00666

Measured 2mo ago against content hash c0d27b4c7dfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

augent CLAUDE.md 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 2mo 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.

CLAUDE.md · 547 lines

How it starts

The opening of the file, as written. The whole thing — 547 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Augent — Audio + Agents

Augent is an MCP server (Model Context Protocol) that gives agents audio intelligence. Download, transcribe, search, and analyze audio from any URL. Built for Claude Code. Compatible with any MCP client.

audio-downloader (Built by Augent)

A speed-optimized audio downloader for downloading audio ONLY from any video URL at lightning speed.

# Download audio from YouTube (or any video URL)
audio-downloader "https://youtube.com/watch?v=xxx"

# Download to custom folder
audio-downloader -o ~/Music "https://youtube.com/watch?v=xxx"

# Download multiple URLs
audio-downloader url1 url2 url3

Speed Optimizations:

aria2c multi-connection downloads (16 parallel connections)
Concurrent fragment downloading (4 fragments)
No video download - audio extraction only
No format conversion - native audio format

Supports: YouTube, Vimeo, SoundCloud, Twitter, TikTok, and 1000+ sites

Workflow: Download → Transcribe → Search

audio-downloader "https://youtube.com/watch?v=tutorial"
augent transcribe ~/Downloads/tutorial.webm
augent search ~/Downloads/tutorial.webm "keyword1,keyword2"

Note-Taking (Primary Workflow)

IMPORTANT: When a user gives you ANY URL and asks what was said, what happened, what's in it, or anything about the content — ALWAYS use the augent pipeline (download_audio + transcribe_audio, or take_notes for notes). This includes tweets, YouTube links, podcast URLs, TikTok, Twitter/X posts, and any link that might contain audio or video. Do NOT use WebFetch for media URLs. Do NOT say "augent can't do that" for social media links. If the URL might have audio or video, download it first and find out.

For note-taking specifically (notes, quiz, summary, highlights) — use the take_notes MCP tool. It downloads, transcribes, and saves .md to Desktop in one call.

When a user asks to "take notes" or "create a quiz" from a URL, use the take_notes tool. One tool call does everything:

User says: "Take notes from https://youtube.com/watch?v=xxx"
You call: take_notes with the URL
Tool does: Downloads audio → Transcribes → Saves .md to Desktop → Returns audio_path and write_to
You MUST then: Read the instruction field from the response and follow it exactly — format the notes and save them by calling take_notes(save_content="<your formatted notes>"). Do NOT use the Write tool for saving notes.
For chapters/search: Use audio_path from step 3. Do NOT call download_audio — the audio is already downloaded.

Read the full file on GitHub · 547 lines

Changes

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.

2mo ago First seen · 547 lines · 6,656 tokens per session scan A c0d27b4c7dfb

Subscribe to this mod's changes

augent CLAUDE.md is an instructions file published in the GitHub repository AugentDevs/augent (6 stars, last pushed 3d ago), licensed MIT. It adds 6,656 tokens to every session, about $0.0266 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 2026-08-31.

agents ai audio mcp speech-to-text transcription

augent CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
augent CLAUDE.mdAugentDevs/augent	Instructions file	6	3d ago	MIT	A	6,656	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	279k	yesterday	MIT	A	4,325	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

augent: Instructions file for Claude Code