What is plaud-mcp AGENTS.md?

An instruction file for Plaud MCP, a tool that copies processed Plaud recordings into dated Markdown notes with summaries, highlights, and speaker-labelled transcripts.

Use it to configure the tool, sync already-processed recordings, or deliberately request transcription for recordings that Plaud has not processed.

It explains the setup and safety rules for syncing recordings, including the difference between free incremental syncing and transcription that uses a limited quota.

How Namraks-Labs/plaud-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Namraks-Labs/plaud-mcp. 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/Namraks-Labs/plaud-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Namraks-Labs/plaud-mcp

Made for: Codex, OpenCode.

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/namraks-labs/plaud-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/namraks-labs/plaud-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/namraks-labs/plaud-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/namraks-labs/plaud-mcp/agents-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/namraks-labs/plaud-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/namraks-labs/plaud-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 953 This file is loaded in full into every session.

When invoked 953 The same file — it is already loaded in full.

Security scan B 1 finding. 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	$0.00953	$0.00953
Opus 5	$0.00477	$0.00477
Sonnet 5	$0.00191	$0.00191
Haiku 4.5	$0.00095	$0.00095

Measured 9d ago against content hash 1f5c94c85938, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

plaud-mcp AGENTS.md scanned grade B 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 9d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- `plaud-mcp auth` (saves to `$PLAUD_STATE_DIR/token`, chmod 600). Pipe on stdin to keep it out of shell history: `pbpaste | plaud-mcp auth`.

AGENTS.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Operating guide for autonomous agents (and the humans configuring them) working with plaud-mcp. Keep it conservative: the only side effect this tool has is writing markdown files into PLAUD_NOTES_DIR. It never deletes recordings, never modifies the Plaud cloud, and never posts anywhere.

What this tool does

Pulls Plaud recordings (summary + highlights + diarized transcript) into one markdown file each, under PLAUD_NOTES_DIR/YYYY-MM-DD/<slug>-<id6>.md. Sync is incremental (tracked in state.json) and idempotent (matched by plaud_file_id in frontmatter).

It can also trigger transcription/AI generation for recordings Plaud hasn't processed yet (plaud-mcp transcribe <id> / the plaud_transcribe tool). This is the one operation with a real cost: it consumes the user's Plaud transcription quota, same as pressing "Transcribe" in the app. Treat it as quota-spending and confirm intent before running it in bulk. sync, by contrast, only pulls already-processed recordings and is free.

Setup contract

Token (required, human-in-the-loop once). There are no API keys. A human must extract a JWT from a logged-in web.plaud.ai session (DevTools → Network → any api request → authorization: bearer eyJ…). Provide it to the tool one of two ways:
- PLAUD_TOKEN env var (preferred for agents/CI), or
- plaud-mcp auth (saves to $PLAUD_STATE_DIR/token, chmod 600). Pipe on stdin to keep it out of shell history: pbpaste | plaud-mcp auth. An agent should not fabricate or guess a token. If none is configured, plaud-mcp status reports token source: none — escalate to the human with the extraction steps above.
Region. Default API host is https://api.plaud.ai. EU accounts use https://api-euc1.plaud.ai. Set via PLAUD_API_DOMAIN or plaud-mcp api <url>.
Output dir. Set PLAUD_NOTES_DIR to where notes should land.

Run contract

Sync: plaud-mcp sync — exits 0 on success (including "0 new"), non-zero on auth/network/parse failure.
Inspect without writing: plaud-mcp sync --dry-run, plaud-mcp list, plaud-mcp get <file-id>.
Health: plaud-mcp status — reports token source, token expiry in days, api domain, dirs, last-sync time, seen-id count.

Read the full file on GitHub · 45 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.

9d ago First seen · 45 lines · 953 tokens per session scan B 1f5c94c85938

Subscribe to this mod's changes

plaud-mcp AGENTS.md is an instructions file published in the GitHub repository Namraks-Labs/plaud-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 953 tokens to every session, about $0.0048 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Documents LLM Writing and docs ai claude mcp model-context-protocol obsidian

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

plaud-mcp: Instructions file for Codex