PlaudBlender copilot-instructions.md

PlaudBlender copilot-instructions.md is an instructions file for GitHub Copilot from Gunnarguy/PlaudBlender. It costs 1,653 tokens per session, scanned A, original, MIT.

Project instructions for PlaudBlender, an application that turns Plaud voice recordings into a searchable timeline of cleaned transcripts, events, and connections. They describe the Dash web interface, project structure, data pipeline, tests, and integrations.

In plain words
What is it for?
Use them when developing or testing the PlaudBlender interface, recording pipeline, knowledge graph, MCP server, or automatic syncing.
Why use it?
They give an AI coding assistant the background needed to find the right files, run the application, process recordings, and check changes.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is main.py → Run with: python scripts/launch_app.py (+ 9 Flask routes).

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: GitHub Copilot.

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.

agentmods badge for PlaudBlender copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gunnarguy/plaudblender/copilot-instructions.svg)](https://agentmods.dev/instructions/gunnarguy/plaudblender/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/gunnarguy/plaudblender/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/gunnarguy/plaudblender/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,653 This file is loaded in full into every session.
When invoked 1,653 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01653 $0.01653
Opus 5 $0.00826 $0.00826
Sonnet 5 $0.00331 $0.00331
Haiku 4.5 $0.00165 $0.00165

Measured 6d ago against content hash 06fdac366ba2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

PlaudBlender copilot-instructions.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 6d 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.

.github/copilot-instructions.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PlaudBlender — AI Agent Instructions

This file is auto-loaded into every Copilot conversation. It tells you how to navigate and work in this project.

Quick Orientation

What Where
Full docs docs/PROJECT_GUIDE.md — architecture, structure, and roadmap
MVP spec docs/chronos-mvp.md — complete Chronos system architecture
Entry point python scripts/launch_app.py — Dash v2 UI on port 8050
Pipeline python scripts/chronos_pipeline.py --full — ingest → process → index → graph
Tests python -m pytest tests/ — 124 tests, run before committing

What This Project Does

Chronos transforms Plaud voice recordings into a searchable knowledge timeline:

  • Fetches transcripts from Plaud API (OAuth) and stores locally
  • Processes through Gemini AI for cognitive cleaning (removes filler, extracts events)
  • Indexes to Qdrant with temporal metadata (day-of-week, hour, category)
  • Provides Dash UI with interactive Knowledge Graph (Cytoscape)
  • Full Plaud integration: devices, workflows, webhooks
  • MCP server for OpenAI/ChatGPT tool access to your knowledge timeline
  • Auto-sync via webhooks and USB watcher for real-time ingestion

UI Layout (Dash v2 — app_v2/)

View Purpose
Timeline Date-grouped event timeline, click recording → detail panel
Topics Events grouped by category (work, meeting, personal, etc.)
Search Semantic search with category/date filters + AI answers (GPT-5.4)
Graph Interactive Cytoscape knowledge graph, 6 layouts, node click details
Stats 8 stat cards, sentiment chart, productivity insights, API cost tracking
Notion Notion uplink — OAuth, page filter, channel select, sync to Notion
Sync Pipeline dashboard: status counts, Full Sync, Reset Stuck
Settings Connectivity checks for Plaud, Gemini, Qdrant, model pricing in dropdowns

Read the full file on GitHub · 114 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.

  1. 6d ago First seen · 114 lines · 1,653 tokens per session scan A 06fdac366ba2

Subscribe to this mod's changes

PlaudBlender copilot-instructions.md is an instructions file published in the GitHub repository Gunnarguy/PlaudBlender (5 stars, last pushed yesterday), licensed MIT. It adds 1,653 tokens to every session, about $0.0083 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 2026-08-31.

Related

Other instructions, from other repositories

remnic AGENTS.md

AGENTS.md instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.

joshuaswarren/remnic · 31,441 tokens

engraphis AGENTS.md

AGENTS.md instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, internal subagent delegation, 0. read this first — two architectures live in one package, 1. commands and ── unified dashboard + memory inspector ──.

Coding-Dev-Tools/engraphis · 4,947 tokens

engraphis CLAUDE.md

Claude Code instructions for Coding-Dev-Tools/engraphis, covering claude.md, the one rule that prevents most mistakes, before you say "done" — run the canonical gate, slash commands available here and working style in this repo.

Coding-Dev-Tools/engraphis · 1,082 tokens

neurostack CLAUDE.md

Instructions for raphasouthall/neurostack, covering neurostack - claude code guide, quick reference, installation, mcp server (recommended for claude code) and openai-compatible api.

raphasouthall/neurostack · 3,464 tokens

my-wiki AGENTS.md

Instructions for NimaChu/my-wiki, covering my wiki agent project, project map, knowledge model, route requests and development checks.

NimaChu/my-wiki · 617 tokens

llm-wiki-newsroom CLAUDE.md

Claude Code instructions for alfadur7/llm-wiki-newsroom, covering llm wiki newsroom, roles, universal cycle, the four loops and reground.

alfadur7/llm-wiki-newsroom · 4,744 tokens