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 instructions/silverstein/minutes/claude-mdgit clone --depth 1 https://github.com/silverstein/minutesWrote 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/instructions/silverstein/minutes/claude-md)<a href="https://agentmods.dev/instructions/silverstein/minutes/claude-md"><img src="https://agentmods.dev/badge/instructions/silverstein/minutes/claude-md.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 | $0.06720 | $0.06720 |
| Opus 5 | $0.03360 | $0.03360 |
| Sonnet 5 | $0.01344 | $0.01344 |
| Haiku 4.5 | $0.00672 | $0.00672 |
Grade A, and why
minutes CLAUDE.md scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **ureq** for HTTP — pure Rust, no secrets in process args (replaced curl) How it starts
The opening of the file, as written. The whole thing — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Minutes
Your AI remembers the conversations you authorize.
Project Overview
Minutes — open-source, privacy-first conversation memory layer for AI assistants. Captures meetings, voice memos, and brain dumps, transcribes locally with whisper.cpp, diarizes speakers, and outputs searchable markdown with structured action items and decisions. Built with Rust + Tauri v2 + Node.js (MCP).
Four input modes, one pipeline:
- Live recording:
minutes record/minutes stop— for meetings, calls, conversations - Live transcript:
minutes live/minutes stop— real-time transcription with delta reads for AI coaching mid-meeting - Notetaking:
minutes note "important point"— timestamped annotations during recording - Folder watcher:
minutes watch— auto-processes voice memos from iPhone/iCloud
Quick Start
cd ~/Sites/minutes
cargo build # Build Rust workspace
cargo test -p minutes-core --no-default-features # Fast tests (no whisper model)
cargo run --bin minutes -- setup --model tiny # Download whisper model
cargo run --bin minutes -- setup --diarization # Download speaker diarization models (~34MB)
cargo run --bin minutes -- record # Start recording
cargo run --bin minutes -- stop # Stop and process
Full Build (CLI + Tauri App)
./scripts/build.sh # Builds everything and installs CLI
./scripts/build.sh --install # Same + copies .app to /Applications
./scripts/install-dev-app.sh # Canonical signed dev app install to ~/Applications/Minutes Dev.app
# Or manually:
export CXXFLAGS="-I$(xcrun --show-sdk-path)/usr/include/c++/v1"
cargo build --release -p minutes-cli # CLI binary
cargo tauri build --bundles app # Tauri .app bundle
rm -f ~/.local/bin/minutes && cp target/release/minutes ~/.local/bin/minutes # Install CLI (rm first: in-place cp over a running binary invalidates its signature -> SIGKILL on every launch)
open target/release/bundle/macos/Minutes.app # Launch app
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 · 376 lines · 6,720 tokens per session scan A 8decad26be3f
minutes CLAUDE.md is an instructions file published in the GitHub repository silverstein/minutes (1,464 stars, last pushed today), licensed MIT. It adds 6,720 tokens to every session, about $0.0336 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vexa AGENTS.md
AGENTS.md instructions for Vexa-ai/vexa, covering agents.md — the agent front door (in-repo), researching vexa? start here, driving vexa from an agent session, your issue is your prd and claiming — and say hello on discord.
stenoai CLAUDE.md
Claude Code instructions for stenolabs/stenoai, covering claude.md, architecture, development commands, backend (python) and desktop app (electron).
vexa CLAUDE.md
Claude Code instructions for Vexa-ai/vexa, a project described as: Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.
stenoai AGENTS.md
AGENTS.md instructions for stenolabs/stenoai, covering agents.md, code review rules, bundled binaries with an api, bare exit() in python and platform parity.
os-clovy AGENTS.md
AGENTS.md instructions for open-software-network/os-clovy, covering clovy — agent instructions, project, os platform (shared brain), structure and domain & decisions — read before writing code.
Logue CLAUDE.md
Instructions for bitwize-ai/Logue, covering logue — development guidelines, project overview, running the build you just made, where documentation goes and dependencies.