Borrowing it
Nothing to install: this file belongs to theantichris/granola. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/theantichris/granola/main/CLAUDE.mdgit clone --depth 1 https://github.com/theantichris/granolaWrote 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/theantichris/granola/claude-md)<a href="https://agentmods.dev/instructions/theantichris/granola/claude-md"><img src="https://agentmods.dev/badge/instructions/theantichris/granola/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 5.1 | $0.02247 | $0.02247 |
| Opus 5 | $0.01123 | $0.01123 |
| Sonnet 5 | $0.00449 | $0.00449 |
| Haiku 4.5 | $0.00225 | $0.00225 |
Grade C, and why
granola CLAUDE.md scanned grade C 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 7d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
2. Extract access token from WorkOS tokens in supabase.json How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Granola CLI is a command-line tool for exporting notes and transcripts from the Granola note-taking application. It provides two distinct export capabilities:
- Notes Export: Connects to the Granola API, authenticates using bearer tokens, fetches AI-generated notes in JSON format, and converts them to clean Markdown files
- Transcripts Export: Reads the local Granola cache file, extracts raw meeting transcripts with timestamps and speaker identification, and exports them to plain text files
Common Commands
Build
go build
Run
# Export notes (AI-generated from API)
go run main.go notes
# Or after building:
./granola notes
# Export transcripts (raw from cache file)
go run main.go transcripts
# Or after building:
./granola transcripts
Test
go test ./...
go test -v ./... # verbose output
Module Management
go mod tidy # clean up dependencies
go mod download # download dependencies
Releases
# Create a new release (automated via GitHub Actions)
git tag v0.1.0
git push origin v0.1.0
# Test release locally (requires GoReleaser)
goreleaser release --snapshot --clean
# Check GoReleaser configuration
goreleaser check
Linting
# Markdown linting (runs in GitHub Actions, installed via brew)
markdownlint-cli2 "**/*.md" "#notes" "#transcripts"
# Go linting (if golangci-lint is installed)
golangci-lint run
Architecture
The project follows a modular Go CLI application structure:
- Entry Point:
main.go- Uses Charmbracelet's fang for execution context - Command Structure:
cmd/directory contains Cobra command definitionscmd/root.go- Defines the root command with configuration initialization using constructor patterncmd/notes.go- Implements the notes command for fetching and converting AI-generated notes from APIcmd/transcripts.go- Implements the transcripts command for reading and exporting raw transcripts from cache
- Internal Packages:
internal/api/- Granola API client with Supabase token authentication and document models (including ProseMirror structures)internal/cache/- Cache file reader for extracting transcript data from local Granola cacheinternal/converter/- Document to Markdown conversion with YAML frontmatterinternal/prosemirror/- ProseMirror JSON to Markdown conversion and plain text extractioninternal/transcript/- Transcript formatter for converting segments to readable text with timestampsinternal/writer/- File system writer for Markdown files with sanitization
- Configuration: Supports multiple configuration sources:
- Environment variables via
.envfile (using godotenv) - Config file (
.granola.tomlin home directory or current directory) - Command-line flags:
- Global:
--debug,--config - Notes command:
--supabase,--timeout,--output - Transcripts command:
--cache,--output
- Global:
- Environment variable mapping:
SUPABASE_FILE,DEBUG_MODE
- Environment variables via
- Logging: Uses Charmbracelet's log package for structured logging
- Debug mode can be enabled via
--debugflag or config - Logger includes timestamp and caller information
- Log levels: Debug, Info, Warn, Error (defaults to Warn, Debug with debug flag)
- Logger is created in Execute() and injected via dependency injection
- Logging Best Practices:
- Log errors only at the command level (cmd package) where they are handled
- Internal packages should return errors without logging to avoid duplicates
- Commands return errors to Cobra rather than logging them (Cobra handles display)
- Debug/Info logging can occur at any level for progress tracking
- Debug mode can be enabled via
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.
- 7d ago First seen · 227 lines · 2,247 tokens per session scan C 31f84c2ba7d2
granola CLAUDE.md is an instructions file published in the GitHub repository theantichris/granola (43 stars, last pushed 11mo ago), licensed MIT. It adds 2,247 tokens to every session, about $0.0112 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
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).
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.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.