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/shironex/omniscribe/claude-mdgit clone --depth 1 https://github.com/Shironex/omniscribeWrote 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/shironex/omniscribe/claude-md)<a href="https://agentmods.dev/instructions/shironex/omniscribe/claude-md"><img src="https://agentmods.dev/badge/instructions/shironex/omniscribe/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 | $0.01744 | $0.01744 |
| Opus 5 | $0.00872 | $0.00872 |
| Sonnet 5 | $0.00349 | $0.00349 |
| Haiku 4.5 | $0.00174 | $0.00174 |
Grade A, and why
omniscribe 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 5d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Backend:** Jest + `@nestjs/testing` TestingModule. Mock factories in `apps/desktop/test/mocks/` (MockPty, electron-store, child_process). How it starts
The opening of the file, as written. The whole thing — 139 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
Omniscribe is a desktop application for orchestrating multiple AI coding assistant sessions in parallel. It uses Electron with an embedded NestJS backend in the main process and a React frontend in the renderer.
Requirements
- Node.js >= 22
- pnpm 10.x
Commands
# Install dependencies
pnpm install
# Development (starts web + desktop concurrently)
pnpm dev
# Build all packages (shared must build first — all others depend on it)
pnpm build
# Build only shared package (required before desktop/web/mcp-server builds)
pnpm build:packages
# Lint / Format
pnpm lint
pnpm format # write
pnpm format:check # CI check (no write)
# Test / Type-check
pnpm test
pnpm typecheck
# Package desktop app for distribution
pnpm --filter @omniscribe/desktop package
# Platform-specific builds
pnpm package:win # Windows
pnpm package:mac # macOS
# Rebuild node-pty after electron update
pnpm --filter @omniscribe/desktop rebuild
Architecture
Monorepo Structure
apps/desktop/- Electron main process with NestJS backendapps/web/- React frontend (served by Vite, loaded by Electron renderer)apps/mcp-server/- MCP server for Claude Code status reportingpackages/shared/- Shared types and utilities
Backend (NestJS in Electron Main)
Located in apps/desktop/src/modules/:
- TerminalModule - PTY management via node-pty, handles spawn/input/resize/kill (global module)
- SessionModule - AI session lifecycle and state (Starting, Idle, Working, NeedsInput, Done, Error)
- GitModule - Git operations (branches, worktrees, commits) via CLI execution with domain services
- GithubModule - GitHub CLI operations (PRs, issues, repo info)
- McpModule - MCP server discovery, config generation, status polling
- WorkspaceModule - Project/tab management, persistence via electron-store
- QuickActionModule - Quick action management and execution
- UsageModule - Claude CLI usage data fetching
- HealthModule - Periodic health checks and zombie session detection
- SharedModule - CORS config, env-utils, throttler guard, NestJS logger adapter
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.
- 5d ago First seen · 139 lines · 1,744 tokens per session scan A 985c706874c7
omniscribe CLAUDE.md is an instructions file published in the GitHub repository Shironex/omniscribe (10 stars, last pushed 5d ago), licensed MIT. It adds 1,744 tokens to every session, about $0.0087 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode tree-widgets.instructions.md
Use when asked to consume workbench tree widgets in VS Code.
vscode accessibility.instructions.md
Use when implementing accessibility features, ARIA labels, screen reader support, accessible help dialogs, or keybinding scoping for accessibility. Covers AccessibleContentProvider, CONTEXTACCESSIBILITYMODEENABLED, verbosity settings, and announcement patterns.
vscode writing-tests.instructions.md
VS Code test writing guidelines — unit tests, integration tests, snapshot tests, and clean teardown patterns. Reference when writing or updating tests.
vscode interactive.instructions.md
Architecture documentation for VS Code interactive window component. Use when working in src/vs/workbench/contrib/interactive.
vscode notebook.instructions.md
Architecture documentation for VS Code notebook and interactive window components. Use when working in src/vs/workbench/contrib/notebook/.
vscode chat.instructions.md
Chat feature area coding guidelines.