Tarantul: Instructions file for Claude Code

CLAUDE.md

Tarantul CLAUDE.md is an instructions file for Claude Code from FarkhodovIslom/Tarantul. It costs 1,620 tokens per session, scanned A, original, MIT.

Repository instructions for Tarantul, a TypeScript personal AI assistant that runs on Bun. They describe its language-model providers, chat channels, scheduling, long-term memory, commands, and coding conventions.

In plain words
What is it for?
Use them when developing, testing, or operating Tarantul and its API, chat integrations, skills, scheduling, or memory system.
Why use it?
They tell an agent how the project is structured and which Bun commands to use for testing, type checking, linting, formatting, and starting the assistant. This helps changes fit its memory and multi-channel design.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is FarkhodovIslom/Tarantul's own configuration. It tells Claude Code how to work on Tarantul itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Tarantul configures →

Reuse

Borrowing it

Nothing to install: this file belongs to FarkhodovIslom/Tarantul. 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/FarkhodovIslom/Tarantul/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/FarkhodovIslom/Tarantul

Made for: Claude Code.

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 Tarantul CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/farkhodovislom/tarantul/claude-md.svg)](https://agentmods.dev/instructions/farkhodovislom/tarantul/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/farkhodovislom/tarantul/claude-md"><img src="https://agentmods.dev/badge/instructions/farkhodovislom/tarantul/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,620 This file is loaded in full into every session.
When invoked 1,620 The same file — it is already loaded in full.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01620 $0.01620
Opus 5 $0.00810 $0.00810
Sonnet 5 $0.00324 $0.00324
Haiku 4.5 $0.00162 $0.00162

Measured 6d ago against content hash a3807efd35e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Tarantul CLAUDE.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.

CLAUDE.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 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

tarantul is a lightweight personal AI assistant framework written in TypeScript on the Bun runtime. It supports 25+ LLM providers, a tool-execution agent loop, multi-channel chat (Telegram/Slack/Discord), cron scheduling, a skill system, and an OpenAI-compatible HTTP API. Its defining feature is a real long-term memory: per-session MEMORY.md + dated daily logs + atomic, [[wikilink]]-connected notes, indexed for hybrid keyword + semantic search and auto-consolidated into a knowledge graph the agent builds and traverses itself (src/agent/memory*.ts). It is Bun-native and zero-framework by design.

Commands

bun install                 # install deps
bun test                    # run all tests (coverage on by default via bunfig.toml)
bun test tests/api.test.ts  # run a single test file
bun test -t "name"          # run tests matching a name
bun run typecheck           # tsc --noEmit (strict)
bun run lint                # biome check src tests
bun run format              # biome format --write src tests

bun run start onboard       # create ~/.tarantul/config.yaml + workspace
bun run start agent         # interactive REPL
bun run start agent -m "…"  # one-shot; also accepts piped stdin
bun run start serve         # OpenAI-compatible API server (default :8080) + channels

There is no build step for normal use — Bun executes the TypeScript directly. tsconfig.json sets outDir: ./dist only for tsc output; runtime entry is src/cli/main.ts.

Conventions

  • Relative imports use a .js extension even though the files are .ts (required by moduleResolution: bundler + verbatimModuleSyntax). Match this — import { X } from "./foo.js", not "./foo".
  • The @/* path alias maps to src/* (tsconfig paths).
  • Strict TypeScript with exactOptionalPropertyTypes and noUncheckedIndexedAccess. Indexed access yields T | undefined; optional props cannot be assigned undefined explicitly. The linter (biome) treats unused vars/imports as errors and non-null assertions / any as warnings.
  • Bun-native, zero-framework. Use Bun.spawn, Bun.file, Bun.write, Bun.serve(), Bun.which() directly. The HTTP API is a raw Bun.serve() fetch handler — no Express/Hono.

Read the full file on GitHub · 83 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 · 83 lines · 1,620 tokens per session scan A a3807efd35e7

Subscribe to this mod's changes

Tarantul CLAUDE.md is an instructions file published in the GitHub repository FarkhodovIslom/Tarantul (6 stars, last pushed 3d ago), licensed MIT. It adds 1,620 tokens to every session, about $0.0081 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

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 · 5,182 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

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens