What is timbal CLAUDE.md?

Development instructions for timbal-ai/timbal, a Python project for building agents and workflows. They cover setup, tests, formatting, linting, benchmarks, and the repository layout.

Use them to install dependencies, run all or selected tests, format and lint Python code, run benchmarks, and find the main source and test directories.

They give contributors the commands and project structure needed to develop and check changes consistently.

timbal CLAUDE.md — Instructions file for coding agents by timbal-ai: Development instructions for timbal-ai/timbal, a Python project for bui

Install

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.

agentmods

npx agentmods add instructions/timbal-ai/timbal/claude-md

Clone the repo

git clone --depth 1 https://github.com/timbal-ai/timbal

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/timbal-ai/timbal/claude-md.svg)](https://agentmods.dev/instructions/timbal-ai/timbal/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/timbal-ai/timbal/claude-md"><img src="https://agentmods.dev/badge/instructions/timbal-ai/timbal/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 7,719 This file is loaded in full into every session.

When invoked 7,719 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.

Model	Per session	Once invoked
Fable 5	$0.07719	$0.07719
Opus 5	$0.03860	$0.03860
Sonnet 5	$0.01544	$0.01544
Haiku 4.5	$0.00772	$0.00772

Measured today against content hash 74ef4f03cc18, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

timbal 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 today.

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 · 708 lines

How it starts

The opening of the file, as written. The whole thing — 708 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.

Commands

Development and Testing

Install dependencies: uv sync --dev (from repo root — pyproject.toml is at root)
Run all tests: uv run pytest (from repo root)
Run single test: uv run pytest python/tests/core/test_agent.py::TestClass::test_method
Linting: uv run ruff check
Format: uv run ruff format
Fix lint: uv run ruff check --fix
Line length: 120 chars (configured in pyproject.toml)

Benchmarks

Langchain benchmarks: cd benchmarks/langchain && uv pip install langchain-core langsmith langgraph && uv run pytest bench_*.py
Quick mode (faster, fewer iterations): default
Full mode: set env TIMBAL_BENCH_MODE=full

Repository Layout

timbal/
├── python/
│   ├── timbal/               # Main package
│   │   ├── __init__.py       # Top-level exports: Agent, Workflow
│   │   ├── core/
│   │   │   ├── runnable.py   # Base class for all executable components
│   │   │   ├── agent.py      # Agent execution engine
│   │   │   ├── workflow.py   # DAG workflow engine
│   │   │   ├── tool.py       # Tool wrapper
│   │   │   ├── tool_set.py   # ToolSet ABC for runtime tool resolution
│   │   │   ├── mcp.py        # MCPServer — MCP servers as tool sources
│   │   │   ├── llm/          # Multi-provider LLM dispatch (router, registry, clients, retry + one module per API)
│   │   │   ├── models.py     # Model strings + context window lookup
│   │   │   └── test_model.py # Offline TestModel for testing
│   │   ├── state/
│   │   │   ├── __init__.py   # get_run_context, get_call_id, etc.
│   │   │   ├── context.py    # RunContext definition
│   │   │   ├── background.py # Session-scoped background-task store
│   │   │   └── tracing/
│   │   │       ├── providers/
│   │   │       │   ├── base.py       # TracingProvider ABC + Exporter ABC
│   │   │       │   ├── in_memory.py  # Default in-memory provider
│   │   │       │   ├── jsonl.py      # JSONL file provider
│   │   │       │   └── platform.py   # Timbal platform provider
│   │   │       └── exporters/
│   │   │           └── otel.py       # OTelExporter (fire-and-forget OTLP/HTTP)
│   │   ├── types/
│   │   │   ├── message.py    # Message with role + content list
│   │   │   ├── file.py       # File type with auto content detection
│   │   │   ├── content/      # TextContent, ToolUseContent, FileContent, etc.
│   │   │   └── events/       # StartEvent, DeltaEvent, OutputEvent
│   │   ├── collectors/       # Output processing; TimbalCollector is default
│   │   └── tools/            # Built-in tool library (Bash, Slack, Gmail, etc.)
│   └── tests/
│       └── core/             # Test files mirroring package structure
├── benchmarks/
│   ├── README.md             # General benchmark guide
│   └── langchain/            # Timbal vs LangChain/LangGraph benchmarks
├── planning/                 # In-progress feature plans (gitignored)
└── pyproject.toml            # Root package config + dev deps

Read the full file on GitHub · 708 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.

today Changed · +18 lines · +351 tokens per session 74ef4f03cc18
5d ago First seen · 690 lines · 7,368 tokens per session scan A 96f1a53fdae7

Subscribe to this mod's changes

timbal CLAUDE.md is an instructions file published in the GitHub repository timbal-ai/timbal (42 stars, last pushed yesterday), licensed Apache-2.0. It adds 7,719 tokens to every session, about $0.0386 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 2026-08-30.

Languages Python agents ai ai-agents ai-agents-framework framework llms

openai-agents-python AGENTS.md

AGENTS.md instructions for openai/openai-agents-python, covering contributor guide, policies & mandatory rules, mandatory skill usage, work status reporting and git worktree and branch safety.

openai/openai-agents-python · 8,006 tokens

railtracks AGENTS.md

AGENTS.md instructions for RailtownAI/railtracks, covering repository overview, accessing docs, setup, common commands and lint / format (must pass before commit, ci enforces this).

RailtownAI/railtracks · 2,434 tokens

Agentflow CLAUDE.md

Instructions for 10xHub/Agentflow, covering agentflow (core python library) — engineering guide, what this package is, working principles for this codebase, package layout (real, current) and import map (verified) — this is the part that bites people.

10xHub/Agentflow · 2,839 tokens

timbal CLAUDE.md