What is tau AGENTS.md?

Development guidance for Tau, a Python coding-agent framework with separate layers for the agent logic, coding environment, and user interface. It also describes the project roadmap and testing direction.

Use it to decide where new code belongs, follow the roadmap, and implement or test the interactive terminal interface.

It helps agents preserve the project’s architecture while adding features incrementally and keeping the core independent from the command-line interface and display code.

tau AGENTS.md — Instructions file by huggingface

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/huggingface/tau/agents-md

Clone the repo

git clone --depth 1 https://github.com/huggingface/tau

Made for: Codex, OpenCode.

Per session 678 This file is loaded in full into every session.

When invoked 678 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	$0.00678	$0.00678
Opus 5	$0.00339	$0.00339
Sonnet 5	$0.00136	$0.00136
Haiku 4.5	$0.00068	$0.00068

Measured 2d ago against content hash 081b6d99eefa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tau AGENTS.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 2d 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.

AGENTS.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tau Agent Instructions

Tau is a Python implementation of Pi's minimalist coding-agent harness architecture. The goal is to develop it incrementally, with each phase clearly documented and tested.

Project Roadmap

The implementation roadmap is tracked in GitHub issue #1:

https://github.com/huggingface/tau/issues/1

Use that issue as the primary reference for phase ordering and architectural intent.

Architecture Principles

Preserve Pi's core separation of concerns:

AgentHarness = reusable agent brain
AgentSession = coding-agent environment
TUI = one possible frontend

Tau should be organized around these layers:

tau_ai      provider/model streaming layer
tau_agent   portable agent harness, loop, tools, events, sessions
tau_coding  CLI app, resources, skills, extensions, commands, TUI integration

Keep the core agent package independent of CLI, Textual, Rich rendering, session file locations, and application-specific resource loading.

TUI Direction

Use Textual for the full interactive TUI, but only behind an adapter boundary. The agent harness should emit events; UI layers should consume those events.

Early phases should prioritize:

print-mode CLI
Rich renderers
Textual interactive app

Do not let Textual become a dependency of the reusable agent harness.

Development Workflow

Work in small, documented phases.
Keep changes aligned with the roadmap issue.
Add or update docs when introducing architectural concepts.
Add tests for behavior before expanding features.
Run tests and Python commands through uv (for example, uv run pytest or uv run python ...) so they use the project environment.
Prefer simple, explicit abstractions over framework-heavy designs.
Keep commits atomic: one coherent feature, fix, docs update, refactor, or cleanup per commit.

GitHub Issue and PR Formatting

When creating or editing GitHub issues and pull requests from the CLI, write multiline Markdown bodies through a temporary file or heredoc and pass them with --body-file.
Do not pass escaped newlines like \n inside quoted --body strings; GitHub will render them literally instead of as line breaks.
Use Markdown headings, blank lines, bullets, and backticks for commands/paths so issue and PR descriptions are readable.
After creating or editing a GitHub issue or PR body, verify the rendered source with gh issue view ... --json body or gh pr view ... --json body when practical.

Read the full file on GitHub · 82 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.

2d ago First seen · 82 lines · 678 tokens per session scan A 081b6d99eefa

Subscribe to this mod's changes

tau AGENTS.md is an instructions file published in the GitHub repository huggingface/tau (2,579 stars, last pushed yesterday), licensed MIT. It adds 678 tokens to every session, about $0.0034 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.

Planning Productivity

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

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

tau AGENTS.md