turnbreak AGENTS.md

A repository instruction file for the Turnbreak project. It records the project's purpose, commands, coding style, and conventions for coding agents.

In plain words
What is it for?
Use it when installing dependencies, running tests, linting, formatting, type-checking, building, or starting the Turnbreak server.
Why use it?
It gives agents the project-specific context needed to work consistently and use the right commands.

Instructions file for CodexOpenCode

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/milkeles/turnbreak/agents-md
Clone the repo
git clone --depth 1 https://github.com/Milkeles/turnbreak

Made for: Codex, OpenCode.

Per session 2,937 This file is loaded in full into every session.
When invoked 2,937 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.

ModelPer sessionOnce invoked
Fable 5 $0.02937 $0.02937
Opus 5 $0.01469 $0.01469
Sonnet 5 $0.00587 $0.00587
Haiku 4.5 $0.00294 $0.00294

Measured 2d ago against content hash e7ae09716497, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

turnbreak 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 · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent instructions file: turnbreak

Covers Whole repo
Last reviewed 2026-08-17

1. Project overview

Turnbreak is an installable agent skill. It shows you something worth reading while your coding agent works, then notifies you when the agent is done.

It fires only after the agent has been running for a set time. It runs in one reused browser tab, never in the agent's terminal.

The name is turnbreak, chosen 2026-08-16 over interlude, idlepage, and waitread. Naming decisions aren't ADRs and don't live in docs/adrs/. If the maintainer renames the project again, rename it everywhere in one commit.


2. Commands

Task Command
Install dependencies uv sync --extra dev --extra sources
Run all tests pytest
Run a single test pytest tests/test_timer.py::test_fires_after_threshold -x
Lint ruff check .
Format ruff format .
Type check mypy src/turnbreak
Build python -m build
Start the server and open the tab turnbreak serve --port 7717
Run the server attached to this terminal turnbreak serve --port 7717 --foreground
Stop a background server turnbreak serve --stop

3. Code style

Python 3.11 or newer. Standard library only in src/turnbreak/core/. Third-party packages are allowed in src/turnbreak/sources/ and in tests.

This split exists because the core runs on every agent turn, inside a synchronous hook. A slow import is a slow turn.

Type hints on every public function. Dataclasses over dicts for anything crossing a module boundary.

For any substantial piece of work, look for an established, well-tested library or API before writing it from scratch. Hand-rolled code for a solved problem, like feed parsing or article extraction, is more likely to be buggy and harder to maintain than a maintained dependency. sources/ and tests may take on third-party dependencies for this reason. Only implement from scratch once a real search turns up nothing suitable, and say why in the commit or ADR.

Read the full file on GitHub · 220 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. 2d ago First seen · 220 lines · 2,937 tokens per session scan A e7ae09716497

Subscribe to this mod's changes

turnbreak AGENTS.md is an instructions file published in the GitHub repository Milkeles/turnbreak (2 stars, last pushed 9d ago), licensed MIT. It adds 2,937 tokens to every session, about $0.0147 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.