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/milkeles/turnbreak/agents-mdgit clone --depth 1 https://github.com/Milkeles/turnbreakWhat 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 | $0.02937 | $0.02937 |
| Opus 5 | $0.01469 | $0.01469 |
| Sonnet 5 | $0.00587 | $0.00587 |
| Haiku 4.5 | $0.00294 | $0.00294 |
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.
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.
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 · 220 lines · 2,937 tokens per session scan A e7ae09716497
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.
Other instructions, from other repositories
sync-agents-settings CLAUDE.md
Instructions for Leoyang183/sync-agents-settings, covering claude.md, commands, architecture, testing and publishing.
sync-agents-settings AGENTS.md
Instructions for Leoyang183/sync-agents-settings, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
obsidian-mind CLAUDE.md
Claude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli.
TokenTracker CLAUDE.md
Claude Code instructions for xiufengsun/TokenTracker, covering claude.md, project shape, frequently used commands, what's where and load-bearing conventions.
obsidian-mind AGENTS.md
AGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo.
parallel-code CLAUDE.md
Instructions for johannesjo/parallel-code, covering parallel code, stack, commands, project structure and conventions.