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 skills add Milkeles/turnbreak --skill adaptersgit clone --depth 1 https://github.com/Milkeles/turnbreakWrote 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.
[](https://agentmods.dev/skills/milkeles/turnbreak/adapters)<a href="https://agentmods.dev/skills/milkeles/turnbreak/adapters"><img src="https://agentmods.dev/badge/skills/milkeles/turnbreak/adapters/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/milkeles/turnbreak/adapters"><img src="https://agentmods.dev/badge/skills/milkeles/turnbreak/adapters.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00059 | $0.00677 |
| Opus 5.5 | $0.00024 | $0.00271 |
| Sonnet 5.5 | $0.00012 | $0.00135 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
turnbreak 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 1mo 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.
This is a copy
89% identical to turnbreak — 37 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
turnbreak skill
turnbreak shows you something worth reading while your coding agent works, then notifies you when it's done. It hooks into your agent's turn start/turn end events to time this.
turnbreak isn't published to a package index. It's already installed on
this machine at a fixed location, invoked below as {{TURNBREAK_COMMAND}}.
Always use that exact invocation. Don't assume a bare turnbreak binary is
on PATH, and don't guess an install source for it.
First, read ARGUMENTS
Whatever the user typed after /turnbreak appears below.
$ARGUMENTS
If that's empty, do NOT run install or any other command. Instead,
show this menu verbatim and stop. Do not take any action until the user
picks one:
turnbreak can:
- install: set up (or update) the turn-start/turn-stop hook for an agent
- onboard: first-run setup for reading interests and finder token consent
- interests: open the interests file to edit what you want to read
- mode: switch between a curated list and a local folder of files
- finder: switch which finder builds the curated list
Which one?
If ARGUMENTS names one of the commands below (e.g. interests, mode folder ~/notes, onboard, finder rss, install claude), skip the menu
entirely and just run that exact {{TURNBREAK_COMMAND}} ... invocation,
then report the result.
Commands
{{TURNBREAK_COMMAND}} install <claude|codex|gemini|copilot>: install or update the turn-start/turn-stop hook for that agent. Merges into existing config, never overwrites.{{TURNBREAK_COMMAND}} onboard: first-run setup. Collects reading interests, and if the agent finder is selected, confirms it's allowed to spend tokens.{{TURNBREAK_COMMAND}} interests: open the interests file in $EDITOR (or print its path if $EDITOR isn't set).{{TURNBREAK_COMMAND}} mode <curated|folder> [path]: switch between a curated reading list and a local folder of files.{{TURNBREAK_COMMAND}} finder <agent|rss|search>: switch which finder builds the curated list.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 64 lines · 59 tokens per session scan A cccffb8b8558
turnbreak is a skill published in the GitHub repository Milkeles/turnbreak (2 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 677 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to turnbreak, differing in 37 lines, and is treated as a copy.
Other skills, from other repositories
notification-auto-dismiss
A notification cleaner for Stop messages from subscribed worktrees. It removes messages that are only waiting for background work to finish and leaves messages needing human input.
briefing
Create an athlete-owned calendar note.
loop-wiki
Ingest and grow an Obsidian knowledge base as a verifiable loop. Combines Loop Engineering (machine-checkable completion criteria, boundary guardrails, a verification pass that resists gaming) with the Obsidian "second brain" organizing model (typed nodes, wikilinks, MOC, an index and an audit log). Use this whenever…
sync-awareness
Suggest syncing MCP server configurations or instruction files to other AI coding agents when the user is editing MCP settings (.claude.json, .mcp.json) or modifying CLAUDE.md files. Available commands: /sync, /sync-list, /sync-diff, /sync-instructions.
discord-communication
A skill for communicating with people through Discord, a chat platform for text, files, and notifications.
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".