breakwatch: Instructions file for Claude Code

AGENTS.md

breakwatch AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from Kepei-Lei102/breakwatch. It costs 1,374 tokens per session, scanned B, original, MIT.

An `AGENTS.md` instruction manual for installing and calibrating breakwatch, a break-reminder tool for Claude Code. It describes the setup procedure, platform limitations, testing steps, and rules for agents working in the repository.

In plain words
What is it for?
Use it when setting up breakwatch, checking macOS, Windows, or Linux compatibility, choosing hook commands, calibrating thresholds, and testing the installation.
Why use it?
It gives an agent repository-specific operating instructions, including how to account for different operating systems and the user’s own work patterns.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is Kepei-Lei102/breakwatch's own configuration. It tells Claude Code, Codex and OpenCode how to work on breakwatch itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything breakwatch configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Kepei-Lei102/breakwatch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Kepei-Lei102/breakwatch/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Kepei-Lei102/breakwatch

Made for: Claude Code, Codex, OpenCode.

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.

agentmods badge for breakwatch AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kepei-lei102/breakwatch/agents-md.svg)](https://agentmods.dev/instructions/kepei-lei102/breakwatch/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kepei-lei102/breakwatch/agents-md"><img src="https://agentmods.dev/badge/instructions/kepei-lei102/breakwatch/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,374 This file is loaded in full into every session.
When invoked 1,374 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01374 $0.01374
Opus 5 $0.00687 $0.00687
Sonnet 5 $0.00275 $0.00275
Haiku 4.5 $0.00137 $0.00137

Measured 8d ago against content hash 6daf351a9ae6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

breakwatch AGENTS.md scanned grade B with 1 finding 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 8d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`~/.claude/settings.json`. **Merge, never overwrite** — that file may already
AGENTS.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent manual — installing and calibrating breakwatch

You have been handed this repository by someone who wants breakwatch set up. README.md is written for a human deciding whether to install. This file is the operating procedure for you.

The one thing you can do that a README cannot: calibrate the thresholds to this person before switching anything on. The shipped numbers are one user's, derived from their midnight pattern. Installing them unexamined is the exact mistake this tool exists to correct. Do not skip step 3.

Procedure

0. Check the platform first. macOS is verified end to end. Windows and Linux are written but were never run — the author had no machine for either. On those, say so plainly before installing rather than after it fails, and treat step 5 as a real test rather than a demo. On Windows also confirm the interpreter: python3 frequently does not resolve there, and if py -3 is what works, substitute it in both hook commands during install.

1. Install. Ask which they prefer, or infer it — if ~/.claude/plugins/ shows they use plugins, add this repo as a marketplace and /plugin install breakwatch. Otherwise do the manual install from README.md: copy plugins/breakwatch/hooks/breakwatch.py to ~/.claude/worklog/, copy plugins/breakwatch/skills/take-a-break/ to ~/.claude/skills/, copy HARNESS.md next to the script, and merge the hooks block into ~/.claude/settings.json. Merge, never overwrite — that file may already hold their permissions, env, and other hooks.

2. Backfill. python3 <path>/breakwatch.py backfill. Claude Code has been writing timestamped transcripts since they started using it, so this gives them months of history immediately, and the tool is useful today rather than in a fortnight. It only writes days that have no file yet, so it is safe to re-run.

3. Calibrate before enabling — the step that matters. Run report 30 and read it for this person, then say what you found in plain numbers. Useful questions:

Read the full file on GitHub · 104 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. 8d ago First seen · 104 lines · 1,374 tokens per session scan B 6daf351a9ae6

Subscribe to this mod's changes

breakwatch AGENTS.md is an instructions file published in the GitHub repository Kepei-Lei102/breakwatch (1 stars, last pushed 26d ago), licensed MIT. It adds 1,374 tokens to every session, about $0.0069 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

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