agentmods.dev

HushFlow CLAUDE.md

HushFlow CLAUDE.md is an instructions file for coding agents from cry8a8y/HushFlow. It costs 900 tokens per session, scanned A, original, MIT.

Project instructions for HushFlow, a Bash command-line tool that turns waiting time for an AI coding assistant into guided breathing exercises.

In plain words
What is it for?
Use them when changing HushFlow so you follow its Bash-only setup, branch-and-pull-request workflow, commit format, and required test commands.
Why use it?
They give Claude Code the project's conventions for language, commits, pull requests, testing, and documentation.

Instructions file

not rated 1 5mo ago A scan 900 tokens original MIT
View the source file cry8a8y/HushFlow
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/cry8a8y/hushflow/claude-md
Clone the repo
git clone --depth 1 https://github.com/cry8a8y/HushFlow

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 HushFlow CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cry8a8y/hushflow/claude-md.svg)](https://agentmods.dev/instructions/cry8a8y/hushflow/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cry8a8y/hushflow/claude-md"><img src="https://agentmods.dev/badge/instructions/cry8a8y/hushflow/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 900 This file is loaded in full into every session.
When invoked 900 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 $0.00900 $0.00900
Opus 5 $0.00450 $0.00450
Sonnet 5 $0.00180 $0.00180
Haiku 4.5 $0.00090 $0.00090

Measured 3d ago against content hash abf90f57e7e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

HushFlow CLAUDE.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 3d 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.

CLAUDE.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HushFlow — Claude Code Instructions

Project Overview

HushFlow is a CLI tool that turns AI coding assistant wait time into guided breathing exercises. Pure Bash implementation, no build step.

Key Conventions

  • Language: Code, commits, and CLI output in English. Documentation available in EN/zh-TW/zh-CN/ja.
  • Commit format: <type>(<scope>): <description> — types: feat, fix, docs, test, chore, refactor
  • PR flow: All changes via branch → PR → merge. No direct push to main.
  • Testing: Run all test suites before committing. All tests must pass.
    • bash test/smoke-test.sh — Core smoke tests (156+ tests)
    • bash test/terminal-detect-test.sh — Terminal detection tests (19 tests)
    • bash test/unit-test.sh — Unit tests for pure functions (29 tests)
    • bash test/sound-test.sh — Sound system tests (27 tests)
    • bash test/install-contract-test.sh — Installer contracts: 3 targets × 7 scenarios (76+ tests)
    • bash test/e2e-install-test.sh — E2E install flow: fresh, non-git dir, update, reinstall (31 tests)
    • bash test/onboarding-test.sh — Onboarding wizard tests (23 tests)
    • bash scripts/test-ui-layout.sh --ci — UI layout tests (requires tmux)
    • pwsh test/install-ps1-test.ps1 — PowerShell installer tests (Windows only)
    • See docs/testing/install-matrix.md for the full cross-platform test matrix

Architecture

  • breathe-compact.sh — Core rendering engine (SIN64/COS32 lookup tables, 10fps double-buffer)
  • cli.sh — CLI entry point for npx hushflow (routes: install, config, theme, animation, sound, stats, doctor, onboarding, version)
  • onboarding.sh — Guided first-run wizard (exercise/theme selection + 5-second live demo)
  • set-exercise.sh — Config management (exercises, themes, animations, sound)
  • hooks/on-start.sh / on-stop.sh — AI tool lifecycle hooks (start/stop + session notification + onboarding trigger)
  • hooks/on-permission.sh — Pauses breathing on PermissionRequest
  • hooks/on-resume.sh — Smart resume after permission approval (3-tier expiry)
  • lib/hook-common.sh — Shared hook bootstrap (hf_log, CONFIG_DIR, SESSION_DIR)
  • lib/stats.sh — Session statistics (TSV format: timestamp\tcycles\tduration\texercise\tanimation\ttheme)
  • lib/wrap.sh — Universal CLI wrapper (hushflow wrap -- <cmd>)
  • lib/sound.sh — Async audio playback with crossfade (ffplay/mpv/afplay/paplay)
  • lib/detect-background.sh — Terminal background color detection (OSC 11)
  • lib/detect-terminal.sh — Terminal emulator detection
  • themes/*.json — Community themes (JSON with RGB color values)

Read the full file on GitHub · 56 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. 3d ago First seen · 56 lines · 900 tokens per session scan A abf90f57e7e1

Subscribe to this mod's changes

HushFlow CLAUDE.md is an instructions file published in the GitHub repository cry8a8y/HushFlow (1 stars, last pushed 5mo ago), licensed MIT. It adds 900 tokens to every session, about $0.0045 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.

breathingclaude-codecligemini-climindfulnessterminal
Related

Other instructions, from other repositories

kmux AGENTS.md

Instructions for kkd927/kmux, covering agents.md, kmux focus and test discipline.

kkd927/kmux · 324 tokens

stealth-code CLAUDE.md

Instructions for suxrobGM/stealth-code, covering stealthcode, build & run, architecture, project structure and key conventions.

suxrobGM/stealth-code · 692 tokens

gemini-cli-hud GEMINI.md

Instructions for yideng-xl/gemini-cli-hud, covering gemini cli hud, what it shows, how it works and notes.

yideng-xl/gemini-cli-hud · 342 tokens

herd CLAUDE.md

Claude Code instructions for poddubnyoleg/herd, covering claude.md, commands, architecture and key design decisions.

poddubnyoleg/herd · 4,674 tokens

herd GEMINI.md

Gemini CLI instructions for poddubnyoleg/herd, covering gemini.md, architecture overview, core tasks & behaviors, file structure and api endpoints.

poddubnyoleg/herd · 663 tokens

gemini-cli-hud AGENTS.md

Instructions for yideng-xl/gemini-cli-hud: This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in nodemodules/next/dist/docs/ before writing any code. Heed deprecation notices.

yideng-xl/gemini-cli-hud · 74 tokens