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/enescaakir/notify/claude-mdgit clone --depth 1 https://github.com/enescaakir/notifyWrote 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/instructions/enescaakir/notify/claude-md)<a href="https://agentmods.dev/instructions/enescaakir/notify/claude-md"><img src="https://agentmods.dev/badge/instructions/enescaakir/notify/claude-md.svg" alt="Measured on agentmods" 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 | $0.00496 | $0.00496 |
| Opus 5 | $0.00248 | $0.00248 |
| Sonnet 5 | $0.00099 | $0.00099 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
notify 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 5d 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.
What it actually says
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Plugin Overview
Claude Code plugin for Windows — fires toast notifications + audio on hook events. No build step. No tests. Edit files directly.
Architecture
| File | Role |
|---|---|
.claude-plugin/plugin.json |
Plugin manifest (name, version, author) |
hooks/hooks.json |
Hook event bindings |
hooks/notify.ps1 |
Generic notifier — accepts -Title, -Message, -Sound params; used by Stop |
hooks/notify-permission.ps1 |
Permission notifier — writes marker file, starts 3s delayed notification |
hooks/notify-post.ps1 |
Post-tool cleanup — removes marker file to cancel pending notification |
assets/claude-logo.jpg |
App logo shown in toasts |
Hook Event Logic
Stop → notify.ps1 with fixed title/message/sound. Simple.
PreToolUse → notify-permission.ps1:
- Reads stdin JSON → extracts
tool_name - Writes marker file
%TEMP%\claude-perm-<tool>.pending - Starts background PS: waits 3s, checks marker still exists, fires toast if so
PostToolUse → notify-post.ps1:
- Reads
tool_namefrom stdin - Removes marker file → cancels pending notification
Auto-approved tools: PostToolUse removes marker before 3s → no toast. Tools needing permission: user sees prompt while 3s expires → toast fires.
Dependencies
- BurntToast PowerShell module:
Install-Module BurntToast -Scope CurrentUser - Windows only (WPF
PresentationCore+ Windows toast APIs) - Built-in Windows sounds at
C:\Windows\Media\must exist
Extending
Add new event to hooks/hooks.json under the hook name (e.g. UserPromptSubmit). Call notify.ps1 with custom params, or write a new script for custom logic. ${CLAUDE_PLUGIN_ROOT} resolves to plugin root at runtime.
Active hooks: PreToolUse, PostToolUse, Stop. Do not duplicate these.
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.
- 5d ago First seen · 46 lines · 496 tokens per session scan A 915a4646d899
notify CLAUDE.md is an instructions file published in the GitHub repository enescaakir/notify (9 stars, last pushed 4mo ago), licensed MIT. It adds 496 tokens to every session, about $0.0025 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
workframe CLAUDE.md
Instructions for ryanzhao1011/workframe, covering workframe — 仓库维护约定, 这是什么, 四条硬约束, 两份 changelog and 提交与平台.
claudemd CLAUDE.md
Claude Code instructions for sdsrss/claudemd, covering code graph (repo-wide ast index) and claude-mem-lite — persistent memory.
mumei CLAUDE.md
Instructions for iroha924/mumei, covering mumei development guide, what mumei is, language policy, bash + jq conventions (essentials) and schemas/ conventions (essentials).
handoff CLAUDE.md
Instructions for AbdurRafay2004/handoff, covering claude.md, what this repo is, runtime model (how the pieces connect), invariants — do not break these when editing hooks and working / testing the hooks.
claude-plugins AGENTS.md
Instructions for msshives-gif/claude-plugins: Marketplace monorepo: every plugin lives under plugins/ /, one marketplace at .claude-plugin/marketplace.json. Simple code and simple documentation is best; complexity and big words are the enemy. Prefer the boring obvious shape; build machinery only when real use forces…
agent-setup AGENTS.md
Instructions for DefaultPerson/agent-setup, covering core, code edits, validation, priorities and if uncertain.