notifications

notifications is a skill for Claude Code, Codex from shwilliamson/automatasaurus. It costs 31 tokens per session (638 once invoked), scanned A, original, MIT.

A notification system that alerts the user when an agent needs a response, approval, help with a problem, or has finished work.

In plain words
What is it for?
Sending attention requests for questions, approvals, blocked work, completion, general information, and errors.
Why use it?
It makes important moments visible when the user is not watching the agent continuously.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

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 skills/shwilliamson/automatasaurus/notifications
Any agent
npx skills add shwilliamson/automatasaurus --skill notifications
Clone the repo
git clone --depth 1 https://github.com/shwilliamson/automatasaurus

Made for: Claude Code, Codex.

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 notifications

README.md
[![agentmods](https://agentmods.dev/badge/skills/shwilliamson/automatasaurus/notifications.svg)](https://agentmods.dev/skills/shwilliamson/automatasaurus/notifications)
Your own site
<a href="https://agentmods.dev/skills/shwilliamson/automatasaurus/notifications"><img src="https://agentmods.dev/badge/skills/shwilliamson/automatasaurus/notifications.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 638 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00031 $0.00638
Opus 5 $0.00015 $0.00319
Sonnet 5 $0.00006 $0.00128
Haiku 4.5 $0.00003 $0.00064

Measured 5d ago against content hash b56e4d7731df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

notifications 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.

template/skills/notifications/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Notification System

Automatasaurus includes a notification system to alert the user when their attention is needed.

Automatic Notifications

The system automatically sends notifications on stop based on context:

  • Questions: When Claude asks a question and waits for input
  • Approvals: When approval is needed to proceed
  • Stuck: When an agent encounters an issue
  • Complete: When all work is done

Explicit Notification Request

When you need to explicitly alert the user, use:

.claude/hooks/request-attention.sh <type> "<message>"

Notification Types

Type When to Use Sound
question You have a question that needs answering Submarine
approval You need approval before proceeding Submarine
stuck You've encountered an issue you can't resolve Basso (alert)
complete All assigned work is finished Hero (success)
info General notification Glass
error An error occurred Basso (alert)

Examples

# Question needs answering
.claude/hooks/request-attention.sh question "Should I use PostgreSQL or MySQL for this project?"

# Approval needed
.claude/hooks/request-attention.sh approval "PR #42 is ready for review"

# Got stuck
.claude/hooks/request-attention.sh stuck "Cannot access the GitHub API - authentication failed"

# Work complete
.claude/hooks/request-attention.sh complete "All 5 user stories have been implemented and tested"

# Error occurred
.claude/hooks/request-attention.sh error "Build failed with 3 errors"

When to Notify

Always Notify For:

  • Questions that block progress
  • Security-related approvals
  • When you've been stuck for more than one attempt
  • Completion of significant milestones
  • Errors that require human intervention

Don't Notify For:

  • Minor progress updates
  • Self-recoverable errors
  • Questions you can answer from context

Configuration

Notifications can be configured via environment variables:

Read the full file on GitHub · 96 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. 5d ago First seen · 96 lines · 31 tokens per session scan A b56e4d7731df

Subscribe to this mod's changes

notifications is a skill published in the GitHub repository shwilliamson/automatasaurus (5 stars, last pushed 6mo ago), licensed MIT. It adds 31 tokens to every session and 638 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens