verbatim-audit-notify

verbatim-audit-notify is a skill for Claude Code from terrylica/cc-skills. It costs 59 tokens per session (3,842 once invoked), scanned A, original, MIT.

A notification workflow that sends Pushover alerts with a unique ID and saves the complete message in a local JSONL audit log. Pushover is a service that delivers push notifications to phones; JSONL is a text format with one JSON record per line.

In plain words
What is it for?
Use it for alerts from scheduled jobs, background services, and automation scripts, especially when an alert may need its full error output or command context.
Why use it?
Phone alerts have short message limits, so long error details can be cut off. The ID lets you retrieve the full original payload later when investigating a failure.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions Claude Code.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/terryli/Library/Containers/org.p0deje.Maccy/Data/Library/Application.

Part of the pushover-commander plugin — 9 skills shipped together , and of cc-skills

Good fit Use it for alerts from scheduled jobs, background services, and automation scripts, especially when an alert may need its full error output or command context.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add terrylica/cc-skills
Claude Code
/plugin install pushover-commander

Made for: Claude Code.

Or install pushover-commander, the plugin that ships this one along with the rest of its 9 skills.

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 verbatim-audit-notify

README.md
[![agentmods](https://agentmods.dev/badge/skills/terrylica/cc-skills/verbatim-audit-notify/github.svg)](https://agentmods.dev/skills/terrylica/cc-skills/verbatim-audit-notify)
Your own site
<a href="https://agentmods.dev/skills/terrylica/cc-skills/verbatim-audit-notify"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/verbatim-audit-notify/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.

agentmods 80×15 button for verbatim-audit-notify

Your own site · 80×15
<a href="https://agentmods.dev/skills/terrylica/cc-skills/verbatim-audit-notify"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/verbatim-audit-notify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,842 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00059 $0.03842
Opus 5 $0.00030 $0.01921
Sonnet 5 $0.00012 $0.00768
Haiku 4.5 $0.00006 $0.00384

Measured 6d ago against content hash 6a481a71bae9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

verbatim-audit-notify 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 6d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/pushover-heartbeat.sh, scripts/pushover-lookup.sh, scripts/pushover-notify.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/pushover-commander/skills/verbatim-audit-notify/SKILL.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pushover Verbatim+UUID Notification

Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.

A two-script skill that solves the "Pushover message hit my phone but I don't remember what it was about" problem for personal automation fleets. Every notification carries a UUID; the full verbatim payload (including everything that didn't fit in Pushover's 1024-char body) lands in a local JSONL audit log keyed by that UUID. You look it up by pasting the UUID back.

Designed for: cron-fired scripts, launchd daemons, hook outputs — any place that wants "fire-and-forget alerting with full context if you ever need to dig in." Personal scale; one Mac; one Pushover account. Not a microservices observability stack.

Why this exists

Pushover messages are limited to 1024 UTF-8 characters in the body and 250 in the title (per pushover.net/api). Real failure events often need thousands of chars of context: stack traces, full env dumps, file paths, the exact failing command. Truncating loses what you actually need to debug.

The fix is the correlation-ID-plus-JSONL pattern: short summary on the device, full verbatim payload in a local newline-delimited JSON file, UUID linking them. When a notification fires, the body contains the UUID and a pushover-lookup command. Run that and you get the complete entry.

Five scripts + three launchd templates

Asset Role
scripts/pushover-notify.sh Sender: generates UUID, writes verbatim JSONL, dispatches Pushover with summary+UUID
scripts/pushover-lookup.sh Retriever: given a UUID (or prefix), prints the pretty-printed JSONL entry
scripts/pushover-prune.sh Retention pruner: deletes audit-YYYYMMDD.jsonl files older than N days (default 30)
scripts/pushover-quota.sh Quota monitor: hits Pushover /apps/limits.json, persists JSON, alerts when low (iter 12b)
scripts/pushover-heartbeat.sh Daily fleet status summary — companion+kokoro+github-notif+quota+disk+failed services (iter 20)
templates/com.terryli.pushover-prune.plist launchd timer — daily at 04:15, 90-day retention (iter 8)
templates/com.terryli.pushover-quota.plist launchd timer — daily at 03:30, alerts when remaining <20% (iter 12b)
templates/com.terryli.pushover-heartbeat.plist launchd timer — daily at 09:03, INFO heartbeat (auto-promotes to WARN on failure) (iter 20)

Read the full file on GitHub · 279 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. 6d ago First seen · 279 lines · 59 tokens per session scan A 6a481a71bae9

Subscribe to this mod's changes

verbatim-audit-notify is a skill published in the GitHub repository terrylica/cc-skills (72 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 3,842 once invoked, about $0.0003 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 2026-09-05.

Related

Other skills, from other repositories

android-development

Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.

travisjneuman/.claude · 33 tokens

email-systems

Transactional email (Resend, SendGrid, SES), templates (React Email, MJML), deliverability (SPF/DKIM/DMARC), and inboxing best practices. Use when building email infrastructure, designing templates, or troubleshooting deliverability.

travisjneuman/.claude · 55 tokens

customer-persona-builder

Data-driven customer persona development combining market research, user behavior analysis, and segmentation frameworks. Use when creating buyer personas, ideal customer profiles (ICPs), or user archetypes.

travisjneuman/.claude · 40 tokens

devops-cloud

DevOps, cloud infrastructure, and platform engineering. Use when working with AWS, GCP, Azure, Kubernetes, Terraform, CI/CD pipelines, or infrastructure as code.

travisjneuman/.claude · 38 tokens

generic-design-system

Complete design system reference for any project - colors, typography, spacing, components, animations. Adapts to project theme and tech stack. Use when implementing UI, choosing colors, creating animations, or ensuring brand consistency. For new design systems, use ui-research skill first.

travisjneuman/.claude · 60 tokens

generic-code-reviewer

Review code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Supports any tech stack - HTML/CSS/JS, React, TypeScript, Node.js, Python, NestJS, Next.js, and more. Use when completing features, before commits, or reviewing pull requests.

travisjneuman/.claude · 70 tokens