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 skills add saski/arnesto --skill code-notifygit clone --depth 1 https://github.com/saski/arnestoWrote 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/skills/saski/arnesto/code-notify)<a href="https://agentmods.dev/skills/saski/arnesto/code-notify"><img src="https://agentmods.dev/badge/skills/saski/arnesto/code-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.
<a href="https://agentmods.dev/skills/saski/arnesto/code-notify"><img src="https://agentmods.dev/badge/skills/saski/arnesto/code-notify.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00054 | $0.00352 |
| Opus 5.5 | $0.00022 | $0.00141 |
| Sonnet 5.5 | $0.00011 | $0.00070 |
| Haiku 4.5 | $0.00005 | $0.00035 |
Grade A, and why
code-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 1mo 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
Code Notify
Goal
Make supported AI tools finish noisy terminal work with a local notification instead of requiring manual polling.
Use This Skill When
- The user asks to enable or wire completion notifications for an AI coding tool.
- A workflow should notify when a long-running task finishes or needs attention.
- You are documenting shared agent capabilities in a cross-tool setup.
Cross-Platform Rules
- Treat
code-notifyas an optional local dependency managed outside this repository. - Verify the installed command, wrapper, hook, or config before using it.
- Prefer shared wording and forward-slash paths so the guidance works across macOS, Linux, and Windows-compatible shells.
- Keep the integration additive. Do not replace existing hooks or notification settings unless the user asks.
Workflow
- Detect whether the current tool already has a notification hook or wrapper configured.
- Look for a local
code-notifycommand, alias, script, or documented install path before assuming invocation details. - If present, use it for end-of-task or attention-needed notifications only.
- If missing, tell the user the integration is unavailable in the current shell and continue without blocking the main task.
Output Guidance
- Mention that
code-notifyis available only after verifying the local installation. - Keep notification instructions tool-agnostic unless the user asks for a specific platform.
- Prefer concise setup notes over tool-specific prose duplication.
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.
- 1mo ago First seen · 37 lines · 54 tokens per session scan A 9d6abc86611e
code-notify is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed yesterday), licensed Unlicense. It adds 54 tokens to every session and 352 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
discovery-question-form
Structured clarification form for unresolved material requirements.
mailbox
A guide for performing email and mailbox tasks through the QwenPaw mailbox system. It covers supported personal email providers, credentials, configuration, and the required mailbox workflow.
channel_message
Use this skill to proactively send a one-way message to a user/session/channel, usually only when the user explicitly asks to send to a channel/session or when proactive notification is needed. First query sessions with qwenpaw chats list, then push with qwenpaw channels send.
mission-slice-sop
Use when starting, building, handing off, restoring, or closing a mission or slice under the default lightweight SDLC.
oma-recap
Summarize AI conversation histories for a specified date or period. Use for daily work recaps and cross-tool activity summaries.