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 skills/brentfarris/echo/global-notificationsnpx skills add BrentFarris/echo --skill global-notificationsgit clone --depth 1 https://github.com/BrentFarris/echoWrote 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/brentfarris/echo/global-notifications)<a href="https://agentmods.dev/skills/brentfarris/echo/global-notifications"><img src="https://agentmods.dev/badge/skills/brentfarris/echo/global-notifications.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 | $0.00052 | $0.01017 |
| Opus 5 | $0.00026 | $0.00508 |
| Sonnet 5 | $0.00010 | $0.00203 |
| Haiku 4.5 | $0.00005 | $0.00102 |
Grade A, and why
global-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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Global notifications (cross-surface / cross-tab alerts)
Echo has two kinds of alerts that must reach the user even when they are NOT looking at the affected chat tab or surface. Session-scoped session_events (tool_call with status: awaiting_input, etc.) are only broadcast to clients subscribed to that workspace+surface+active tab, so they CANNOT be used for global alerts. Instead Echo uses global Hub broadcasts + frontend listener modules.
The chat-completion pattern (model to copy)
- Backend (
internal/server/chat_sessions.go): on turn finish withstatus == "done", calls.manager.server.hub.Broadcast(chatCompletedMessage{...})withtype: "chat_completed",workspaceId,workspaceName,surface(chat|code),chatId,turnId,preview.Hub.Broadcast(inws.go) fans out to all clients (no subscription needed). - Frontend (
web/src/completionNotifications.ts, started inweb/js/app.jsbootstrap viastartCompletionNotifications()): listensws.on("chat_completed", ...), playsnotification-1.wavsound, and shows a browserNotification. Clicking it doeswindow.location.hash = chatCompletionRouteHash({workspaceId, chatId, surface}), which deep-links to the exact chat tab. Tab activation is already handled:home.js(chat surface) andcodeView.ts(code surface,?chat=open) readchatCompletionTargetFromHashand callactivateChatTab/expectedChatId+onExpectedChatResolved. chatCompletionRouteHash/chatCompletionTargetFromHashlive inweb/src/navigation.ts.
Plan-question notifications (mirrors the completion pattern)
When a Plan-mode ask_user_questions call starts awaiting input:
- Backend
chat_sessions.go(~line 2103) broadcastsplanQuestionsMessagewithtype: "plan_questions_awaiting"+ the same target metadata (workspaceId,workspaceName,surface,chatId,turnId,callId) plusquestions(array of{id, question, options}). This is additive; the session-scopedtool_callevent remains for the active-view rendering. - Frontend
web/src/planQuestionNotifications.ts(started viastartPlanQuestionNotifications()inapp.js) listensws.on("plan_questions_awaiting", ...), plays the question sound (delegated toplayPlanQuestionSound()), and shows a notification. Clicking deep-links viachatCompletionRouteHashlike completions.
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.
- 4d ago First seen · 39 lines · 52 tokens per session scan A 5bf47afbb0d4
global-notifications is a skill published in the GitHub repository BrentFarris/echo (11 stars, last pushed 5d ago), licensed MIT. It adds 52 tokens to every session and 1,017 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 2026-08-30.
Other skills, from other repositories
Interceptor
Real Chrome/Brave + macOS Computer Use from inside the browser — zero CDP fingerprint, real sessions; mandatory for visual deploy verification. Drive clickwork yourself. USE WHEN verify deploy, confirm UI, screenshot verification, computer use, macos automation, debug web, troubleshoot, visual check, motion/animation…
Art
Static visual content across 20+ formats — diagrams, mermaid, infographics, D3 dashboards, comics, icons, wallpaper — via Nano Banana Pro (default), Nano Banana, and Flux. USE WHEN art, illustration, diagram, flowchart, infographic, header image, blog social thumbnail, visualize, generate image, mermaid, architecture…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
ISA
Owns the Ideal State Artifact — the primitive holding a project or task's articulated ideal state; scaffolds, interviews, grills a half-formed idea into shape via checkpointed discovery, scores completeness, reconciles feature excerpts to master, seeds from a repo, and appends decisions/changelog/verification across a…
Research
Multi-agent web research with mandatory URL verification, confidence-tagged output, and four depth modes (quick to deep investigation). USE WHEN research, do research, quick research, extensive research, deep investigation, find information, investigate, extract alpha, analyze content, retrieve content, AI trends…
Apify
Scrapes social platforms, business data, and e-commerce via Apify actors — Instagram, LinkedIn, TikTok, YouTube, Facebook, Google Maps, Amazon, and web crawls — filtering in code. USE WHEN scrape Instagram, scrape LinkedIn, scrape TikTok, scrape YouTube, scrape Facebook, Google Maps leads, Amazon reviews, business…