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 jerpint/woltspace --skill notifygit clone --depth 1 https://github.com/jerpint/woltspaceWrote 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/jerpint/woltspace/notify)<a href="https://agentmods.dev/skills/jerpint/woltspace/notify"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/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/jerpint/woltspace/notify"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/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 | $0.00019 | $0.00942 |
| Opus 5 | $0.00010 | $0.00471 |
| Sonnet 5 | $0.00004 | $0.00188 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade A, and why
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 2d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notify — Push Messages to the User
Sessions can send messages back to the user at any time. Use this when you finish something worth reporting, hit a blocker that needs input, or find something the user should know about mid-task.
Usage
# Default — auto-routes via session registry, falls back to Telegram
notify <<'WOLTSPACE_NOTIFY_7F3A91C2'
your message here
WOLTSPACE_NOTIFY_7F3A91C2
# Explicit Slack — send to a specific Slack channel + thread
notify --slack CHANNEL THREAD_TS <<'WOLTSPACE_NOTIFY_4D8E20B1'
your message here
WOLTSPACE_NOTIFY_4D8E20B1
# Explicit Telegram — send to a specific Telegram chat
notify --telegram CHAT_ID <<'WOLTSPACE_NOTIFY_A6C195E4'
your message here
WOLTSPACE_NOTIFY_A6C195E4
Use a fresh random suffix in the delimiter for every message, and quote the
opening delimiter exactly as shown. Put the closing delimiter on a line by
itself. Never paste the bare closing delimiter on its own line into the message
body, because that would end the heredoc early. A single-quoted heredoc passes
its body literally: the shell does not expand backticks, $(), variables,
quotes, or other metacharacters.
notify accepts no message argument. This keeps message text out of the shell
command itself on every harness.
Explicit routing
When your session receives a message from Slack or Telegram, the prepended context includes the routing info you need:
[slack message from human, channel=C0123ABC, thread=1711234567.890123]: hey do the thing
Reply by replacing YOUR_REPLY in this exact single-quoted heredoc, then run it:
notify --slack C0123ABC 1711234567.890123 <<'WOLTSPACE_NOTIFY_4D8E20B1'
YOUR_REPLY
WOLTSPACE_NOTIFY_4D8E20B1
[telegram message from human, chat_id=98765432]: hey do the thing
Reply by replacing YOUR_REPLY in this exact single-quoted heredoc, then run it:
notify --telegram 98765432 <<'WOLTSPACE_NOTIFY_A6C195E4'
YOUR_REPLY
WOLTSPACE_NOTIFY_A6C195E4
Use the exact heredoc from the prepended context and replace only YOUR_REPLY.
Woltspace generates a fresh delimiter every time. This ensures the message stays
literal and goes to the specific Slack thread or Telegram chat it came from;
you do not need to load this skill merely to reply.
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.
- 2d ago Changed · +33 lines eb6a8a76c603
- 6d ago First seen · 67 lines · 19 tokens per session scan A 5e7fd15979f4
notify is a skill published in the GitHub repository jerpint/woltspace (12 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 942 once invoked, about $0.0001 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 2026-09-09.
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…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
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…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.