Repeat a prompt with /loop /loop 5m check if the deployment finished and tell me what happened 1. With an interval first, the prompt runs on that schedule. 2. Leave the interval out and Claude picks a delay each round. 3. A bare /loop runs a built-in maintenance prompt (unfinished work, the branch's pull request). 4. Esc cancels a self-paced loop while it waits. Gotcha: loops are tied to the session. They fire only…

Channel
On Claude: News & Hints
@on_claude
On this record: Growth · Engagement · What this channel posts · Posts · Citations · Cite this entry
7subscribers
+0 since we began measuring on 16 November 2026
Risers and fallers across the register · movement among entries of Under 1,000.
Register entry
| Telegram ID | -1003960541820 |
|---|---|
| Type | Channel |
| Username | @on_claude |
| Created | Between 1 April 2026 and 31 August 2026 — estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 16 November 2026 |
| Last confirmed live | 16 November 2026 |
| Measurements held | 2 |
| On Telegram | t.me/on_claude |
Growth
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 16 Nov 2026, 10:22 | 7 | no change |
| 16 Nov 2026, 09:47 | 7 | first reading |
Engagement
20 posts held, back to 29 October 2026 — the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 1 page of Telegram’s post history, 20 posts per page.
- ERR · 30 days
- 35.7%
- avg views ÷ 7 subscribers
- Avg views / post
- 2.5
- 20 posts measured
- Reaction rate
- —
- this channel exposes no reaction counts
- Posts in window
- 20
- of 20 held
ERR is average views per post over the last 30 days divided by subscribers, the definition TGStat uses, so this figure is comparable with the one you will see elsewhere. It falls structurally as a channel grows: a high ERR on a small channel and a low one on a large channel describe reach mathematics, not quality. We publish the figure and the sample it came from and pass no verdict on it.
ER is defined industry-wide as (forwards + reactions + comments) ÷ views — note the denominator is views, not subscribers. Telegram’s public web preview carries views and reactions but not forward or comment counts, so the reaction rate above is the reactions term only and is therefore a floor: the true ER for this channel is higher by an amount we have not measured and will not estimate.
| Window | Rolling 30 days · latest post in window 15 November 2026 |
|---|---|
| Posts held | 20 (29 October 2026 – 15 November 2026) |
| Views total | 50 |
| Reactions total | — |
| Forwards / comments | not exposed by the public surface — not measured, not estimated |
| Readings taken | 16 Nov 2026, 10:22 UTC |
Views are a single reading per post, taken at the time above. A post published in the last day or two is still accumulating views, which pulls the 30-day average down slightly. That is a property of the standard definition rather than a fault in it, so we keep the definition rather than “correcting” the number into something nobody can reproduce.
Precision. Telegram publishes view counts on its public widget in short form — 8.12K, 3.7M — so any reading at or above 1,000 reaches us rounded to three significant figures, and only counts below 1,000 are exact. Averages and rates derived from them are shown to the same precision rather than to the unit: a figure like 3,701,250 would assert digits nobody measured.
Reaction counts are published per emoji and rounded the same way, so a total below 1,000 is exact and a larger one is a sum that may carry a rounded component from each emoji above 1,000. Because it is a sum, it does not look rounded — read a large reaction total as three significant figures per contributing emoji rather than as the figure it prints.
What this channel posts
- Photos
- 38
- Links
- 42
Lifetime counters from Telegram’s own channel header, read 16 November 2026 — not the date at the top of this page, which is when the subscriber count was last read. Below Telegram’s rounding threshold, so these counts are exact.
Recent posts
Telegram’s own ‘edited’ marker: 0 of 20 posts held from the last 30 days (0%) carried it when this register last read them. The marker says a post was changed after publishing, not what it said before — this register holds the earlier wording only where an edit fell between two of its own reads (see the edit ledger and how it is measured).
Feature how-to: Claude Meetings (beta) Claude can join a Google Meet as a visible participant: it takes notes and builds live docs or whiteboards. 1. Open Meetings in Claude (claude.ai/meetings) and connect your Google Calendar. 2. Pick an upcoming meeting and click Add Claude. 3. In the call, say "Claude" plus your question, or type in the Meet chat. 4. Say "Claude, make a doc" (or whiteboard) and it builds live, …
Skill pick: mcp-builder From the anthropics/skills repo. It guides building an MCP server in four phases: research and plan, implement (TypeScript or Python), review and test, then write evaluation questions. Use: "Use the mcp-builder skill to build an MCP server for our internal API." Install (README): /plugin marketplace add anthropics/skills /plugin install example-skills@anthropic-agent-skills Caveats: the REA…
What shipped: Claude Fable 5.2 and Mythos 5.2 New model pair, same underlying model with different safeguards: Fable 5.2 (claude-fable-5-2) for every API customer; Mythos 5.2 (claude-mythos-5-2) for orgs verified under Anthropic's Cyber or Life Sciences programs. Specs: 1M token context, 128k max output, adaptive thinking always on via the effort parameter. Anthropic says outputs run up to 30% faster than 5.1; an o…
Talk: Anthropic's Applied AI team on how Claude Managed Agents is built Claude Managed Agents and Evolution of Agentic Surfaces — Gagan Bhat & Isabella Kai He, Anthropic by AI Engineer, 31 min, intermediate, for developers, free on YouTube The description argues that a harness encodes assumptions about what a model cannot do, and that these go stale as models improve, so the agent loop (the brain) is split from tool…
Ask a side question off the record /btw what was the name of that config file again? Claude answers from the conversation so far, in a dismissible overlay. The question and answer never enter the history, and it works while Claude is busy without interrupting the turn. Gotcha: /btw has no tools, so it cannot read files or run commands. If the question needs that, press f in the overlay to fork it into a background …
Feature how-to: Cowork's approval mode Every Cowork task has a mode selector in the chat box, right where you type: 1. Open the mode selector in the message box. 2. Manual — approve each action before Claude takes it (this replaced the old "Ask before acting"). 3. Auto — default on Pro, Max, Ultra and Team: routine actions go through without a prompt. 4. Skip — no approval prompts at all. 5. Switch modes mid-task a…
Write a skill description Claude can match Claude picks a skill by its description, which goes into the system prompt. Per the docs: 1. Write in third person: "Processes Excel files", not "I can help you process Excel files". 2. Say what it does and when to use it. 3. Include words users really say. description: Summarize a pull request diff as release notes. Use when the user asks for a changelog entry or what cha…
What shipped: Personal Finance in Claude (beta) Claude can now answer questions about your money using accounts you connect through Plaid — read-only, so it can't move money or give investment advice. Ask things like "what did I spend on groceries last month?" and get real numbers, spending charts, bill calendars or a quick dashboard. Rolling out this week on Pro, Max and Ultra plans in the US. Look for "Personal F…
Stash a half-written prompt You are halfway through a long prompt and need a quick answer first. Press Ctrl+S: the draft is stashed and the box clears. Send the quick question. Press Ctrl+S again on the empty prompt and the draft returns, with its cursor position, pasted content and input mode. A stashed ! shell command comes back in shell mode. Gotcha: don't confuse it with Ctrl+X Ctrl+S, which sends your queued m…
Connector pick: Asana Claude's Connectors Directory now includes Asana, listed under productivity tools next to Linear and Notion. Once connected, Claude gets 30+ tools to search, create and update tasks, projects and goals straight from the chat. One concrete use: ask "what's due today across my projects" for a live pull from Asana, or turn a conversation into a project by having Claude create the tasks, assign ow…
Walkthrough: choosing Claude Code plugins without overloading Claude The Only Claude Code Plugins You Actually Need by Tech With Tim, 22 min, intermediate, free on YouTube The description argues that once Claude sees more than about 50 tools at once, it starts picking the wrong ones, so the video shows only the plugins its author keeps installed. Chapters: 1:18 the plugin marketplace, 2:51 language servers, 5:06 Git…
Showing the 12 most recent of 20 posts we hold for @on_claude. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked ≈ was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.
Mentions
Named by 1 registered channel — every channel on the register whose own posts have named this one, by its current username or any other username it currently holds, merged from two separately captured readings of the same fact so a namer caught by only one of them is not missed and a namer both caught is not counted twice. A username this channel has since dropped is not matched — that handle may belong to someone else now, and crediting today’s namer to yesterday’s owner would misattribute it.
Named by
Channels on the register whose posts name this channel's handle.
A mention is a weaker signal than a forward and is counted separately for that reason — naming a channel is not republishing it, and a handle in a post body is easy to place deliberately. The post counts beside each row below are distinct posts in which the handle appeared, from posts we have read on both sides — the “Named by N registered channels” figure above is a different count, of distinct NAMING CHANNELS rather than posts, and is not the sum of the rows under it.
Cite this entry
A live page changes as we take new readings, so a citation should name the measurement it is based on, not just the URL. The line below cites the subscriber count as measured 16 November 2026 — this entry's latest reading, not the date you are reading this.
“On Claude: News & Hints” (@on_claude), 7 subscribers as measured 16 November 2026. Telegram Register, tgregister.com/channel/on_claude.
Full measurement history, CC BY 4.0. Every reading this register holds for this entry, not just the latest one, as a dated, downloadable record: CSV · JSON. Free to use with attribution to tgregister.com. Each file carries its own generation timestamp, which is the figure to cite for exactly when the data was retrieved.