add-telegram
Skill0 starsChanged 6 months agoMITView on GitHub
Add Telegram as a channel to COS (Chief of Staff). Uses curl + Bash against the Telegram Bot API — no npm, no daemon, no Grammy.
- Reads credentials
16 other projects use a version of this.
Adopted by
Most recently taken up by
- nanocoai/nanoclawtheir own version, first seen Nov 15, 2026
- ss2code/nanoclaw-opstheir own version, first seen Oct 15, 2026
- prathish-ks/isthmustheir own version, first seen Oct 12, 2026
- juancruzmunozalbelo/swarmclawtheir own version, first seen Oct 8, 2026
- gavrielc/nanoclawtheir own version, first seen Oct 8, 2026
- qwibitai/nanoclawtheir own version, first seen Oct 8, 2026
Used with
Projects with it also use add-anydoc, add-clidash and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
TomGranotSkilladd-anydoc
Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when agents need to read attached Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or text-based PDF files without uploading them to a hosted parser.
Also in 5 projects that use this
TomGranotSkilladd-clidash
Add clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON. Ships pre-wired for NanoClaw's ncl CLI (agent groups, sessions, channels, users, roles), plus message-activity charts, a log tail, and a read-only file viewer for group skills/CLAUDE.md/profiles.
Also in 5 projects that use this
juancruzmunozalbeloSkilladd-voice-transcription
Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.
Also in 5 projects that use this
b1rdmaniaSkillmigrate-memory
Migrate from monolith CLAUDE.md to the three-file memory system (identity + state + log). Non-destructive — backs up the original first.
Also in 7 projects that use this
juancruzmunozalbeloSkilladd-telegram-swarm
Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".
Also in 6 projects that use this
qwibitaiSkilladd-iron-proxy
Install or refresh Iron Proxy and its official Iron Control web console for NanoClaw. Use when selecting the Iron gateway, adding its management UI, configuring credentials and grants, or restoring the proxy, approval bridge, and agent guidance.
Also in 4 projects that use this
- +5 more from TomGranot
Other versions16 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 16
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- Runchuan-BU/BioClaw★ 405same name
- DingyangLyu/MatClaw★ 98same name
- b1rdmania/ghostclaw★ 91same name
- microsoft/amplifier-app-nanoclaw★ 5same name
- 0-CYBERDYNE-SYSTEMS-0/FFT_nano★ 4same name
- TomGranot/groupguard★ 3same name
- prathish-ks/isthmus★ 2same name
6 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- claude.mdCLAUDE.md
- add-draftsSkill
- add-gmailSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 4 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 16 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Look for scripts/telegram.sh in the vault root and Step 0.5b in CLAUDE.md.
- Distinctive: line 22
If they don't have one:
- Distinctive: line 30
Wait for the user to provide the token before continuing.
- Distinctive: line 34
Run the skill setup:
- Very specific: line 42
Write them to .env (gitignored)
- Distinctive: line 49
If you didn't provide your chat ID during setup:
- Very specific: line 88
Run /ingest. If you sent yourself messages via the bot before this step, they should appear as inbox/tg-*.md files and get processed …
- Very specific: line 111
Check that TELEGRAM_BOT_TOKEN is exported in your shell:
- Very specific: line 126
Delete context/telegram-state.json and recreate it:
“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Add Telegram Channel (COS)
COS is a pure Markdown vault with no app server. This skill adds Telegram support via a simple Bash script (scripts/telegram.sh) that polls for messages during ingest and can send the morning briefing.
Phase 1: Pre-flight
Check if already applied
Look for scripts/telegram.sh in the vault root and Step 0.5b in CLAUDE.md. If both exist, skip to Phase 3 (configuration).
Check for bot token
Ask the user:
Do you have a Telegram bot token, or do you need to create one?
If they don't have one:
- Open Telegram and search for
@BotFather- Send
/newbotand follow the prompts:
- Bot name: Something friendly (e.g., "COS Bot")
- Bot username: Must end in "bot" (e.g., "mycos_bot")
- Copy the token it gives you (looks like
123456:ABC-DEF1234ghIkl-zyx57W2v1u123ew11)
Wait for the user to provide the token before continuing.
Phase 2: Apply
Run the skill setup:
bash .claude/skills/add-telegram/setup.shThis will:
- Collect
TELEGRAM_BOT_TOKENandTELEGRAM_CHAT_ID - Write them to
.env(gitignored) - Copy
scripts/telegram.shto the vault - Initialize
context/telegram-state.json - Patch
CLAUDE.mdwith ingest Step 0.5b and sweep Step 9 (outbound send)
Phase 3: Get your Chat ID
If you didn't provide your chat ID during setup:
# Set token from .env or provide directly
TELEGRAM_BOT_TOKEN=<your-token> bash scripts/telegram.sh getmeThis will print your chat ID. Add it to .env:
TELEGRAM_CHAT_ID=<your-id>Alternatively, manually find it:
- Search for your bot in Telegram and send it any message
- Run:
curl -s "https://api.telegram.org/bot<YOUR_TOKEN>/getUpdates" | python3 -m json.tool- Look for
"chat": {"id": <number>}— that number is your chat ID
Phase 4: Verify
Test poll
bash scripts/telegram.sh poll .Expected: prints "Fetched N updates" (0 is fine if no new messages).
Test send
bash scripts/telegram.sh send "COS Telegram integration working"Expected: message appears in your Telegram chat with the bot.
Run ingest
Run /ingest. If you sent yourself messages via the bot before this step, they should appear as inbox/tg-*.md files and get processed normally.
Troubleshooting
"command not found: bash scripts/telegram.sh"
The script wasn't copied. Re-run setup.sh or manually copy:
cp .claude/skills/add-telegram/add/scripts/telegram.sh scripts/telegram.sh
chmod +x scripts/telegram.shcurl returns 401
Token is wrong or expired. Verify with:
curl -s "https://api.telegram.org/bot<TOKEN>/getMe"No messages appear in inbox
Check that TELEGRAM_BOT_TOKEN is exported in your shell:
set -a && source .env && set +a
bash scripts/telegram.sh poll .Then run /ingest to process.
Messages appear but aren't processed
The tg-*.md files land in inbox/. Run /ingest manually to process them.
Offset stuck / replaying old messages
Delete context/telegram-state.json and recreate it:
echo '{"offset": 0}' > context/telegram-state.json
bash scripts/telegram.sh poll . skipDoes it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

