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 tu11aa/squadrant --skill telegramgit clone --depth 1 https://github.com/tu11aa/squadrantWrote 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/tu11aa/squadrant/telegram)<a href="https://agentmods.dev/skills/tu11aa/squadrant/telegram"><img src="https://agentmods.dev/badge/skills/tu11aa/squadrant/telegram/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/tu11aa/squadrant/telegram"><img src="https://agentmods.dev/badge/skills/tu11aa/squadrant/telegram.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 | $0.00066 | $0.00805 |
| Opus 5.5 | $0.00026 | $0.00322 |
| Sonnet 5.5 | $0.00013 | $0.00161 |
| Haiku 4.5 | $0.00007 | $0.00081 |
Grade A, and why
telegram 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 2mo 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
squadrant:telegram — Telegram Integration
Squadrant pushes crew lifecycle events to Telegram forum topics and accepts commands back from your phone.
Setup
Run the wizard once (re-run at any time to reconfigure):
squadrant telegram setup
The wizard will:
- Detect an existing bot token and reuse it (or prompt for a new one).
- Wait for a message in your forum supergroup to detect the group id and your user-id.
- Ask whether to enable remote control — say yes to capture your user-id and enable Gate 2 (command execution).
After setup, the bot's /command menu is registered automatically.
Re-run setup if remoteControl ended up OFF (you said no, or it was skipped). Use --reset-token to rotate the bot token.
Two Gates
| Gate | What it checks | Controls |
|---|---|---|
| Gate 1 — chats allowlist | telegram.chats contains the chat id |
Inbound messages are processed |
| Gate 2 — remoteControl + user-id | remoteControl: true AND sender is in telegram.users |
Commands execute |
"⛔ not authorized" means Gate 2 is closed — re-run setup and say yes to remote control.
Reference: docs/diagrams/2026-06-23-telegram-daemon-architecture.html
Register the / Command Menu
Setup registers the menu automatically. To re-register on demand:
squadrant telegram register-commands
If the / autocomplete shows no commands in Telegram, run this command.
Notifications
Live toggle (ephemeral — resets on restart):
squadrant telegram notify <project> on
squadrant telegram notify <project> off
Persistent preferences (written to per-project config):
squadrant telegram notify <project> crew <all|alert_only|done_only|none>
squadrant telegram notify <project> cap <on|off>
squadrant telegram notify --status
Crew notification tiers (cumulative — each includes all below):
| Tier | What fires |
|---|---|
all |
Every crew event (started, blocked, done, failed) |
alert_only |
Blocked + done + failed (default) |
done_only |
Done + failed only |
none |
No crew notifications |
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.
- 2mo ago First seen · 95 lines · 66 tokens per session scan A d50f1af86488
telegram is a skill published in the GitHub repository tu11aa/squadrant (2 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 805 once invoked, about $0.0003 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.
telegram compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| telegramtu11aa/squadrant | Skill | 2 | yesterday | MIT | A | 66 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |