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 k1p1l0/claude-telegram-supercharged --skill daemongit clone --depth 1 https://github.com/k1p1l0/claude-telegram-superchargedWrote 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/k1p1l0/claude-telegram-supercharged/daemon)<a href="https://agentmods.dev/skills/k1p1l0/claude-telegram-supercharged/daemon"><img src="https://agentmods.dev/badge/skills/k1p1l0/claude-telegram-supercharged/daemon/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/k1p1l0/claude-telegram-supercharged/daemon"><img src="https://agentmods.dev/badge/skills/k1p1l0/claude-telegram-supercharged/daemon.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 | $0.00055 | $0.00692 |
| Opus 5 | $0.00028 | $0.00346 |
| Sonnet 5 | $0.00011 | $0.00138 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade B, and why
daemon scanned grade B with 1 finding 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 10d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
tail -30 ~/.claude/channels/telegram/data/supervisor-stderr.log How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/telegram:daemon — Telegram Daemon Lifecycle Manager
Full lifecycle management for the Telegram bot daemon (launchd + supervisor + Claude).
Arguments — dispatch on first word
start (default if no args and daemon is not running)
Start the daemon via launchd:
launchctl load ~/Library/LaunchAgents/com.user.claude-telegram.plist 2>&1
If it fails with "already loaded", report that the daemon is already running. After loading, wait 5 seconds, then run the status check to confirm it started.
stop
Stop the daemon:
launchctl unload ~/Library/LaunchAgents/com.user.claude-telegram.plist 2>&1
Wait 3 seconds, verify all processes are gone:
ps aux | grep -E "channels.*telegram" | grep -v grep
Report success or if orphan processes remain.
restart
Unload then load:
launchctl unload ~/Library/LaunchAgents/com.user.claude-telegram.plist 2>/dev/null
sleep 2
launchctl load ~/Library/LaunchAgents/com.user.claude-telegram.plist
Wait 10 seconds, then run full status check.
status (default if no args and daemon IS running)
Run the full monitor check — same as /telegram:monitor:
- Process status (supervisor, expect, claude, MCP server, caffeinate)
- Launchd loaded/not
- Remote control URL
- Lock file
- Last 5 log lines
logs
Tail the last 30 lines of supervisor stderr:
tail -30 ~/.claude/channels/telegram/data/supervisor-stderr.log
stdout
Tail the last 30 lines of daemon's Claude output:
tail -30 ~/.claude/channels/telegram/data/supervisor-stdout.log
url
Just show the remote control URL:
cat ~/.claude/channels/telegram/data/supervisor-stdout.log | strings | grep "session_" | tail -1
No args
Check if daemon is running. If running → show status. If not running → ask if user wants to start it.
Important notes
- The
launchctl load/unloadcommands may fail with "Input/output error" — this usually means the service is already in the requested state. Handle gracefully. - After start/restart, always verify the daemon actually started by checking processes.
- The plist path is always:
~/Library/LaunchAgents/com.user.claude-telegram.plist - Show the remote control URL after every start/restart so the user can monitor.
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.
- 10d ago First seen · 105 lines · 55 tokens per session scan B 8c59abe0a2d5
daemon is a skill published in the GitHub repository k1p1l0/claude-telegram-supercharged (113 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 692 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
authentication-patterns
OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.
case-interview-practice
Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.
i18n-localization
Internationalization and localization for global applications. Use when adding multi-language support, handling regional formats, or preparing apps for global markets.
research-archival
Scrape AI research URLs, archive with frontmatter, create GitHub Issues with identity verification.
cloudflare-workers-publish
Deploy static HTML files to Cloudflare Workers with 1Password credential management.