Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/k1p1l0/claude-telegram-superchargednpx agentmods add skills/k1p1l0/claude-telegram-supercharged/updateWrote 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/update)<a href="https://agentmods.dev/skills/k1p1l0/claude-telegram-supercharged/update"><img src="https://agentmods.dev/badge/skills/k1p1l0/claude-telegram-supercharged/update/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/update"><img src="https://agentmods.dev/badge/skills/k1p1l0/claude-telegram-supercharged/update.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 | $0.00048 | $0.00762 |
| Opus 5.5 | $0.00019 | $0.00305 |
| Sonnet 5.5 | $0.00010 | $0.00152 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade B, and why
update scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/cache/telegram-update-check.json 2>/dev/null || echo '{"update_available":"unknown"}' How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Telegram Supercharged Plugin
Pull the latest version from GitHub and apply it to the installed plugin.
Process
Step 1: Check current state
# Get local file hash (Claude Code runs the newest version directory in the cache)
CACHE="$HOME/.claude/plugins/cache/claude-plugins-official/telegram"
LOCAL_FILE="$CACHE/$(ls "$CACHE" | sort -V | tail -1)/server.ts"
LOCAL_HASH=$(shasum -a 256 "$LOCAL_FILE" 2>/dev/null | cut -c1-12)
echo "Local hash: $LOCAL_HASH"
Step 2: Check for updates
# Read cache if available
cat ~/.claude/cache/telegram-update-check.json 2>/dev/null || echo '{"update_available":"unknown"}'
Step 3: Pull latest from GitHub
If update is available (or unknown), pull the latest:
cd /tmp
if [ -d "claude-telegram-supercharged" ]; then
cd claude-telegram-supercharged && git pull
else
git clone https://github.com/k1p1l0/claude-telegram-supercharged.git
cd claude-telegram-supercharged
fi
Step 4: Compare versions
REMOTE_HASH=$(shasum -a 256 /tmp/claude-telegram-supercharged/server.ts 2>/dev/null | cut -c1-12)
echo "Remote hash: $REMOTE_HASH"
echo "Local hash: $LOCAL_HASH"
If hashes match, report "Already up to date" and exit.
Step 5: Show what changed
cd /tmp/claude-telegram-supercharged && git log --oneline -10
Show the user the recent commits and ask for confirmation before updating.
Step 6: Apply update
After user confirms, run the installer from the checkout. It copies server.ts and the skills into the cache directory Claude Code actually runs, keeps the official package.json (its start script keeps bun install output off the MCP channel), and installs the supervisor, the daemon wrapper and the Agentic Mode hook:
TELEGRAM_SUPERCHARGED_DIR=/tmp/claude-telegram-supercharged bash /tmp/claude-telegram-supercharged/install.sh
Then restart: a new Claude Code session, or for the daemon launchctl bootout + launchctl bootstrap (a soft restart doesn't reload the supervisor).
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.
- 1mo ago Changed · -12 lines 4c0b92991d87
- 1mo ago First seen · 110 lines · 48 tokens per session scan B 4f8cd3758b07
update is a skill published in the GitHub repository k1p1l0/claude-telegram-supercharged (138 stars, last pushed 2d ago), licensed Apache-2.0. It adds 48 tokens to every session and 762 once invoked, about $0.0002 per session on Opus 5.5. 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
make-plugin
Research marketplace gaps, generate 10 Claude plugins with monetization, and submit them. Use when the user says "make plugin" or wants to create and publish Claude plugins.
api-test
Skill "api-test" from barnburner121/claude-plugin-marketplace, covering api-test, description, when to use, tools and apigeneratetests.
api-doc
Generate OpenAPI/Swagger specs from route handlers.
arch-docs
Generate architecture documentation with diagrams.
async-audit
Detect async/await anti-patterns and race conditions.
auth
Generate authentication flows (JWT, OAuth2, session-based).