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 contextgit 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/context)<a href="https://agentmods.dev/skills/k1p1l0/claude-telegram-supercharged/context"><img src="https://agentmods.dev/badge/skills/k1p1l0/claude-telegram-supercharged/context/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/context"><img src="https://agentmods.dev/badge/skills/k1p1l0/claude-telegram-supercharged/context.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 | $0.00770 |
| Opus 5 | $0.00028 | $0.00385 |
| Sonnet 5 | $0.00011 | $0.00154 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade B, and why
context scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
BOT_TOKEN=$(grep TELEGRAM_BOT_TOKEN "$HOME/.claude/channels/telegram/.env" 2>/dev/null | cut -d= -f2 | tr -d '"' | tr -d "'") Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST "https://api.telegram.org/bot${BOT_TOKEN}/sendMessage" \ How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Transfer to Telegram Bot
Transfer the current conversation context to the Telegram bot session so it can continue the work.
Process
Step 1: Gather context
Summarize the current conversation into a structured context handoff. Include:
- What we were working on — the main task/topic
- Key decisions made — important choices, approaches taken
- Current state — what's done, what's pending
- Files changed — any relevant file paths
- Action items — what the Telegram bot should do next (if any)
Keep it concise — under 2000 characters. The bot has limited context.
Step 2: Write to bot memory
Append the context to the bot's memory file so it persists across restarts:
MEMORY_FILE="$HOME/.claude/channels/telegram/data/memory.md"
Append a new section with timestamp:
## YYYY-MM-DD HH:MM — Context Transfer
**Chat 305120844**: [summary here]
IMPORTANT: Do not overwrite the file — APPEND to it. Read existing content first, then write old + new.
Step 3: Send as Telegram message
Send the context as a direct message to the user's Telegram chat so the bot sees it immediately in the current session:
BOT_TOKEN=$(grep TELEGRAM_BOT_TOKEN "$HOME/.claude/channels/telegram/.env" 2>/dev/null | cut -d= -f2 | tr -d '"' | tr -d "'")
# If not in .env, check environment
if [ -z "$BOT_TOKEN" ]; then
BOT_TOKEN="$TELEGRAM_BOT_TOKEN"
fi
CHAT_ID="305120844"
curl -s -X POST "https://api.telegram.org/bot${BOT_TOKEN}/sendMessage" \
-H "Content-Type: application/json" \
-d "{
\"chat_id\": \"${CHAT_ID}\",
\"text\": \"📋 *Context transfer from CLI session*\n\n${CONTEXT_TEXT}\",
\"parse_mode\": \"Markdown\"
}"
Step 4: Confirm
Tell the user:
Context transferred to Telegram bot:
✓ Written to memory (persists across restarts)
✓ Sent as message (bot sees it now)
Switch to Telegram and continue the conversation there.
Context Format Template
Use this format for the transferred context:
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 · 104 lines · 55 tokens per session scan B 79beee05de7b
context 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 770 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
handoff
Emit a paste-ready two-part handoff for a fresh session: a ## Goal statement hard-capped under 4000 characters (produced by the /goal skill), plus an unbounded ## Full prompt carrying cwd, ordered reading list, hard rules, pitfalls, and deliverables. Runs with or without a git repository — branch and PR facts are…
knowledge-graph
Local code knowledge-graph + cache (no MCP, no network) — index a repo and retrieve ranked file:line for a topic instead of grepping whole files; show graph/cache status; blast-radius / dependents of a file; refresh or reset. Use for "knowledge graph status", "index this repo", "what depends on ", "find the code for ".
chronicle
Memory & context steward — session-learning history, the global reference store (repos/projects/ideas), AND live context management (size status, post-compaction resume capsule, project learnings, promotion). Use to review past sessions, remember/recall/forget a reference, check context size, resume after compaction…
fable-context-thrift
Use at the start of any multi-step task and during exploration — before reading files, searching, or re-checking completed work, especially when tempted to read whole files, re-verify known facts, or run independent lookups one at a time.
session-logs
Search, browse, and analyze session history to recall past conversations, decisions, and completed work.
memory-manager
Store, recall, and organize persistent context, preferences, and knowledge across sessions.