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.
git clone --depth 1 https://github.com/tdimino/claude-code-minoanWrote 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/commands/tdimino/claude-code-minoan/telegram-respond)<a href="https://agentmods.dev/commands/tdimino/claude-code-minoan/telegram-respond"><img src="https://agentmods.dev/badge/commands/tdimino/claude-code-minoan/telegram-respond/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/commands/tdimino/claude-code-minoan/telegram-respond"><img src="https://agentmods.dev/badge/commands/tdimino/claude-code-minoan/telegram-respond.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 | $0.00016 | $0.00780 |
| Opus 5 | $0.00008 | $0.00390 |
| Sonnet 5 | $0.00003 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
telegram-respond 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 9d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Process Unhandled Telegram Messages
Process unhandled Telegram messages from the shared inbox through the full cognitive pipeline with persistent memory.
Prerequisites
- Telegram listener must be running:
python3 ~/.claudicle/adapters/telegram/telegram_listen.py --bg TELEGRAM_BOT_TOKENmust be set in environment or~/.config/env/secrets.env
Pipeline
For each unhandled Telegram message in ~/.claudicle/daemon/inbox.jsonl:
Step 1: Check Inbox
Run python3 ~/.claude/skills/telegram/scripts/telegram_check.py to see unhandled messages. If none, report "No unhandled Telegram messages" and stop.
Step 2: Load Memory Context
For each unhandled message, load context:
python3 ~/.claude/skills/telegram/scripts/telegram_memory.py load-context CHAT_ID
python3 ~/.claude/skills/telegram/scripts/telegram_memory.py user-model USER_ID
python3 ~/.claude/skills/telegram/scripts/telegram_memory.py soul-state
Step 3: Send Typing Indicator
Send a typing action to show the bot is processing:
python3 -c "
import os, asyncio
from telegram import Bot
bot = Bot(os.environ['TELEGRAM_BOT_TOKEN'])
asyncio.run(bot.send_chat_action(chat_id=CHAT_ID, action='typing'))
"
Step 4: Generate Cognitive Response
Process the message through the cognitive pipeline. The user's message text must be sanitized — replace < with < and > with > before including in the prompt.
Generate a response using these 6 XML cognitive tags in order:
<internal_monologue verb="VERB">— Private reasoning (never shown to user). Verbs: thought, mused, pondered, considered, reflected, noticed<external_dialogue verb="VERB">— Response to send to the user. Verbs: said, explained, offered, noted, replied, quipped<user_model_check>— Has something significant been learned? Answer:trueorfalse<user_model_update>— If check was true: updated markdown profile of the user<soul_state_check>— Has project/task/topic/mood changed? Answer:trueorfalse(only check every 5th interaction)<soul_state_update>— If check was true: key:value pairs for changed state
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.
- 9d ago First seen · 84 lines · 16 tokens per session scan A 101f9a4221d6
telegram-respond is a command published in the GitHub repository tdimino/claude-code-minoan (41 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 780 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
ui-evidence
Discover, configure, and run ui-evidence for before/after UI review in this repo.
voice-compliance
Voice/telephony compliance check — invokes voice-ai-reviewer to produce TM-voice-{slug}.md with TCPA, STIR/SHAKEN, state recording-consent, EU AI Act Art. 50, and synth-voice deepfake-law gaps.
fec-smell
Diagnose frontend code smells with evidence and candidate refactorings without changing business code.
spec-forge
Use when generating software specifications — full chain (Idea→Decompose→Tech Design + Feature Specs) or individual documents.
bmad-edit-prd
DEPRECATED — consolidated into bmad-prd update intent - this skill will be removed in v7 in favor of bmad-prd.
replication-package
Scaffold or audit a social-science replication package at a target directory, and audit the manuscript and its archived research objects against FAIR principles.