tg-customer-support-plugin

Name: tg-customer-support-plugin
Author: igorrendulic

Verified

Local-first Telegram support agent for Codex and Claude. Index Telegram, docs, and repo evidence locally; draft replies; post only after operator confirmation.

1stars

0forks

Python

Installation

# Add to your Claude Code skills
git clone https://github.com/igorrendulic/tg-customer-support-plugin

Getting Started

Guides for using ai agents skills like tg-customer-support-plugin.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportVerified

Last scanned: 6/27/2026

{
  "issues": [],
  "status": "PASSED",
  "scannedAt": "2026-06-27T06:53:58.822Z",
  "npmAuditRan": true,
  "pipAuditRan": true,
  "promptInjectionRan": true
}

README.md

Frequently Asked Questions

What is tg-customer-support-plugin?

tg-customer-support-plugin is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by igorrendulic. Local-first Telegram support agent for Codex and Claude. Index Telegram, docs, and repo evidence locally; draft replies; post only after operator confirmation. It has 1 GitHub star.

Is tg-customer-support-plugin safe to use?

Yes. tg-customer-support-plugin passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install tg-customer-support-plugin?

Clone the repository with "git clone https://github.com/igorrendulic/tg-customer-support-plugin" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is tg-customer-support-plugin written in?

tg-customer-support-plugin is primarily written in Python. It is open-source under igorrendulic on GitHub, so you can review or fork the full source.

Are there alternatives to tg-customer-support-plugin?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh tg-customer-support-plugin against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

superpowers

by obra

An agentic skills framework & software development methodology that works.

234,966

tender-search voltron-lions-claudecode

Telegram Support Agent

A local-first support agent for founders and maintainers who answer users in Telegram.

It lets Codex or Claude search your Telegram support history, website/docs, manual support notes, and optional repo evidence. It can answer support analytics questions and draft evidence-backed replies, but it only posts to Telegram after explicit operator confirmation.

No hosted helpdesk. No SaaS support inbox. Telegram sessions, SQLite metadata, retrieval indexes, drafts, and confirmation records stay on your machine.

Demo

Search Telegram support history, local docs, and repo evidence. Draft a reply. Post only after explicit confirmation.

https://github.com/user-attachments/assets/

Who this is for

This is for people who already run support inside Telegram:

solo founders answering users directly
maintainers of developer tools
small SaaS teams without a hosted helpdesk
support engineers who need local searchable context
projects where support data should stay on the operator's machine

What it does

Syncs a configured Telegram support chat into a local profile.
Crawls website/blog/docs seeds for support knowledge.
Builds local hybrid search with SQLite FTS5 + sqlite-vec.
Uses local embeddings for semantic retrieval.
Searches live repository evidence for product/API/debugging questions.
Creates evidence-backed reply drafts.
Requires explicit confirmation before posting to Telegram.
Works from Codex, Claude, or the tg-support CLI.

Not a Telegram bot

This project is not designed to autonomously answer users.

It is an operator-assist workflow: the agent can search, summarize, and draft replies, but posting requires an explicit confirmation. This keeps the risky action — writing to Telegram — behind a deterministic local CLI boundary.

Install

For Codex, add the plugin marketplace and install the plugin:

codex plugin marketplace add igorrendulic/tg-customer-support-plugin
codex plugin add telegram-support-agent@tg-customer-support-plugin

Quickstart

After install, open Codex in the workspace where you want to use the support agent and ask it to use the telegram-support skill, for example:

Use the telegram-support skill to set up profile default for @my-support-chat with seed https://example.com.

The first time the workflow runs the bundled scripts/tg-support helper, it creates its own runtime environment, installs the Telegram, browser-rendering, and retrieval dependencies, and installs Chromium for Playwright. Retrieval uses SQLite FTS5, sqlite-vec, and local BAAI/bge-small-en-v1.5 embeddings. The first index build may need to download or load the BGE Small model through sentence-transformers; after that, search runs against the local profile index.

Then ask Codex to log in, sync Telegram history, crawl the configured seed, and build the local index:

Use the telegram-support skill to log in and build the local corpus for profile default.

Codex will first check profile readiness. If Telegram API credentials are missing, it will ask you for the API ID and API hash from https://my.telegram.org, store them under the local profile, and continue setup from there.

Once indexing finishes, ask normal support questions in Codex:

Use the telegram-support skill to find recent passkey setup issues.
Use the telegram-support skill to draft a reply for message 123.

To run the CLI directly outside Codex:

git clone https://github.com/igorrendulic/tg-customer-support-plugin.git
cd tg-customer-support-plugin
scripts/tg-support --help

By default, the auto-created environment lives under ~/.tg-support/.venv. Set TG_SUPPORT_VENV to put it somewhere else.

The package also exposes a tg-support console script inside that auto-created environment:

~/.tg-support/.venv/bin/tg-support --help

Development Install

For local development, clone the repo and install the package with dev and retrieval dependencies:

git clone <repo-url>
cd tg-support-plugin
python3 -m venv .venv
.venv/bin/pip install -e ".[retrieval,dev]"

Add Telegram and browser-rendering adapters when you need real Telegram login or Playwright crawling:

.venv/bin/pip install -e ".[telegram,render,retrieval,dev]"

Use

Create a local profile with one Telegram chat. Website or blog seeds are optional:

scripts/tg-support --profile default setup \
  --chat my-support-chat

Optionally add website or blog seeds for public support resources:

scripts/tg-support --profile default setup \
  --chat my-support-chat \
  --seed https://example.com/blog

Optionally add one or more operator identities so Support Exchanges can distinguish configured support answers from peer/community replies:

scripts/tg-support --profile default setup \
  --chat my-support-chat \
  --operator igormailio \
  --operator Igor

Optionally add a GitHub repository and branch for code-grounded behavior or debugging answers. The branch defaults to main when omitted. This uses your existing local git or gh authentication; do not paste GitHub credentials into the support workflow.

scripts/tg-support --profile default setup \
  --chat my-support-chat \
  --seed https://example.com/blog \
  --repository owner/project

Then build the local corpus:

scripts/tg-support --profile default credentials --api-id 123456
scripts/tg-support --profile default login
scripts/tg-support --profile default sync
scripts/tg-support --profile default crawl
scripts/tg-support --profile default index
scripts/tg-support --profile default status

crawl follows same-scope links two levels deep by default. Use --depth 0 to crawl only configured seed URLs.

index creates source-linked documents, Support Exchanges, an FTS5 exact-term index, and a 384-dimensional sqlite-vec vector index for BAAI/bge-small-en-v1.5. Support Exchanges separate requester text, configured operator replies, peer/community replies, and unanswered questions so adjacent chat messages are not treated as one author's document. If the retrieval dependencies, embedding model, or local SQLite extension loading are not available, the command returns JSON with ok: false, the SQLite version when relevant, and next_action instead of silently falling back to weaker search.

Ask questions or prepare a reply draft:

scripts/tg-support --profile default search "password reset issues"
scripts/tg-support --profile default repo-evidence "account transfer api"
scripts/tg-support --profile default stats active-users
scripts/tg-support --profile default draft-context --user alice
scripts/tg-support --profile default draft-create --message-id 123 --text "Thanks, try the reset link here..."

Repository Evidence is live and branch-specific rather than indexed. Use it for product-behavior, capability, API-behavior, or debugging questions. If the checkout cannot refresh, the CLI returns a stale warning so the agent can tell the operator that cited code may be outdated.

draft-context returns evidence sufficiency metadata with the evidence bundle. When evidence supports a direct answer, the agent should draft the direct reply. When evidence is missing, weak, conflicting, or needs private/account-specific details, the agent should offer both a cautious evidence-limited answer and a DM follow-up asking for the missing information. DM follow-up wording is not Manual Knowledge and is not evidence.

When evidence includes a Support Exchange, configured operator replies can support direct answers. Peer/community replies and unanswered exchanges are context unless corroborated by Manual Knowledge, Repository Evidence, web evidence, or another authoritative source.

Save dated support knowledge through Codex after reviewing the parsed fields, or directly through the CLI after the operator has confirmed the note:

scripts/tg-support --profile default knowledge-add \
  --text "Account transfers were discontinued. Users must register a new email address." \
  --effective-date 2026-04-02 \
  --caveats "Old email addresses are quarantined until further notice."
scripts/tg-support --profile default index

Active manual knowledge can appear in search or draft evidence ahead of older Telegram and web sources. If returned JSON includes conflicts, show the manual note and the competing evidence to the operator before answering or drafting.

Posting is intentionally a separate confirmed action. Show the operator the exact draft, target, and evidence first, then use the generated post or cancel token:

scripts/tg-support --profile default confirm <post_or_cancel_token>

Local profile data lives outside the source tree by default:

~/.tg-support/profiles/<profile>/

That profile directory contains the profile config, optional repository checkout state, Telegram API credentials, Telegram session file, SQLite database, and rebuildable indexes. Treat it as sensitive local state.

Set TG_SUPPORT_HOME to move profile data elsewhere.

Existing local profiles created with an older embedding model must be recreated or edited before use. The CLI intentionally rejects unsupported embedding_model values instead of mixing incompatible vector dimensions in the same profile.

Architecture

flowchart LR
    TG[Telegram Support Chat] --> SYNC[tg-support sync]
    WEB[Website / Blog / Docs] --> CRAWL[tg-support crawl]
    NOTES