tg-cli-bridge CLAUDE.md

tg-cli-bridge CLAUDE.md is an instructions file for coding agents from jaxhemopo/tg-cli-bridge. It costs 836 tokens per session, scanned A, original, MIT.

Project instructions for tg-cli-bridge, a Go program that connects Telegram messages to agent command-line tools. They describe how to build, test, configure, run, and install it on macOS.

In plain words
What is it for?
Working on the Telegram bridge, its command-line process handling, output formatting, configuration, and macOS background-service setup.
Why use it?
They give an agent the repository's operating rules and architecture before it changes or debugs the code.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/jaxhemopo/tg-cli-bridge/claude-md
Clone the repo
git clone --depth 1 https://github.com/jaxhemopo/tg-cli-bridge

Wrote 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.

agentmods badge for tg-cli-bridge CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jaxhemopo/tg-cli-bridge/claude-md.svg)](https://agentmods.dev/instructions/jaxhemopo/tg-cli-bridge/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jaxhemopo/tg-cli-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/jaxhemopo/tg-cli-bridge/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 836 This file is loaded in full into every session.
When invoked 836 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00836 $0.00836
Opus 5 $0.00418 $0.00418
Sonnet 5 $0.00167 $0.00167
Haiku 4.5 $0.00084 $0.00084

Measured 5d ago against content hash 42f4d5a83921, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

tg-cli-bridge CLAUDE.md 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 5d 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.

CLAUDE.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tg-cli-bridge

Go binary that bridges a Telegram bot to an agentic CLI (Gemini CLI, AGY/Antigravity, Claude Code, plain shell, etc.).

Build

go build -o tg-cli-bridge ./cmd/tg-cli-bridge
go test ./...
go vet ./...

Install & run (macOS)

tg-cli-bridge init          # interactive config wizard
tg-cli-bridge run           # foreground test
tg-cli-bridge install       # register LaunchAgent + start

Key files

Path What it does
cmd/tg-cli-bridge/main.go CLI entrypoint, all subcommands
internal/bridge/bridge.go Core loop: receives Telegram updates, runs agent, sends reply
internal/rpc/rpc.go Spawns the CLI process, captures stdout, streams progress
internal/output/output.go ANSI stripping, prose/code classification, menu detection, DiffSince
internal/config/config.go TOML load/validate, KnownPresets, UpdateCLI
internal/launchd/launchd.go macOS LaunchAgent install/uninstall/status

Architecture — RPC mode

Each Telegram message spawns the agent CLI once as a subprocess:

Telegram message
  → bridge receives it
  → posts ⏳ status bubble
  → rpc.Run: exec CLI with --prompt "text" [--resume latest]
  → streams stdout; edits bubble in-place as keywords are detected
  → CLI exits
  → delete status bubble
  → send prose-only reply to Telegram

No persistent process. The CLI starts fresh each turn and exits. Session continuity comes from the CLI's own --resume / --continue flag (Gemini and AGY both support this).

Design decisions

  • One spawn per message — avoids tmux pane-watching and Telegram rate-limit hammering from constant redraws.
  • Prose-only outputoutput.FormatForTelegram classifies lines as prose vs code/tool-call banners. Only prose reaches Telegram so tool-call boxes don't pollute the chat.
  • Status bubble — single ⏳ message edits in-place as agent stdout reveals what it's doing (email, drive, shell, etc.). Deleted before the real reply lands so the chat stays clean.
  • DiffSince — some CLIs (AGY --continue) reprint the entire conversation history on every invocation. DiffSince(prev, curr) extracts only the new content.
  • KnownPresets in config.go — maps short names (gemini, agy, claude) to the right flags. Powers both the init wizard and the /switch Telegram command.

Read the full file on GitHub · 76 lines

Changes

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.

  1. 5d ago First seen · 76 lines · 836 tokens per session scan A 42f4d5a83921

Subscribe to this mod's changes

tg-cli-bridge CLAUDE.md is an instructions file published in the GitHub repository jaxhemopo/tg-cli-bridge (1 stars, last pushed 3mo ago), licensed MIT. It adds 836 tokens to every session, about $0.0042 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 2026-08-31.

Related

Other instructions, from other repositories

kmux AGENTS.md

AGENTS.md instructions for kkd927/kmux, covering agents.md, kmux focus and test discipline.

kkd927/kmux · 324 tokens

agent-exporter AGENTS.md

Instructions for ihatenodejs/agent-exporter, covering development commands, example: bun run dev sync --provider opencode, creates compiled binary at dist/agent-exporter, then use: agent-exporter and architecture.

ihatenodejs/agent-exporter · 1,750 tokens

agent-exporter CLAUDE.md

Instructions for ihatenodejs/agent-exporter, a project described as: Export usage statistics from various harnesses.

ihatenodejs/agent-exporter · 5 tokens

sessionview AGENTS.md

AGENTS.md instructions for tyql688/sessionview, covering sessionview, commands, app / frontend, gates must pass under both feature sets: default (gui) and and --no-default-features --features headless.

tyql688/sessionview · 2,157 tokens

gemini-cli-desktop AGENTS.md

Instructions for Piebald-AI/gemini-cli-desktop, a project described as: Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.

Piebald-AI/gemini-cli-desktop · 6 tokens

cc-use-exp general.instructions.md

Instructions for doccker/cc-use-exp, a project described as: ⛔ No longer maintained → dev-agent-kit/recipes 让 Claude Code、Antigravity、Gemini CLI、Codex、Cursor 开箱即用的分层配置模板,总结十多年的日常开发经验.

doccker/cc-use-exp · 163 tokens