telegram-gateway-debug-loop

A testing and debugging workflow for a Telegram message gateway, using real conversations and detailed runtime logs.

In plain words
What is it for?
Use it to investigate stuck runs, failed deliveries, locks, scheduler issues, asynchronous behaviour, and multi-step tool workflows.
Why use it?
It helps reproduce message-delivery and scheduling problems while observing what the gateway is doing.

Skill for Claude CodeCodex

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 skills/z80dev/lemon/telegram-gateway-debug-loop
Any agent
npx skills add z80dev/lemon --skill telegram-gateway-debug-loop
Clone the repo
git clone --depth 1 https://github.com/z80dev/lemon

Made for: Claude Code, Codex.

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 680 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00076 $0.00680
Opus 5 $0.00038 $0.00340
Sonnet 5 $0.00015 $0.00136
Haiku 4.5 $0.00008 $0.00068

Measured 2d ago against content hash 604b32a8aa5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

telegram-gateway-debug-loop 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 2d 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/skills/telegram-gateway-debug-loop/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Telegram Gateway Debug Loop

Use this skill to run end-to-end repros with real Telegram traffic.

Setup

  1. Load Telegram credentials from ~/.zeebot/api_keys/telegram.txt.

    • Read the file to get api_id, api_hash, and phone number.
    • NEVER print, echo, or commit these values. Hold them in memory only.
  2. Start gateway with debug logging:

    cd /Users/z80/dev/lemon
    LOG_LEVEL=debug ./bin/lemon-gateway --debug --sname lemon_gateway_debug
    

    Run this in the background and monitor its output.

  3. Optionally attach a remote shell for live introspection:

    iex --sname lemon_attach --cookie lemon_gateway_dev_cookie --remsh lemon_gateway_debug@$(hostname -s)
    

Sending Messages via Telethon

  1. Use Telethon through uv (no global install needed):

    uv run --with telethon python <script.py>
    

    Write a temporary Python script that:

    • Connects with the user's Telegram credentials
    • Sends messages into a dedicated debug topic/thread
    • Keeps all probes in that thread
  2. Stress async behavior with prompts that trigger delegation/tool runs:

    • agent_id=coder delegation
    • Async poll loops
    • Multi-step tool workflows

Inspecting Runtime State

  1. While traffic is active, inspect runtime state via the remote shell:
    • :sys.get_state(LemonGateway.Scheduler) — scheduler state
    • :sys.get_state(LemonGateway.EngineLock) — lock state
    • DynamicSupervisor.which_children(LemonGateway.ThreadWorkerSupervisor) — active workers

Watching for Failures

  1. Watch gateway logs for high-value failure signatures:
    • :unknown_channel — message routed to unknown channel
    • Scheduler stalls or lock starvation
    • Context overflow/trim failures
    • Delivery retries/timeouts

Capturing Repros

  1. For each repro, capture:
    • The exact prompt(s) sent
    • Thread ID
    • Timestamps
    • State snapshots from the remote shell
    • Relevant log lines

If $ARGUMENTS is provided, focus the debug session on reproducing that specific issue.

Read the full file on GitHub · 79 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. 2d ago First seen · 79 lines · 76 tokens per session scan A 604b32a8aa5c

Subscribe to this mod's changes

telegram-gateway-debug-loop is a skill published in the GitHub repository z80dev/lemon (129 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 680 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens