What is discord-troubleshooting?

A troubleshooting guide for getting a Gemini Discord bot connected and running. It covers Discord settings, bot tokens, gateway errors, and local port conflicts.

Use it to inspect daemon logs, diagnose Discord gateway close codes such as invalid tokens or disabled permissions, resolve port conflicts, and verify the bot connection.

It helps identify why the bot cannot connect instead of relying on trial and error. It also checks whether the bot is actually online after changes.

discord-troubleshooting — Skill by Yamato-main/gemini-discord

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.

Any agent

npx skills add Yamato-main/gemini-discord --skill discord-troubleshooting

Clone the repo

git clone --depth 1 https://github.com/Yamato-main/gemini-discord

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yamato-main/gemini-discord/discord-troubleshooting/github.svg)](https://agentmods.dev/skills/yamato-main/gemini-discord/discord-troubleshooting)

Your own site

<a href="https://agentmods.dev/skills/yamato-main/gemini-discord/discord-troubleshooting"><img src="https://agentmods.dev/badge/skills/yamato-main/gemini-discord/discord-troubleshooting/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yamato-main/gemini-discord/discord-troubleshooting"><img src="https://agentmods.dev/badge/skills/yamato-main/gemini-discord/discord-troubleshooting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,217 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00054	$0.01217
Opus 5.5	$0.00022	$0.00487
Sonnet 5.5	$0.00011	$0.00243
Haiku 4.5	$0.00005	$0.00122

Measured 2mo ago against content hash 01127fc20594, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

discord-troubleshooting 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 2mo 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.

skills/discord-troubleshooting/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Core Concepts

When the gemini-discord extension is installed, the bot might fail to connect due to missing Discord Developer Portal settings, an invalid bot token, or local networking conflicts.

This skill provides a systematic diagnosis and resolution flow to ensure the bot is successfully connected and online.

Workflow Patterns

1. Diagnose Gateway Status

Start by checking if the daemon is running and what its current status is:

Read the daemon log file at .gemini-discord/daemon.log (relative to the extension installation directory).
Look for the last startup sequence and any errors, specifically gateway close codes or startup failures:
- 4014 (Disallowed Intents): The bot is requesting privileged intents (Message Content and/or Server Members) that are not enabled in the Discord Developer Portal.
- 4004 (Invalid Token): The configured DISCORD_BOT_TOKEN is invalid or expired.
- Port in use: The daemon logs Port <number> in use, trying next... or older installs fail with ❌ ERROR Port in use. Is the daemon already running?.
- ECONNREFUSED: The daemon control API server is not running or unreachable on its configured port.

2. Resolve Intent Issues (4014 / Disallowed Intents)

If you identify a 4014 disconnect code, you have two options to resolve it:

Option A: Frictionless Fallback (Recommended First Step)

Disabling the optional Server Members Intent in your configuration bypasses the requirement to toggle it in the developer portal:

Update .env or configuration to include:

DISCORD_ENABLE_SERVER_MEMBERS_INTENT=false

Restart the daemon. The bot will connect successfully as long as the Message Content Intent is enabled. Note: The daemon now includes automatic pre-flight probe validation and will dynamically fall back to false if the portal toggle is missing.

Option B: Guide User to Enable Intents in Portal

If the Message Content Intent itself is missing, the bot cannot connect and you must instruct the user:

Tell the user to go to the Discord Developer Portal.
Select their bot application and click on the Bot tab on the left sidebar.
Scroll down to the Privileged Gateway Intents section.
Toggle on Message Content Intent (Mandatory) and Server Members Intent (Optional but enabled by default in configuration).
Save changes.

Read the full file on GitHub · 83 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.

2mo ago First seen · 83 lines · 54 tokens per session scan A 01127fc20594

Subscribe to this mod's changes

discord-troubleshooting is a skill published in the GitHub repository Yamato-main/gemini-discord (5 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 1,217 once invoked, about $0.0002 per session on Opus 5.5. 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.

Debugging TypeScript discord discord-bot gemini-cli gemini-cli-extension mcp

discord-troubleshooting next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
discord-troubleshootingYamato-main/gemini-discord	Skill	5	yesterday	MIT	A	54	Claude Code, Codex
nodejs-keccak256Jamkris/everything-gemini-code	Skill	93	5mo ago	MIT	A	51	Claude Code, Codex
canary-watchJamkris/everything-gemini-code	Skill	93	5mo ago	MIT	A	13	Claude Code
debug-assistantrichardcb/oh-my-gemini	Skill	18	7mo ago	MIT	A	39	Claude Code, Codex
quick-fixrichardcb/oh-my-gemini	Skill	18	7mo ago	MIT	A	55	Claude Code, Codex
troubleshooternielsvbrecht/victoriametrics-logs-mcp	Skill	1	7mo ago	Apache-2.0	A	15	Claude Code, Codex
benchmarkJamkris/everything-gemini-code	Skill	93	5mo ago	MIT	A	8	Claude Code, Codex