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.
npx skills add Yamato-main/gemini-discord --skill discord-user-awarenessgit clone --depth 1 https://github.com/Yamato-main/gemini-discordWrote 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/skills/yamato-main/gemini-discord/discord-user-awareness)<a href="https://agentmods.dev/skills/yamato-main/gemini-discord/discord-user-awareness"><img src="https://agentmods.dev/badge/skills/yamato-main/gemini-discord/discord-user-awareness/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/skills/yamato-main/gemini-discord/discord-user-awareness"><img src="https://agentmods.dev/badge/skills/yamato-main/gemini-discord/discord-user-awareness.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 | $0.00052 | $0.00692 |
| Opus 5 | $0.00026 | $0.00346 |
| Sonnet 5 | $0.00010 | $0.00138 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
discord-user-awareness 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 12d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discord user awareness
Boss vs guest allowlist (critical)
| Setting | Who | Powers |
|---|---|---|
DISCORD_BOSS_USER_ID |
One human operator | Full bridge: user discovery, allowlist, admin, moderation |
DISCORD_ALLOWED_USER_IDS |
Other humans | Chat only when guests are disabled — no user lists, no admin tools |
Never put the bot's user ID in either field. Putting the bot on the guest allowlist does not give it admin powers — it only pollutes config.
When to use
- The user wants to add or remove someone from the guest allowlist.
- The request refers to another person, "the other user", a display name, or a vague target.
- You need a stable numeric Discord user ID for
allowlist_add,kick, ortimeout. - The message includes
@pings and you must not confuse users, roles, channels, @everyone/@here, or this bot.
@ mention rules
Every incoming Discord message includes a [Mentions] block. Trust it over guesswork:
| Signal | Meaning |
|---|---|
| User pings | Real <@userId> mentions — humans or bots, each with a stable id |
| This bot | Your bridge identity — never "the other user" |
| Role pings | <@&roleId> — not a user; do not allowlist or moderate as a person |
| Channel refs | <#channelId> — use channel discovery, not user discovery |
| @everyone / @here | Broadcast only — not a specific member |
Plain @Name in text |
Not a ping unless it appears under User pings |
When the user says "the other user" while pinging you, the target is a different human from the User pings list (or run users discovery).
Workflow
- Run
discord_adminwith actionstatusif you do not already know the bot's own ID (shown as Bot:name(id)). - Run
discord_adminwith actionusers. Passquerywhen the user named someone or you need to narrow the list. - Pick a human from the Humans section. Never use an ID from Bots or the bot's own ID from status.
- Run
allowlist_addor moderation with the resolveduser_id.
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.
- 12d ago First seen · 56 lines · 52 tokens per session scan A 64f40088d6aa
discord-user-awareness is a skill published in the GitHub repository Yamato-main/gemini-discord (5 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 692 once invoked, about $0.0003 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.
Other skills, from other repositories
novel-archiving
A writing-workflow skill for archiving each completed novel chapter. It creates a chapter summary and updates files that record characters, plot clues, the timeline, relationships, and world details.
novel-memory
A file-based memory system for Chinese-language fiction projects. It stores story plans, character details, world rules, timelines, relationships, chapter summaries, and unresolved clues.
quadrants
Manage Quadrants tasks and projects via natural language. Use when the user wants to create, view, complete, or organize tasks on the Eisenhower Matrix. Supports listing projects, adding tasks (single or bulk), viewing priority tasks, completing tasks, and getting project overviews. Triggers on mentions of…
Hacker News
Search and browse Hacker News with API access to stories, comments, users, and hiring threads.
novel-worldbuilding
A Chinese-language skill for designing novel outlines, characters, fictional worlds, plot structure, and planned clues.
novel-research
A research aid for novel writing that searches for real-world details, checks story logic, and studies writing references. It is intended to support fiction rather than replace the author's judgment.