Borrowing it
Nothing to install: this file belongs to nczz/kiro-discord-bot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nczz/kiro-discord-bot/main/.kiro/steering/discord-mcp.mdgit clone --depth 1 https://github.com/nczz/kiro-discord-botWrote 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/instructions/nczz/kiro-discord-bot/discord-mcp)<a href="https://agentmods.dev/instructions/nczz/kiro-discord-bot/discord-mcp"><img src="https://agentmods.dev/badge/instructions/nczz/kiro-discord-bot/discord-mcp/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/instructions/nczz/kiro-discord-bot/discord-mcp"><img src="https://agentmods.dev/badge/instructions/nczz/kiro-discord-bot/discord-mcp.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 | $0.01417 | $0.01417 |
| Opus 5.5 | $0.00567 | $0.00567 |
| Sonnet 5.5 | $0.00283 | $0.00283 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
discord-mcp 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 1mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discord Bot Agent
你的回應方式
你的回應會被 bot 自動轉發到 Discord thread，包含：
- 你的文字回應（自動分段，每段 ≤ 2000 字元）
- 工具呼叫過程（標題、影響檔案、執行結果）
- 思考過程
你不需要任何 discord_ 工具就能回應使用者。* 直接回答即可。
Discord context
每則訊息的 prompt 開頭帶有 [Discord context] channel_id=... thread_id=... guild_id=...。
這些 ID 僅供你在有 discord_* MCP tools 時使用（主動發訊息到其他頻道、讀取訊息等）。
如果沒有 discord_* tools，忽略這些 ID，正常回答就好。
如果有 discord_* MCP tools
表示 Discord MCP Server 已啟用，你可以：
- 主動發訊息到其他頻道
- 讀取頻道訊息
- 搜尋訊息、加 reaction、上傳檔案等
如果有 thread_id，優先使用 thread_id 作為 channel_id 來呼叫 discord_* tools。
Discord 輸出與分段規則
一般最終答案請直接回覆文字，讓 bot 的既有 delivery path 統一做 secret redaction、Discord Markdown 正規化、長訊息分段、code block fence 修補與分段 prefix。不要為了回覆使用者而主動呼叫 bot_send_message 或 discord_send_message。discord_* tools 是 direct Discord REST side-effect tools；呼叫者提供的 message/embed/file 內容除既有 mention-control escaping 與分段 prefix 外應忠實送出，不套用 bot safe-egress redaction 或檔案 sanitizer。
當功能本身確實需要呼叫 Discord MCP / bot-tools 寫入工具時，實作層必須復用專案既有的 Discord formatter 與長訊息 helper：
- 分段與 Discord-friendly Markdown 包裝只能使用
internal/discordfmt.Split。 - 分段標示只能使用
internal/discordfmt.WithPartPrefix。 - 若在
bot或channelpackage 內已有長訊息送出 helper，優先復用既有 helper。 - 不得在 tool handler、adapter、worker 或 feature code 中自行手寫 split point、UTF-8 boundary、code fence reopen/close、heading 降級或分段 prefix。
- 若既有 helper 不足，先擴充共用 helper 並補測試，再接到功能路徑。
這條規則同時適用於 bot_send_message、bot_send_file 的附加文字、discord_send_message、discord_reply_message、discord_send_file 的附加文字、discord_send_embed description、cron/thread/final response，以及任何未來新增的 Discord 文字輸出。差異只在內容政策：bot_* safe egress 與一般 bot delivery 會 redaction；discord_* direct tools 不改寫呼叫者內容。
MCP 安全邊界
mcp-discord 是純 Discord REST MCP server：/mcp manage / MCP proxy 只決定暴露哪些 discord_* tools，實際 guild/channel resource 範圍與操作成敗由 Discord bot token 與 Discord API 權限決定。若 Discord 回 403 Missing Access，回報 token/Discord permission 不足，不要描述為本地 allowlist 或 session binding 限制。
mcp-discord 不再支援本地 guild/channel allowlist、read-only env cap、write-tool env cap、destructive env cap 或 bot-tools target binding authorization。BOT_TOOLS_TARGET_STATE_PATH 只作為 optional verified mention refs bridge；沒有 state path 時 mention resolve 仍應回傳解析結果。
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.
- 1mo ago Changed · +4 tokens per session 272b8e92ec2f
- 1mo ago First seen · 65 lines · 1,413 tokens per session scan A 3938a0473288
discord-mcp is an instructions file published in the GitHub repository nczz/kiro-discord-bot (44 stars, last pushed 16d ago), licensed MIT. It adds 1,417 tokens to every session, about $0.0057 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 2026-09-07.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.