Borrowing it
Nothing to install: this file belongs to chrismdemian/claude-code-discord-bridge. 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/chrismdemian/claude-code-discord-bridge/main/AGENTS.mdgit clone --depth 1 https://github.com/chrismdemian/claude-code-discord-bridgeWrote 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/chrismdemian/claude-code-discord-bridge/agents-md)<a href="https://agentmods.dev/instructions/chrismdemian/claude-code-discord-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/chrismdemian/claude-code-discord-bridge/agents-md/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/chrismdemian/claude-code-discord-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/chrismdemian/claude-code-discord-bridge/agents-md.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 | $0.00686 | $0.00686 |
| Opus 5 | $0.00343 | $0.00343 |
| Sonnet 5 | $0.00137 | $0.00137 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
claude-code-discord-bridge AGENTS.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 yesterday.
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-code-discord-bridge
A Claude Code plugin that mirrors Claude Code sessions to Discord. Every running instance
appears as a forum post, you see what Claude does live, and you can send prompts back from
a phone. Two halves with different lifetimes: the plugin (server.ts) is an MCP channel
server running inside Claude Code and dies with it, handling Discord to Claude Code; the
bridge service (bridge/) is a persistent pm2-managed process that stays alive and handles
Claude Code to Discord.
Stack
Bun, TypeScript, discord.js v14, @modelcontextprotocol/sdk, pm2.
Rules
- Discord's limits are hard edges, not guidance: 2,000 characters per message (chunk long output), 4,096 per embed description, 5 requests per 2 seconds per webhook.
- Hook timeouts differ by type — 30s for
http, 600s forcommand. PermissionRequest must be acommandhook because it needs the 600s window; everything else useshttp. - Hooks are defined in
hooks/hooks.jsonand auto-merged with the user's own. Never write to theirsettings.json. createWebhook's avatar must be a Buffer or a data URI. A file path fails.- On Windows, stop a session with
taskkill /PID, notprocess.kill(pid, 'SIGINT'). - Components V2 requires the
MessageFlags.IsComponentsV2flag. - All Discord output goes through the formatter pipeline, one responsibility per file under
bridge/formatters/. Catch and log errors rather than letting the bridge crash. - Prefer Bun APIs where they exist (
Bun.file,Bun.serve,Bun.spawn). - Commit messages describe what was built. No phase numbers, no build-plan references, no attribution or Co-Authored-By trailers.
- After a build phase, run that phase's test criteria from
PRODUCT.md§25 and fix what a review turns up before committing. Do not move on with failing tests.
Interfaces that are not obvious from the code
- Claude Code writes session transcripts as JSONL at
~/.claude/projects/{encoded-path}/{session-id}.jsonl. The bridge tails these for live output. - Running sessions write PID files to
~/.claude/sessions/{pid}.json, watched with chokidar. - Injecting Discord messages into a session uses the
notifications/claude/channelMCP capability. - One session equals one forum post, tagged by status (Active/Completed/Error) and model. A single "Claude" webhook carries all output; the formatters differentiate with emoji prefixes and embed colours.
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.
- yesterday First seen · 52 lines · 686 tokens per session scan A dfba88d59d14
claude-code-discord-bridge AGENTS.md is an instructions file published in the GitHub repository chrismdemian/claude-code-discord-bridge (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 686 tokens to every session, about $0.0034 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 2026-09-16.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).